# How to Build & Sell AI Agents: Ultimate Beginner’s Guide

https://www.youtube.com/watch?v=w0H1-b044KY

[00:00] Two years ago, I taught myself how to build AI agents without any prior experience in AI.
[00:03] And since then, I've started multiple AI businesses that have generated over $5 million in revenue.
[00:10] I've grown from 0 to 450,000 subscribers here on YouTube.
[00:15] And I've built AI agents for some of the biggest companies in the world.
[00:18] It's pretty safe to say that learning how to build AI agents has completely changed my life.
[00:22] So, in this full course, I'm going to teach you everything, and I mean everything that I have learned over the past 2 years about building and more importantly making money with AI agents, even if you don't know how to code.
[00:33] My hope is that you too can learn and use this incredibly powerful skill in order to build the life of your dreams before these AI agents start taking our jobs.
[00:40] As you can see, by the length of this video, I'm not going to be holding anything back.
[00:43] So, in order to make it a bit easier to consume, we're going to be splitting it into three different chapters.
[00:47] First, we'll build your foundational understanding of AI agents, covering what they are, how they work under the hood, and the key concepts that you need to know before you actually start building them.
[00:58] And this is without any technical background required.
[00:59] Secondly, we will be diving into four different
[01:01] we will be diving into four different endto-end AI agent tutorials, taking you over my shoulder every step of the way as we build some of the most popular AI agent use cases on the market today.
[01:10] And I have carefully planned these builds out to give you a taste of multiple different noode platforms and different AI agent types.
[01:16] and you'll learn how to build each of these step by step watching over my shoulder.
[01:19] And finally, I will give you my proven blueprint for monetizing your AI agent building skills over the coming years while this technology continues to explode in adoption and popularity.
[01:28] I'll be sharing the exact strategies that I've used to generate millions of dollars with this skill set over the past 2 years.
[01:33] So, let's get into it.
[01:35] Now, if you're new to the channel, let me quickly share why I'm qualified to teach you about AI agents.
[01:40] So, if you are new to the channel and don't know who I am, my name is Liam Mley and 2 years ago, I started learning about AI with no prior experience in the field.
[01:47] I was teaching myself how to build AI agents and chat bots all through my own self-study, which I documented right here on this YouTube channel from day one.
[01:53] So, you can go back and watch all my previous videos of how I got from there to here.
[01:56] This led me to starting Morningside AI, which is my AI automation agency where we build AI systems and agents for
[02:02] we build AI systems and agents for businesses from basic customer support.
[02:04] businesses from basic customer support systems to full AI SAS platforms and even we've built my own AI agent SAS platform, Agent, which is now over 45,000 users.
[02:10] At Morningside, we've worked with publicly traded companies and even recently an MBA team.
[02:15] I also run the world's largest AI business community with over 120,000 members on school as of this recording.
[02:21] and through my community and through this YouTube channel here, I've taught hundreds of thousands of people from all backgrounds really how to build and make money from AI agents.
[02:30] So, everything that I'm about to teach you today is exactly what helped me to achieve all of this.
[02:34] So, let's dive in.
[02:39] Now, if you look at how long this video is, you'll realize that there is a lot to cover here.
[02:44] And now, I don't want you to give up halfway through the video.
[02:46] So, let's quickly take a moment just to get clear on why AI agents are quite literally the next big thing.
[02:51] And I know that sounds cliche and you hear it all the time, but seriously, they are.
[02:54] And why learning to build them is by far one of the most valuable skills that anyone can have over the coming decades.
[02:58] And if if my experience over
[03:02] decades.
[03:04] And if if my experience over the past 2 years is anything to go by, the past 2 years is anything to go by, that should be enough proof for you guys.
[03:05] that should be enough proof for you guys to believe me.
[03:07] So, stick with me.
[03:07] But here's the hard truth about AI and jobs right now.
[03:10] According to the latest research, McKenzie predicts that AI and agents could automate up to 50% of current work by 2030.
[03:14] And the World Economic Forum reports that 41% of companies plan to reduce their workforce due to AI.
[03:20] Now, a lot of this sounds doom and gloom, and of course, many people are naturally worried about their career in future based off seeing this kind of data.
[03:26] But it's not all bad if you know where to look.
[03:29] And this video isn't about making you feel all sad.
[03:32] It's about uplifting you.
[03:33] And if you look on the flip side of the same data, these same reports reveal an enormous opportunity for those willing to seize it.
[03:38] So the World Economic Forum's future of job report states that 50% of employees plan to reorient their business in response to artificial intelligence.
[03:44] And due to this reorientation, 66% of employees plan to hire talent with specific AI skills such as prompt engineering.
[03:53] So on one hand, we have the expectation of massive layoffs and automation of work over the next 5 to 10 years.
[03:58] But on the other, we have the majority of employers searching
[04:03] have the majority of employers searching for people who have these AI skills or for people who have these AI skills or really just basic AI literacy.
[04:08] really just basic AI literacy. Why?
[04:10] Because AI literate employees who can automate parts of their work can have 5 to 10x the output of someone who doesn't have any AI literacy.
[04:15] And I promise you that brushing up on your AI and reaching this point of AI literacy so that you can be on the winning side of this next 5 to 10 years is actually so much easier than you think.
[04:25] I mean, it's easy as watching this entire video in order to build your AI skills base to make a big step towards AI literacy.
[04:31] And if you don't believe me when I say that a little bit of self-study like this video goes a long way, here's a great clip that I've seen recently on the All-In podcast from one of the most respected investors and technologists in the world, Navar Raakan, alongside a whole bunch of other very smart billionaires.
[04:44] Again, I would say the easiest way to see that AI is not taking jobs or creating opportunities is go brush up on your AI.
[04:53] Learn a little bit, watch a few videos, use the AI, tinker with it, and then go reapply for that job that rejected you and watch how they pull you in.
[05:01] And so this video is exactly what Naval is talking about.
[05:02] So whether you're an aspiring entrepreneur wanting
[05:03] you're an aspiring entrepreneur wanting to learn valuable AI skills and launch.
[05:05] to learn valuable AI skills and launch an AI business like I have, or you're a.
[05:07] an AI business like I have, or you're a business owner wanting to just.
[05:09] business owner wanting to just understand agents so you can use them to.
[05:11] understand agents so you can use them to grow your business, or maybe you're just.
[05:13] grow your business, or maybe you're just wanting to make sure that you are the.
[05:14] wanting to make sure that you are the last person that your boss thinks of.
[05:16] last person that your boss thinks of firing because he or she's an AI wiz and.
[05:18] firing because he or she's an AI wiz and I can't afford to lose them.
[05:21] I can't afford to lose them. Then I have made this video for you guys.
[05:22] made this video for you guys. Now, what I want you to do is close out all of.
[05:23] I want you to do is close out all of your other tabs.
[05:25] your other tabs. Go get a notebook and a pen and a beverage of choice and make.
[05:27] pen and a beverage of choice and make sure you make a commitment to yourself.
[05:29] sure you make a commitment to yourself right now in order to finish this.
[05:31] right now in order to finish this training and ensure that you are going.
[05:32] training and ensure that you are going to be empowered by AI and not replaced.
[05:35] to be empowered by AI and not replaced by it. Now, if you've done all that.
[05:36] by it. Now, if you've done all that, let's get stuck into.
[05:39] let's get stuck into it. All right, so step one in building.
[05:41] it. All right, so step one in building AI agents is knowing what the hell an.
[05:43] AI agents is knowing what the hell an agent actually is.
[05:45] agent actually is. So, 2 years ago, when I first started learning about AI.
[05:47] I first started learning about AI agents, I had no idea what they actually.
[05:49] agents, I had no idea what they actually were. The term AI agent gets thrown.
[05:51] were. The term AI agent gets thrown around a lot in almost like everywhere.
[05:52] around a lot in almost like everywhere these days. You got AI agents this, AI.
[05:54] these days. You got AI agents this, AI agents that. But what actually is an AI.
[05:57] agents that. But what actually is an AI agent? Well, the clearest definition.
[05:58] agent? Well, the clearest definition that I found that helps beginners to.
[05:59] that I found that helps beginners to really wrap their head around what they.
[06:01] really wrap their head around what they are is this. An AI agent is a digital.
[06:03] are is this. An AI agent is a digital worker that can understand instructions.
[06:06] worker that can understand instructions and take actions in order to complete and take actions in order to complete tasks.
[06:10] So, in a very simple way, just like businesses have employees who handle different tasks, an AI agent is like having a digital employee.
[06:14] But the cool thing is that you can build them and you can make them do whatever you want.
[06:20] You're like literally building an employee that you can put to work to do things for you.
[06:23] And of course, they cost much less to run than a human and they don't need sick days and they don't start beef with Mike over in the sales department because of his comment at the coffee machine.
[06:32] So, I'm sure you can see the appeal of this kind of digital work and AI agents to businesses who are looking to adopt them.
[06:41] In order to really understand why these AI agents are such a big deal, we need to look at where we are coming from.
[06:47] So most of you have probably encountered those chat bots on websites before.
[06:50] You know those little little chat widgets that pop up saying like, "Hey, how can I help you?"
[06:55] So these kinds of chat bots are pretty basic, right?
[06:57] They a lot of the time they're useless and they're they're kind of like a waiter who can only really recite the menu but can't actually take your order or or bring your food.
[07:03] They can't do anything.
[07:05] They just respond with some kind of
[07:06] just respond with some kind of pre-written answers.
[07:08] Well, nowadays it's pre-written answers.
[07:08] Well, nowadays it's a simple AI generated answer.
[07:10] But AI a simple AI generated answer.
[07:10] But AI agents are different, right?
[07:13] So, here's an example.
[07:15] If you ask a regular chatbot about booking an appointment, it might say, "Oh, our business hours are 9 to5.
[07:19] Please call to book."
[07:21] And that's it.
[07:22] They just give you some information back.
[07:25] But with an AI agent, it could actually go and check the calendar, find some available slots, go back and forth with the person that they're chatting to in order to book an appointment, send you a confirmation email, then update the business's scheduling system and CRM automatically in seconds.
[07:39] This ability to take action is what makes agents so powerful.
[07:41] They're not just fancy chat bots.
[07:42] They're actually digital workers who can search through databases, update spreadsheets, send emails, book appointments, generate hold documents, and much much more.
[07:54] And so building and deploying an AI agent is a bit like hiring a new employee because when you bring someone into a business, you need to firstly explain their roles and the responsibilities to them.
[08:04] You need to give them access to your system so they can use them.
[08:06] And you need to trust them
[08:08] can use them.
[08:08] And you need to trust them to handle those tasks independently.
[08:10] And to handle those tasks independently.
[08:10] And now when we are building agents, as we see later, it's exactly the same, except these agents are going to be working 24/7.
[08:15] They're never going to get tired.
[08:17] They can be duplicated and modified instantly.
[08:19] And they cost a fraction of what a human employee does.
[08:21] And this is exactly why understanding how to build and sell AI agents is becoming such a crucial and valuable skill these days.
[08:27] Because whether you're an entrepreneur looking to scale your business or you're an employee wanting to become irreplaceable and and make more money at work, knowing how to create and deploy these digital workers is like the biggest cheat code in the whole world right now.
[08:44] Now that you understand what AI agents actually are, let's look under the hood and see how they actually work.
[08:50] Just like humans need a brain, memory, and tools in order to do their job, AI agents need specific components in order to function correctly.
[08:57] An AI agent needs five key parts in order to work.
[08:59] Firstly, every AI agent needs a brain.
[09:01] In the AI world, we call this a large language model or an LLM for short.
[09:03] And you've probably heard of some of these.
[09:08] You've probably heard of some of these.
[09:11] You've got GPT from OpenAI, Claude from Anthropic, Gemini from Google, etc.
[09:13] You can think of the LLM as having a super smart intern who can understand your instructions in plain English, and then figure out how to get things done from those instructions.
[09:22] So, without this brain, all of the other parts would be useless, right?
[09:25] It's like having a whole desk full of office supplies but having no one sitting there in order to use them.
[09:30] Secondly, the brain needs instructions on how to behave.
[09:32] And this is prompting.
[09:34] So writing a prompt for an agent is how you program a lot of the behavior of it rather than having to code it manually.
[09:39] And this is really what makes building AI agents so much more accessible to non-coders as the way of actually programming the functionality and how they work is done through clearly written instructions rather than having to actually code it.
[09:52] Thirdly, agents need memory.
[09:53] Imagine trying to have a conversation with someone who forgets everything you said 30 seconds ago, right?
[09:56] So, memory is really important because it allows your agent to remember what you talked about just a few messages ago, keep track of the tasks that it's been working on, build on previous conversations, and even in more advanced ones, it can learn from your past interactions.
[10:08] And the
[10:09] from your past interactions.
[10:11] And the good news about memory is that most AI agent platforms completely handle this memory component automatically.
[10:15] So, you don't need to worry too much about it.
[10:16] But just know that it is an important part of a functioning AI agent.
[10:19] The fourth component of an agent, and this one is optional, but it is external knowledge.
[10:22] AI models like GPT and Gemini are pre-trained on a huge amount of data, but that data is basically cut off at a certain point, eg 2024.
[10:29] It's kind of like having a new employee who only really knows what they learned in school.
[10:35] But just like you can train an employee like that with your company's specific materials, you can also give an AI agent additional knowledge on top of the information it was trained on through providing things like PDFs of your company documents, spreadsheets with product information, customer service transcript, or basically any other textbased information.
[10:54] Without this added knowledge, agents will be limited to general information and couldn't handle specific business tasks.
[10:59] But as I said, knowledge is optional and you will only need it in some builds.
[11:02] Finally, and this is the most important part, we have tools.
[11:04] So tools are what transform an AI agent from just being able to chat to being able to actually
[11:11] able to chat to being able to actually get things done.
[11:12] So you can think of tools like giving your digital employee access to different softwares.
[11:16] Just like you might give a new hire access to your email or your calendar or your CRM system, you can give an AI agent access to digital tools that let it take actions when needed.
[11:24] These tools let your agent do things like checking real-time data, updating databases, sending messages and notifications, creating documents, all the stuff we went over just before and much, much more.
[11:35] The really powerful part, which we're going to cover later, is when agents use multiple tools together in order to solve complex problems, just like us humans would use multiple different websites and softwares when doing our tasks.
[11:46] Now, let me show you how all of these parts work together in a real example.
[11:47] So, say you want an agent to handle customer support.
[11:50] When the agent is sent a message, the brain immediately understands the prompt that it has been given and also understands what the customer is asking.
[12:01] It checks its recent memory before replying each time to understand the full context of their conversation.
[12:05] And if the brand detects that the customer wants a specific question answered from the knowledge base, it will use its external knowledge in order to deliver the right
[12:12] knowledge in order to deliver the right information to them.
[12:14] And finally, it may use tools to update a customer's account or to process a refund whenever required during the conversation.
[12:20] So all of these things are happening in seconds as the conversation is going on.
[12:21] Which is why AI agents are such a game changer.
[12:23] They can combine all of these components in order to create a fully capable digital worker that very very closely replicates how humans work.
[12:34] Now that you know the anatomy of an agent and the five parts of it, a more practical framework for understanding how we actually plan and build AI agents is what I call the three ingredients.
[12:44] Basically, you only have three elements to plan when creating an AI agent, which when mixed in various ways can create millions and different types of agents for different use cases.
[12:53] This is because the AI model or brain can be easily swapped in and out and isn't really a major factor in the performance of the agent as any of the top models that you pick from any of the different providers at any given time, they're all pretty good.
[13:04] And also, the recent chat memory is handled by default in almost all cases when you're building on these platforms that you're going to see later.
[13:09] What this leaves us with is what really matters when building and
[13:12] what really matters when building and planning AI agents.
[13:14] Firstly, the knowledge, the external data that you want the agent to be able to use when answering.
[13:17] Secondly, the tools, the different actions that you want the agent to be able to take, eg saving the contact info to the CRM or getting some live data on stocks or sending an email.
[13:27] And then finally, prompting, which is the glue that ties everything together and determines how the agent behaves.
[13:33] So, write these down.
[13:35] While the agent has five components, the brain, the prompt, the memory, the knowledge, and tools, your main focus as an AI agent builder is in the three ingredients of prompting, knowledge, and tools.
[13:44] In the next chapter, we'll be looking at how you actually build an agent using the different combination of these three ingredients.
[13:48] But first, we need to dive deeper into the keystone of understanding how to build your own valuable digital workers.
[13:53] And it all comes down to tools.
[13:58] Now, we need to dig a lot deeper on tools as they are by far the most powerful part of AI agents.
[14:05] But in order to understand deeply and be able to build powerful agents with them, we need to take a few steps back and actually cover the basics of how software and the web and internet as a
[14:14] software and the web and internet as a whole works.
[14:16] Now, this is as techy as it's going to get in this video, but I promise once you understand this, it's so important and it's literally like having a superpower.
[14:22] So, please stick with me through this.
[14:24] So, remember how we said that tools are what allow agents to take an action to actually do things rather than just chat?
[14:30] Well, the way agents use tools and do work online is just how we do it as well, but with one key difference.
[14:37] Instead of clicking buttons and typing into forms, agents use what we call APIs.
[14:42] And every time you use the internet, you're actually making dozens of requests to APIs as well and getting responses back, but you just don't realize it.
[14:49] So, let me show you what I mean.
[14:51] So, when you click on this video, here's what actually happened.
[14:56] Firstly, your browser sent a request to YouTube servers saying, "Hey, I want to watch this video."
[15:00] And then YouTube servers sent back all of the data needed.
[15:05] And thirdly, your browser unpacked that data and started playing the video on your screen.
[15:08] So this request and response pattern happens with almost everything that you do online.
[15:13] When you open up Instagram, you are requesting your feed from Instagram
[15:15] are requesting your feed from Instagram service.
[15:17] When you send a tweet, you are service.
[15:19] When you send a tweet, you are sending your data through Twitter's service.
[15:20] And when you check your email, you are requesting from Google the latest messages in your inbox and they're sending it back and your browser is loading it.
[15:22] And when you check your email, you are requesting from Google the latest messages in your inbox and they're sending it back and your browser
[15:24] latest messages in your inbox and they're sending it back and your browser
[15:25] they're sending it back and your browser is loading it.
[15:27] is loading it. Thankfully, we get pretty websites and apps that make it very easy for us to do this and use software via APIs through a nice application.
[15:29] websites and apps that make it very easy for us to do this and use software via APIs through a nice application.
[15:31] for us to do this and use software via APIs through a nice application. But under the hood, it is still two computers talking back and forth, requesting, sending, and displaying new information for us on our screen.
[15:33] APIs through a nice application. But under the hood, it is still two
[15:34] under the hood, it is still two computers talking back and forth, requesting, sending, and displaying new information for us on our screen.
[15:36] computers talking back and forth, requesting, sending, and displaying new information for us on our screen.
[15:38] requesting, sending, and displaying new information for us on our screen. These request and response happen through what we call APIs, which are application programming interfaces.
[15:40] information for us on our screen. These request and response happen through what we call APIs, which are application programming interfaces.
[15:41] request and response happen through what we call APIs, which are application programming interfaces.
[15:43] we call APIs, which are application programming interfaces. So, you can think of APIs like waiters in a restaurant.
[15:45] programming interfaces. So, you can think of APIs like waiters in a restaurant.
[15:47] think of APIs like waiters in a restaurant. Basically, they're going to take your order or your request to the kitchen, which are the servers of the business, and then they bring back your food, which is the response.
[15:48] restaurant. Basically, they're going to take your order or your request to the kitchen, which are the servers of the business, and then they bring back your food, which is the response.
[15:50] take your order or your request to the kitchen, which are the servers of the business, and then they bring back your food, which is the response.
[15:52] kitchen, which are the servers of the business, and then they bring back your food, which is the response.
[15:54] business, and then they bring back your food, which is the response. So, you have request and response, and you have you as the client, and them as the server.
[15:56] food, which is the response. So, you have request and response, and you have you as the client, and them as the server.
[15:57] have request and response, and you have you as the client, and them as the server.
[15:59] server. There are two main types of requests that you can make. Firstly, either a get request. This is basically just like asking for information like checking the weather or looking up the price or loading this video.
[16:01] server. There are two main types of requests that you can make. Firstly, either a get request. This is basically just like asking for information like checking the weather or looking up the price or loading this video.
[16:02] requests that you can make. Firstly, either a get request. This is basically just like asking for information like checking the weather or looking up the price or loading this video.
[16:05] either a get request. This is basically just like asking for information like checking the weather or looking up the price or loading this video.
[16:07] just like asking for information like checking the weather or looking up the price or loading this video. You're requesting to get the information to do something.
[16:08] checking the weather or looking up the price or loading this video. You're requesting to get the information to do something.
[16:10] price or loading this video. You're requesting to get the information to do something. Secondly, we have post requests, which is when you're sending
[16:12] requesting to get the information to do something. Secondly, we have post requests, which is when you're sending
[16:14] something. Secondly, we have post requests, which is when you're sending
[16:15] requests, which is when you're sending some kind of information like posting a tweet, sending an email, or uploading a photo.
[16:21] So, go back and write both those down because we're going to be using them extensively in the building section of this video.
[16:26] Now, here's where it gets interesting.
[16:28] So, AI agents use these same APIs as their buttons to do things.
[16:32] So, each tool an agent has access to use is essentially an API that it is able to call.
[16:36] So, these kinds of tools come in two different flavors.
[16:38] We have pre-made integrations like Google Calendar or Gmail where it kind of comes out of the box ready for you to use and just plug straight into your agent.
[16:45] And then we have custommade tools that we can build ourselves.
[16:49] So you can think of pre-made integrations like buying a readymade meal where they've done a lot of the hard work versus custom tools where we are like cooking from scratch.
[16:57] And both work, but custom tools give you a lot more control.
[17:00] And this is a skill that I'm going to be teaching you in the second chapter of this video.
[17:04] Okay.
[17:06] So now you got the basics.
[17:07] Let's get clear on how a tool is actually made and what the key parts are as you're going to be using them a lot.
[17:11] So, let's break this down using a simple example of a text capitalization tool.
[17:15] example of a text capitalization tool.
[17:17] It takes in some text and the outputs the capitalized version of it.
[17:19] So, first to create a tool, we need a function.
[17:21] We need something that does work.
[17:23] In this case, it's super simple, right?
[17:24] It needs to take in text and it needs to make it uppercase.
[17:26] So, this can either be done through a basic Python function or you can use an LLM to do this as well.
[17:31] Basically, we need to build some way to capitalize the text that we give to this function and actually do the do the work.
[17:39] Next, in order for the AI agent to use this function, we need to wrap it in an API.
[17:42] So, we have the function and then the API wraps around it.
[17:44] And this is essentially making that functionality we created accessible over the internet via APIs.
[17:51] Without it, the function cannot be used by our agent.
[17:53] And in order to use the API that we've just created and use this function inside it, the API is going to expect the same sort of inputs that the function needs.
[18:01] So the input of the text that we want to capitalize and it's going to output the capitalized version.
[18:06] So this is very important to remember function.
[18:08] It takes in the input of the uncized text does work and outputs the capitalized version.
[18:14] We're basically then just building an API around it so that we can
[18:16] building an API around it so that we can put it on the internet and then we can put it on the internet and then we can have an agent that knows how to call that API.
[18:19] can send information into the input go through the function and then get spit out and then our agent catches it at the end.
[18:27] But the magic step and what has really caused the AI revolution to kick off is that we can explain to our agent how to use this API just by explaining how the API works in natural language.
[18:40] And this is where schemas come in.
[18:42] A schema is like a one-page instruction manual on how to use an API and therefore how to access the functionality inside that API.
[18:48] And when an AI agent is given one of these schemas, it too can read that instruction manual and determine things like what the tool does, what information it needs as an input, like we talked about before, and what information to expect as an output.
[19:02] Now, they may look scary, but they're actually really, really easy to understand, and we're going to cover them in the next chapter with this video.
[19:08] And the good part about it is that these days, schemas are automatically created by many of these no code platforms that you build agents on.
[19:14] But I'm teaching you this because it still helps to know what they are doing and what that what's really happening
[19:17] and what that what's really happening under the hood on these platforms.
[19:19] And under the hood on these platforms.
[19:19] And there are still going to be times where there are still going to be times where you may need to roll up your sleeves and you may need to roll up your sleeves and do it yourself.
[19:22] The incredible part about these schemas is that modern AI like chatpt can read these instructions and perfectly understand not just how to use it and like okay I need an input and then I expect an output but also when to use it.
[19:32] For example, let's say we had an agent and we gave it that capitalization tool that we just talked about and then we said can you please capitalize this text?
[19:39] Mary had a little lamb.
[19:41] The agent would then read over the schemas that we provided it and then it would see that there's a tool with a description saying this tool capitalizes text right in the instructions for the capitalization tool.
[19:50] We would have said this thing is for capitalizing text and it takes in some text and it gives you the capitalized version.
[19:57] And so the agent will read that and see okay this looks like based off the instruction they just gave this is the tool that they want to use.
[20:03] And then it will check the requirements and see that the tool takes in one input in string format which is just text which we have described as the text to be capitalized.
[20:11] So it reads all this.
[20:13] He says okay it it needs one input.
[20:15] It's in string format.
[20:15] So I know I need to give it some text and okay what does this text do?
[20:17] It's the text
[20:18] what does this text do? It's the text that they want to capitalize. Great. So
[20:20] that they want to capitalize. Great. So now it knows it needs the input and it
[20:22] now it knows it needs the input and it knows that this is where it's going to
[20:23] knows that this is where it's going to send the text to be capitalized. Then
[20:24] send the text to be capitalized. Then now that it knows what it wants, it goes
[20:26] now that it knows what it wants, it goes back to our message and it intelligently
[20:28] back to our message and it intelligently extracts Mary had a little lamp. not,
[20:30] extracts Mary had a little lamp. not, hey, can you please capitalize Mary had
[20:32] hey, can you please capitalize Mary had a little lamb? It's smart enough to know
[20:33] a little lamb? It's smart enough to know that we want that taken out. So, it will
[20:35] that we want that taken out. So, it will take that part, Mary had a little lamb,
[20:37] take that part, Mary had a little lamb, out of our input, and then it sends that
[20:39] out of our input, and then it sends that to the API where our capitalization
[20:42] to the API where our capitalization function does its thing. Then the API
[20:43] function does its thing. Then the API sends back the capitalized version plus
[20:46] sends back the capitalized version plus a bunch of other response data as well.
[20:48] a bunch of other response data as well. Then the agent looks at your original
[20:50] Then the agent looks at your original question, looks at this messy response
[20:52] question, looks at this messy response it got back from the API, and then using
[20:54] it got back from the API, and then using its brain, the LLM, it writes a natural
[20:56] its brain, the LLM, it writes a natural language response answering your
[20:58] language response answering your question. It would say, "Here's your
[20:59] question. It would say, "Here's your capitalized text colon Mary had a little
[21:02] capitalized text colon Mary had a little lamb in all caps." That may sound
[21:03] lamb in all caps." That may sound complicated. It may have gone over your
[21:04] complicated. It may have gone over your head. Please go back and just listen to
[21:06] head. Please go back and just listen to it again. You really, really need to
[21:08] it again. You really, really need to understand this process of uh the
[21:10] understand this process of uh the message comes in, looks at the schema,
[21:11] message comes in, looks at the schema, realizes, okay, it wants to use this
[21:13] realizes, okay, it wants to use this tool. Okay. What do I need to do in
[21:14] tool. Okay. What do I need to do in order to use this tool? Okay. Well, then
[21:16] order to use this tool? Okay. Well, then I'm going to grab it out of the input.
[21:18] I'm going to grab it out of the input. I'm going to put it in here. And it can
[21:19] I'm going to put it in here. And it can actually go back and forth. Say our
[21:21] actually go back and forth. Say our capitalization tool needed some other
[21:22] capitalization tool needed some other input. Say you needed to provide uh the
[21:25] input. Say you needed to provide uh the number of letters you wanted to be
[21:26] number of letters you wanted to be capitalized. It may see that this tool
[21:28] capitalized. It may see that this tool needs two inputs and I've only been
[21:30] needs two inputs and I've only been given one. So then it will go back and
[21:32] given one. So then it will go back and ask me, hey, could you can you please
[21:34] ask me, hey, could you can you please tell me how many letters you want to be
[21:35] tell me how many letters you want to be capitalized and you will see this magic
[21:37] capitalized and you will see this magic in the agents that we're going to build.
[21:39] in the agents that we're going to build. When the agent can ask you questions in
[21:40] When the agent can ask you questions in order to help fulfill the needs of the
[21:42] order to help fulfill the needs of the tool, you have this very intelligent
[21:43] tool, you have this very intelligent system that really will blow you away
[21:45] system that really will blow you away when you see it in action. And one thing
[21:46] when you see it in action. And one thing many people miss about this process is
[21:48] many people miss about this process is the agent actually gets back raw
[21:50] the agent actually gets back raw computer data from the API or what we
[21:52] computer data from the API or what we call JSON. But using the LLM, it can
[21:55] call JSON. But using the LLM, it can transform that into natural conversation
[21:56] transform that into natural conversation and answer your question in a very very
[21:59] and answer your question in a very very uh clear and concise way. So it's
[22:00] uh clear and concise way. So it's basically like having an employee who
[22:02] basically like having an employee who can read all this technical information
[22:04] can read all this technical information and then explain it to you in plain
[22:05] and then explain it to you in plain English, which is another part of why AI
[22:07] English, which is another part of why AI agents are so powerful. And so when you
[22:09] agents are so powerful. And so when you understand this pattern that we've just
[22:10] understand this pattern that we've just gone through, I promise you, you will
[22:11] gone through, I promise you, you will never see the internet the same way
[22:13] never see the internet the same way again. Every action online is just
[22:15] again. Every action online is just requests and responses. And therefore,
[22:18] requests and responses. And therefore, we can build our own tools and AI agents
[22:20] we can build our own tools and AI agents to automate all of it. So instead of you
[22:22] to automate all of it. So instead of you manually searching the web, copying
[22:24] manually searching the web, copying information, pasting it into
[22:26] information, pasting it into spreadsheets, sending emails, an AI
[22:28] spreadsheets, sending emails, an AI agent can do it all automatically using
[22:29] agent can do it all automatically using tools if you build it correctly. It's
[22:31] tools if you build it correctly. It's like having a digital employee who can
[22:33] like having a digital employee who can press all of these API buttons for you
[22:36] press all of these API buttons for you thousands of times faster than any human
[22:38] thousands of times faster than any human could. And don't worry if this feels a
[22:39] could. And don't worry if this feels a little bit technical. In the next
[22:41] little bit technical. In the next chapter, uh I'm going to show you how to
[22:42] chapter, uh I'm going to show you how to create your own tools like this from
[22:44] create your own tools like this from scratch using platforms like Relevance
[22:46] scratch using platforms like Relevance AI, uh where you can build out powerful
[22:47] AI, uh where you can build out powerful tools without writing any code. and will
[22:49] tools without writing any code. and will really start to click into place once
[22:50] really start to click into place once you see the stuff in action in the
[22:52] you see the stuff in action in the building section. But before we get into
[22:53] building section. But before we get into that, let me reveal the power of AI
[22:55] that, let me reveal the power of AI agents which is unleashed when they are
[22:57] agents which is unleashed when they are given multiple tools to work
[23:00] given multiple tools to work with. Now, obviously having an AI agent
[23:02] with. Now, obviously having an AI agent that just capitalizes text isn't very
[23:04] that just capitalizes text isn't very useful. I get that. The real magic
[23:06] useful. I get that. The real magic happens when you give agents multiple
[23:08] happens when you give agents multiple tools and the ability to use them
[23:09] tools and the ability to use them together in order to achieve complex
[23:11] together in order to achieve complex goals. So, do you remember our
[23:13] goals. So, do you remember our definition? AI agents are workers that
[23:15] definition? AI agents are workers that can understand instructions and take
[23:16] can understand instructions and take actions to complete tasks. When you give
[23:19] actions to complete tasks. When you give an AI agent a task, it's going to try
[23:21] an AI agent a task, it's going to try its best to execute on it, but if it
[23:23] its best to execute on it, but if it doesn't have the right tools on hand to
[23:24] doesn't have the right tools on hand to do the job, it's going to be useless.
[23:26] do the job, it's going to be useless. And so, the more tools that you can give
[23:28] And so, the more tools that you can give an agent, the more flexibility it has to
[23:30] an agent, the more flexibility it has to solve problems just like a human would.
[23:32] solve problems just like a human would. So, let me give you a real example from
[23:33] So, let me give you a real example from my own business, right? Say I build an
[23:35] my own business, right? Say I build an agent and give it the task. Find AI
[23:37] agent and give it the task. Find AI startups that have recently raised money
[23:39] startups that have recently raised money and put them in a spreadsheet and add a
[23:41] and put them in a spreadsheet and add a summary of each of the businesses in the
[23:42] summary of each of the businesses in the spreadsheet and then email me the link
[23:44] spreadsheet and then email me the link to the spreadsheet. When you give an AI
[23:45] to the spreadsheet. When you give an AI agent a task like this and provide it
[23:47] agent a task like this and provide it with multiple tools to use, it can break
[23:49] with multiple tools to use, it can break down this problem just like a human
[23:51] down this problem just like a human would. For example, it might think first
[23:54] would. For example, it might think first I need to search for AI startups using
[23:56] I need to search for AI startups using my web searching tool. Okay, let's do
[23:57] my web searching tool. Okay, let's do that first. Then I'll need to create a
[23:59] that first. Then I'll need to create a new spreadsheet with my Google Sheets
[24:01] new spreadsheet with my Google Sheets tool. And then for each company that I
[24:03] tool. And then for each company that I find, I'll need to add a row to the
[24:04] find, I'll need to add a row to the spreadsheet. And then I'll need to write
[24:06] spreadsheet. And then I'll need to write a summary of each business and put it in
[24:07] a summary of each business and put it in a new column. And then finally, I'll use
[24:09] a new column. And then finally, I'll use my email tools in order to send the link
[24:10] my email tools in order to send the link to Liam. And that's all great, but then
[24:12] to Liam. And that's all great, but then when you add on top of that powerful
[24:14] when you add on top of that powerful reasoning models like OpenAI's 01 and 03
[24:16] reasoning models like OpenAI's 01 and 03 and even things like deepseat as the
[24:18] and even things like deepseat as the brain of the agent that can plan, take
[24:20] brain of the agent that can plan, take actions, then reflect and then plan
[24:22] actions, then reflect and then plan again and so on. You have essentially
[24:24] again and so on. You have essentially created a truly intelligent AI that
[24:26] created a truly intelligent AI that solves problems and approaches them just
[24:28] solves problems and approaches them just like a human would. So, say for example,
[24:30] like a human would. So, say for example, the original plan was to use the web
[24:32] the original plan was to use the web search tool to search for AI startups
[24:34] search tool to search for AI startups raising money. Probably a terrible
[24:35] raising money. Probably a terrible search term, but what if that doesn't
[24:38] search term, but what if that doesn't return any good results to the agent?
[24:39] return any good results to the agent? Well, a human would go, damn, I need to
[24:41] Well, a human would go, damn, I need to change my search term or maybe I need to
[24:43] change my search term or maybe I need to try find a different method of finding
[24:44] try find a different method of finding these companies on like LinkedIn or
[24:46] these companies on like LinkedIn or something. The latest in AI technology
[24:47] something. The latest in AI technology like these reasoning models, it allows
[24:49] like these reasoning models, it allows these agents to do this exact same kind
[24:51] these agents to do this exact same kind of reflection and replanning in order to
[24:54] of reflection and replanning in order to achieve their objective. And this is
[24:55] achieve their objective. And this is when you can really see why we call them
[24:57] when you can really see why we call them digital workers because they can do
[24:59] digital workers because they can do things like planning multiple steps.
[25:01] things like planning multiple steps. They will use different tools in a
[25:03] They will use different tools in a sequence and even adjust their approach
[25:05] sequence and even adjust their approach based on the results from those tools.
[25:07] based on the results from those tools. Now, I should mention that this
[25:08] Now, I should mention that this technology isn't perfect yet, right? So,
[25:10] technology isn't perfect yet, right? So, these multi-step tasks are often
[25:12] these multi-step tasks are often unreliable and agents typically need
[25:14] unreliable and agents typically need human supervision for more complex
[25:16] human supervision for more complex workflows. But things are moving
[25:19] workflows. But things are moving incredibly, incredibly fast. In fact,
[25:20] incredibly, incredibly fast. In fact, we're already seeing the next evolution,
[25:22] we're already seeing the next evolution, which is multiple agents working
[25:24] which is multiple agents working together. Instead of just one agent
[25:25] together. Instead of just one agent trying to do everything, you can have
[25:27] trying to do everything, you can have one main agent that you give orders to,
[25:29] one main agent that you give orders to, and then it can use all of the other
[25:30] and then it can use all of the other agents underneath it as tools where it
[25:32] agents underneath it as tools where it can send specific instructions. Like
[25:34] can send specific instructions. Like underneath the main agent might be a
[25:36] underneath the main agent might be a research agent, which is best at finding
[25:38] research agent, which is best at finding companies and has its own tools. Then
[25:39] companies and has its own tools. Then you have a writing agent that's really
[25:41] you have a writing agent that's really good at writing summaries. Then you have
[25:42] good at writing summaries. Then you have an emailing agent, which has got all the
[25:44] an emailing agent, which has got all the emailing tools. And so each of these
[25:45] emailing tools. And so each of these agents can be specialized in their
[25:47] agents can be specialized in their specific task with multiple tools. and
[25:49] specific task with multiple tools. and then they all work together to achieve a
[25:50] then they all work together to achieve a common goal. This is exactly what major
[25:53] common goal. This is exactly what major companies like HubSpot and Microsoft and
[25:54] companies like HubSpot and Microsoft and Google are building towards. It's these
[25:57] Google are building towards. It's these entire workforces of AI agents that can
[25:59] entire workforces of AI agents that can handle complex business processes
[26:00] handle complex business processes automatically. In the next chapter, I'll
[26:02] automatically. In the next chapter, I'll show you how to build AI agents like
[26:03] show you how to build AI agents like this for yourself using no code tools.
[26:05] this for yourself using no code tools. But first, we need to understand the
[26:06] But first, we need to understand the different ways that these agents can
[26:08] different ways that these agents can actually be used in the real
[26:11] actually be used in the real world. So, we understand how AI agents
[26:14] world. So, we understand how AI agents and tools work under the hood. Now,
[26:15] and tools work under the hood. Now, great. If you don't, please go back and
[26:18] great. If you don't, please go back and take some notes, right? You should by
[26:19] take some notes, right? You should by now have a whole bunch of notes um from
[26:21] now have a whole bunch of notes um from the stuff that we've covered already.
[26:22] the stuff that we've covered already. And this stuff that you're learning took
[26:23] And this stuff that you're learning took me two years in order to learn and and
[26:25] me two years in order to learn and and be able to apply effectively. So, you
[26:27] be able to apply effectively. So, you best believe it that it's going to take
[26:28] best believe it that it's going to take you two to three watches before it all
[26:30] you two to three watches before it all sinks in. So, if you're feeling a bit
[26:31] sinks in. So, if you're feeling a bit lost and and overwhelmed, don't worry.
[26:33] lost and and overwhelmed, don't worry. That's how it feels with learning
[26:34] That's how it feels with learning anything new or how it should feel if
[26:36] anything new or how it should feel if you're learning something that's
[26:37] you're learning something that's actually pushing your boundaries and
[26:38] actually pushing your boundaries and adding something to your to your
[26:39] adding something to your to your capabilities. Next, we need to look at
[26:41] capabilities. Next, we need to look at the different ways that AI agents can be
[26:43] the different ways that AI agents can be used in the real world. There are two
[26:45] used in the real world. There are two main categories of AI agents.
[26:47] main categories of AI agents. Conversational agents and automated
[26:49] Conversational agents and automated agents. Conversational agents are ones
[26:50] agents. Conversational agents are ones that humans interact with directly
[26:52] that humans interact with directly through chat on things like websites.
[26:55] through chat on things like websites. You've got maybe you're chatting to it
[26:56] You've got maybe you're chatting to it on WhatsApp. You've got interacting with
[26:58] on WhatsApp. You've got interacting with it over the phone via phone call. You've
[27:00] it over the phone via phone call. You've got chatting to it via Instagram DMs or
[27:02] got chatting to it via Instagram DMs or custom apps and websites. For example,
[27:04] custom apps and websites. For example, OpenAI's GPT platforms allows you to
[27:06] OpenAI's GPT platforms allows you to create agents that you can chat with
[27:08] create agents that you can chat with directly on your computer or on your
[27:09] directly on your computer or on your phone. or using platforms like my own
[27:11] phone. or using platforms like my own Agent, you can connect these agents that
[27:13] Agent, you can connect these agents that you build onto a WhatsApp number or onto
[27:15] you build onto a WhatsApp number or onto Instagram. And I'll show you how to do
[27:17] Instagram. And I'll show you how to do this in the tutorial chapter of this
[27:19] this in the tutorial chapter of this video. So, in all these cases, you or
[27:21] video. So, in all these cases, you or someone else is there sending messages
[27:23] someone else is there sending messages or instructions to the agent and
[27:25] or instructions to the agent and explaining what you want to do and kind
[27:26] explaining what you want to do and kind of chatting back and forth with it,
[27:28] of chatting back and forth with it, whether it's on a website, WhatsApp,
[27:29] whether it's on a website, WhatsApp, Instagram, or whatever. And within these
[27:31] Instagram, or whatever. And within these conversational agents, it's not just
[27:32] conversational agents, it's not just text based. It's like I said, there's AI
[27:34] text based. It's like I said, there's AI voice agents as well, which are an
[27:35] voice agents as well, which are an extremely exciting sector of the AI
[27:37] extremely exciting sector of the AI space right now. And these systems use
[27:39] space right now. And these systems use multimodal models that can take in audio
[27:42] multimodal models that can take in audio as input and then produce audio as an
[27:44] as input and then produce audio as an output. And so these agents can be
[27:46] output. And so these agents can be chatted to over the phone or via audio
[27:48] chatted to over the phone or via audio rather than via text. This AI voice
[27:50] rather than via text. This AI voice stuff is super cool. And in the tutorial
[27:52] stuff is super cool. And in the tutorial section, I'm going to show you how to
[27:53] section, I'm going to show you how to take the exact same AI agent that we can
[27:55] take the exact same AI agent that we can chat to on a website and then connect it
[27:57] chat to on a website and then connect it to a phone number and talk to it on the
[27:58] to a phone number and talk to it on the phone. But then we get to what I call
[28:00] phone. But then we get to what I call automated agents. And so these are
[28:02] automated agents. And so these are slightly different from the
[28:03] slightly different from the conversational ones. The truth is that
[28:04] conversational ones. The truth is that AI agents don't always need humans to
[28:06] AI agents don't always need humans to talk to them and use them directly. All
[28:09] talk to them and use them directly. All they need is some kind of input or
[28:11] they need is some kind of input or instructions to trigger them and that
[28:13] instructions to trigger them and that tells them what to do. This means that
[28:14] tells them what to do. This means that we can build these automated agents that
[28:16] we can build these automated agents that instead of waiting for some kind of
[28:18] instead of waiting for some kind of human input, they are actually part of
[28:20] human input, they are actually part of larger systems and processes and they're
[28:22] larger systems and processes and they're triggered automatically by events like a
[28:24] triggered automatically by events like a new email received or a form submission
[28:26] new email received or a form submission or they work on schedules like once a
[28:28] or they work on schedules like once a day and they essentially work in the
[28:30] day and they essentially work in the background without necessarily having
[28:32] background without necessarily having human oversight or input. For example,
[28:34] human oversight or input. For example, later in the video, we are going to be
[28:35] later in the video, we are going to be building an automated agent that is
[28:37] building an automated agent that is triggered by a new form submission. When
[28:39] triggered by a new form submission. When the form is submitted, some of that form
[28:41] the form is submitted, some of that form data is taken and sent to the agent,
[28:42] data is taken and sent to the agent, which then causes it to use the tools
[28:44] which then causes it to use the tools that we've equipped it with and follows
[28:46] that we've equipped it with and follows the instructions in the prompt that we
[28:47] the instructions in the prompt that we gave it in order to make decisions and
[28:49] gave it in order to make decisions and take appropriate actions on our behalf
[28:51] take appropriate actions on our behalf in a fully automated way. We are still
[28:53] in a fully automated way. We are still sending the message to the agent, but
[28:55] sending the message to the agent, but it's not a human needing to type it
[28:57] it's not a human needing to type it manually or speak it over the phone.
[28:59] manually or speak it over the phone. There's no human step. The input is
[29:01] There's no human step. The input is being automated in some way. And this of
[29:02] being automated in some way. And this of course opens up a huge number of use
[29:04] course opens up a huge number of use cases for AI agents in businesses
[29:06] cases for AI agents in businesses especially. And of course I'll be
[29:07] especially. And of course I'll be showing you how to build both types of
[29:08] showing you how to build both types of these conversational and automated
[29:10] these conversational and automated agents in the tutorial section of this
[29:12] agents in the tutorial section of this video. But the last step of building
[29:14] video. But the last step of building your foundation of knowledge before we
[29:15] your foundation of knowledge before we move into that is to look at some real
[29:17] move into that is to look at some real world examples of how businesses are
[29:19] world examples of how businesses are using these AI agents right
[29:23] using these AI agents right now. So firstly we have the personal
[29:25] now. So firstly we have the personal assistant category. And this is what
[29:27] assistant category. And this is what most people think of when they hear the
[29:28] most people think of when they hear the word agent. something that you can chat
[29:30] word agent. something that you can chat to that's going to update your calendar
[29:31] to that's going to update your calendar and sort of send emails and even make
[29:33] and sort of send emails and even make phone calls for you. Um, now these are
[29:35] phone calls for you. Um, now these are all nice to have features, but honestly
[29:38] all nice to have features, but honestly uh this space is likely going to be
[29:39] uh this space is likely going to be dominated by the big tech giants. You've
[29:41] dominated by the big tech giants. You've got OpenAI through Chatbt trying to do
[29:43] got OpenAI through Chatbt trying to do this with Tasks, Google through their
[29:45] this with Tasks, Google through their suite of apps and connecting them to
[29:47] suite of apps and connecting them to Gemini and Apple through Siri. These
[29:49] Gemini and Apple through Siri. These guys are going to eat up this entire
[29:50] guys are going to eat up this entire market of personal assistance and your
[29:52] market of personal assistance and your own personal AI agent that helps you do
[29:54] own personal AI agent that helps you do personal stuff. the real opportunity
[29:56] personal stuff. the real opportunity lies in business applications and how
[29:58] lies in business applications and how people like you and I can build and sell
[30:00] people like you and I can build and sell AI agents to businesses which we're
[30:01] AI agents to businesses which we're going to be covering in depth in the
[30:03] going to be covering in depth in the final chapter of this video. So, we've
[30:04] final chapter of this video. So, we've got the next chapter which is going to
[30:05] got the next chapter which is going to be on building the four tutorials and
[30:08] be on building the four tutorials and the final chapter is all about how to
[30:09] the final chapter is all about how to sell and how to monetize your AI agent
[30:11] sell and how to monetize your AI agent skills that you've just learned. One of
[30:12] skills that you've just learned. One of the core use cases for businesses right
[30:14] the core use cases for businesses right now are what's called co-pilots. And
[30:16] now are what's called co-pilots. And these are AI agents made for specific
[30:18] these are AI agents made for specific roles in a business. We're going to be
[30:20] roles in a business. We're going to be building one of these later in the
[30:21] building one of these later in the video. And these specialized AI agents
[30:23] video. And these specialized AI agents are essentially helping someone in a
[30:25] are essentially helping someone in a specific role in a business to do their
[30:27] specific role in a business to do their job more effectively. Take a customer
[30:29] job more effectively. Take a customer support co-pilot for example. It would
[30:31] support co-pilot for example. It would have a knowledge base that allows reps
[30:33] have a knowledge base that allows reps to get answers to customer queries
[30:34] to get answers to customer queries instantly and deliver them over the
[30:35] instantly and deliver them over the phone. So they've got the little
[30:36] phone. So they've got the little co-pilot up on the side there. They're
[30:38] co-pilot up on the side there. They're on the phone. They get a question, they
[30:40] on the phone. They get a question, they can search and for an answer in the
[30:41] can search and for an answer in the knowledge base, it gives them back and
[30:42] knowledge base, it gives them back and they can give it to them over the phone.
[30:44] they can give it to them over the phone. This same agent could also have a tool
[30:45] This same agent could also have a tool that allows them to look up the customer
[30:47] that allows them to look up the customer information very quickly. Um, I could
[30:49] information very quickly. Um, I could have another tool that it makes it very
[30:50] have another tool that it makes it very easy to send a summary of the call into
[30:52] easy to send a summary of the call into the database so that the next rep who
[30:54] the database so that the next rep who picks up the phone and talks with them
[30:55] picks up the phone and talks with them knows exactly what was discussed
[30:56] knows exactly what was discussed previously. It's like giving every
[30:58] previously. It's like giving every support rep some kind of AI assistant
[31:00] support rep some kind of AI assistant that makes them dramatically more
[31:01] that makes them dramatically more effective. It also makes their customer
[31:03] effective. It also makes their customer support a lot more consistent as to what
[31:05] support a lot more consistent as to what the company wants people to be saying,
[31:06] the company wants people to be saying, which is a a big problem with managing
[31:08] which is a a big problem with managing large customer support systems. And then
[31:10] large customer support systems. And then we have lead generation and appointment
[31:11] we have lead generation and appointment setting agents. These are probably the
[31:13] setting agents. These are probably the most valuable type right now. And
[31:15] most valuable type right now. And businesses are using these on their
[31:16] businesses are using these on their websites, through WhatsApp, on
[31:18] websites, through WhatsApp, on Instagram, and even over the phone to
[31:20] Instagram, and even over the phone to engage and have conversations with the
[31:21] engage and have conversations with the interested people who are approaching
[31:23] interested people who are approaching the business 24/7. They can offer
[31:25] the business 24/7. They can offer instant answers about products and
[31:27] instant answers about products and services. And they're even smart enough
[31:28] services. And they're even smart enough to be able to capture emails and phone
[31:30] to be able to capture emails and phone numbers mid-con conversation for later
[31:32] numbers mid-con conversation for later follow-up by sales team. Some can even
[31:34] follow-up by sales team. Some can even book appointments on the spot and mid-
[31:36] book appointments on the spot and mid- conversation by using a tool to check
[31:37] conversation by using a tool to check the calendar availability and then using
[31:39] the calendar availability and then using another tool to create a new booking
[31:41] another tool to create a new booking once they've agreed on a time with the
[31:43] once they've agreed on a time with the prospect. Another real world agent use
[31:44] prospect. Another real world agent use case and one of my favorites is a
[31:46] case and one of my favorites is a research agent. And so these can help
[31:48] research agent. And so these can help businesses by automatically researching
[31:50] businesses by automatically researching leads that come in through their website
[31:51] leads that come in through their website or elsewhere. And when someone fills out
[31:53] or elsewhere. And when someone fills out a form, the agent can spring into action
[31:55] a form, the agent can spring into action and start searching the web for
[31:56] and start searching the web for information on the company, finding
[31:58] information on the company, finding their LinkedIn profile of the person
[31:59] their LinkedIn profile of the person they're going to get on a call with and
[32:00] they're going to get on a call with and gathering any other valuable data that
[32:02] gathering any other valuable data that it can find. Then it can take all of
[32:03] it can find. Then it can take all of this information and generate a summary
[32:05] this information and generate a summary of who this person is and what this
[32:07] of who this person is and what this company is also and decide whether
[32:09] company is also and decide whether they're a good fit for working with the
[32:10] they're a good fit for working with the company and if so then they can send the
[32:13] company and if so then they can send the sales team some kind of detailed brief
[32:14] sales team some kind of detailed brief or suggested strategy on how to close
[32:16] or suggested strategy on how to close this particular person on a call based
[32:18] this particular person on a call based on the research. So it's basically like
[32:20] on the research. So it's basically like having a an automated team of
[32:22] having a an automated team of researchers who as soon as leads show
[32:23] researchers who as soon as leads show interest in your business, they're out
[32:25] interest in your business, they're out there figuring out everything about them
[32:26] there figuring out everything about them and determining one whether they're a
[32:28] and determining one whether they're a good fit for you and your products and
[32:29] good fit for you and your products and services which is called qualification.
[32:30] services which is called qualification. Then secondly, if they are qualified,
[32:32] Then secondly, if they are qualified, giving the sales rep something that will
[32:34] giving the sales rep something that will bring them up to speed on who this
[32:35] bring them up to speed on who this person or who this company is and how
[32:37] person or who this company is and how they can try to close
[32:39] they can try to close them. So, we have covered a lot so far.
[32:42] them. So, we have covered a lot so far. So, before we dive into each of these
[32:43] So, before we dive into each of these agent builds that I'm going to walk you
[32:45] agent builds that I'm going to walk you through over my shoulder, please make
[32:47] through over my shoulder, please make sure that you've got your notes taken
[32:48] sure that you've got your notes taken out and the core concepts of this video
[32:50] out and the core concepts of this video so far understood properly. You should
[32:52] so far understood properly. You should be clear on things like what is the
[32:54] be clear on things like what is the definition of an AI agent? What are the
[32:56] definition of an AI agent? What are the five parts of an agent? How is building
[32:59] five parts of an agent? How is building an AI agent like being a chef? And how
[33:01] an AI agent like being a chef? And how many ingredients do you have to play
[33:02] many ingredients do you have to play with? What are the two main parts of a
[33:05] with? What are the two main parts of a tool? And what do schemers do? So, pause
[33:08] tool? And what do schemers do? So, pause the video now and try to answer these
[33:09] the video now and try to answer these questions. And if you aren't 100%
[33:11] questions. And if you aren't 100% confident, you need to go back and watch
[33:13] confident, you need to go back and watch it again. So, don't rush this or you're
[33:15] it again. So, don't rush this or you're going to feel way out of depth when we
[33:17] going to feel way out of depth when we get into the tutorials that we're going
[33:18] get into the tutorials that we're going to be covering next. But if you are,
[33:19] to be covering next. But if you are, congratulations. You are one step closer
[33:21] congratulations. You are one step closer to AI literacy and becoming a much more
[33:23] to AI literacy and becoming a much more valuable uh participant in this global
[33:26] valuable uh participant in this global economy. So before we get into the
[33:27] economy. So before we get into the second chapter, there's just three very
[33:28] second chapter, there's just three very quick things from me. Firstly, if you
[33:30] quick things from me. Firstly, if you are a business owner who wants to fast
[33:32] are a business owner who wants to fast track to becoming an AI leader within
[33:34] track to becoming an AI leader within your industry, at my agency, Morningside
[33:36] your industry, at my agency, Morningside AI, we offer everything from AI
[33:38] AI, we offer everything from AI education and upskilling programs for
[33:39] education and upskilling programs for executives and staff to AI strategy and
[33:42] executives and staff to AI strategy and roadmap consulting and of course AI
[33:44] roadmap consulting and of course AI development services as well. So we
[33:45] development services as well. So we would love to help you get ahead. So
[33:47] would love to help you get ahead. So feel free to get in touch via our
[33:48] feel free to get in touch via our website in the description below. And
[33:50] website in the description below. And secondly, at Morningside, we are hiring
[33:52] secondly, at Morningside, we are hiring for all sorts of roles right now. So
[33:53] for all sorts of roles right now. So whether you want to build AI systems for
[33:55] whether you want to build AI systems for some of the world's biggest companies
[33:56] some of the world's biggest companies that we have as clients or to help
[33:58] that we have as clients or to help produce videos like these that are seen
[34:00] produce videos like these that are seen by millions of people or create
[34:02] by millions of people or create educational material for thousands of
[34:04] educational material for thousands of businesses. Uh we have roles for all
[34:05] businesses. Uh we have roles for all sorts of things right now. So you can
[34:06] sorts of things right now. So you can apply using the link in the description.
[34:08] apply using the link in the description. And please, even if you're just vaguely
[34:09] And please, even if you're just vaguely interested, I really recommend you just
[34:11] interested, I really recommend you just check out the link and see what roles
[34:12] check out the link and see what roles we're hiring for. Uh you never know
[34:14] we're hiring for. Uh you never know what's going to be on there. Um and it
[34:16] what's going to be on there. Um and it may be a very good way for you to use
[34:17] may be a very good way for you to use your skills to fast track into the AI
[34:18] your skills to fast track into the AI space by working under myself and my
[34:20] space by working under myself and my team. And finally, if you have gotten
[34:22] team. And finally, if you have gotten any value so far in this video, please
[34:23] any value so far in this video, please head down below and leave a like on the
[34:25] head down below and leave a like on the video. It helps me reach more people.
[34:27] video. It helps me reach more people. Um, I put a lot of work into these
[34:28] Um, I put a lot of work into these videos and it also lets me know that you
[34:30] videos and it also lets me know that you enjoy this kind of content and that I
[34:31] enjoy this kind of content and that I should make more of it. And of course,
[34:32] should make more of it. And of course, if you like this kind of content and
[34:33] if you like this kind of content and want to see more of it, you can
[34:34] want to see more of it, you can subscribe so that YouTube will put my
[34:36] subscribe so that YouTube will put my videos up for you whenever a new one is
[34:38] videos up for you whenever a new one is released. So, there's also a little
[34:39] released. So, there's also a little share button if you want to click that.
[34:40] share button if you want to click that. That'll let YouTube know this is good
[34:41] That'll let YouTube know this is good content and that you're sharing it to
[34:42] content and that you're sharing it to other people. Not only will that help
[34:44] other people. Not only will that help me, but you can share it to your friends
[34:45] me, but you can share it to your friends and family who may also or you may want
[34:48] and family who may also or you may want to help them to brush up on these skills
[34:49] to help them to brush up on these skills or help them give a way to get on the
[34:51] or help them give a way to get on the front foot with AI. And that's what I
[34:52] front foot with AI. And that's what I really make these videos for. So, thank
[34:54] really make these videos for. So, thank you for sitting through that little bit
[34:55] you for sitting through that little bit of housekeeping and self-promotion. Now,
[34:57] of housekeeping and self-promotion. Now, let's get stuck into the
[35:01] building. I have carefully assembled
[35:03] building. I have carefully assembled this chapter on building to give you the
[35:05] this chapter on building to give you the most bang for your buck possible in
[35:07] most bang for your buck possible in order to kick off your AI agent learning
[35:09] order to kick off your AI agent learning journey. We are going to be covering
[35:10] journey. We are going to be covering four different use cases across four
[35:12] four different use cases across four different AI agent building platforms.
[35:14] different AI agent building platforms. These are all no code, so don't worry
[35:16] These are all no code, so don't worry about that. And the chances of you
[35:18] about that. And the chances of you falling in love with at least one of
[35:19] falling in love with at least one of these platforms is pretty much 100% as
[35:22] these platforms is pretty much 100% as you're going to rapidly start to connect
[35:23] you're going to rapidly start to connect the dots uh about how you can start to
[35:25] the dots uh about how you can start to use these kinds of agents and these
[35:27] use these kinds of agents and these platforms in your own life or in your
[35:28] platforms in your own life or in your work or for your friends and family and
[35:30] work or for your friends and family and those around you. So, here's a quick
[35:31] those around you. So, here's a quick rundown of the builds we're going to be
[35:33] rundown of the builds we're going to be getting into. The first build is going
[35:34] getting into. The first build is going to be a sales co-pilot built with
[35:36] to be a sales co-pilot built with relevance AI. And here we're going to be
[35:38] relevance AI. And here we're going to be building three custom research tools
[35:40] building three custom research tools from scratch, including an advanced web
[35:42] from scratch, including an advanced web scraping tool, which is a a great skill
[35:44] scraping tool, which is a a great skill that I want to teach you. And with
[35:45] that I want to teach you. And with these, we are going to be creating a
[35:46] these, we are going to be creating a conversational agent to help the sales
[35:48] conversational agent to help the sales reps at Big Boy Recruits, a hypothetical
[35:51] reps at Big Boy Recruits, a hypothetical fantasy uh recruitment firm, in order
[35:53] fantasy uh recruitment firm, in order for them to be better prepared for sales
[35:55] for them to be better prepared for sales course. So that's the purpose of the
[35:56] course. So that's the purpose of the sales co-pilot. The second build is
[35:58] sales co-pilot. The second build is going to be an automated lead
[35:59] going to be an automated lead qualification agent. And this will be
[36:01] qualification agent. And this will be built on a platform called N8N. And this
[36:03] built on a platform called N8N. And this time we will be helping Big Boy
[36:05] time we will be helping Big Boy Recruits, our fantasy recruitment firm,
[36:07] Recruits, our fantasy recruitment firm, to automatically research and qualify
[36:09] to automatically research and qualify new leads and then send an email
[36:10] new leads and then send an email notification to the correct sales rep.
[36:12] notification to the correct sales rep. And this is going to show you that
[36:13] And this is going to show you that automated style of agent where it's
[36:15] automated style of agent where it's built into a process rather than having
[36:16] built into a process rather than having a human input necessarily. In build
[36:18] a human input necessarily. In build number three, we will be building a
[36:19] number three, we will be building a website and phone-based lead generation
[36:22] website and phone-based lead generation customer support agent. This will be
[36:23] customer support agent. This will be built on voice flow and it's going to be
[36:25] built on voice flow and it's going to be able to do three things. Firstly, answer
[36:27] able to do three things. Firstly, answer questions from a knowledge base,
[36:28] questions from a knowledge base, generate instant quotes using a custom
[36:30] generate instant quotes using a custom tool we build and also do lead capture
[36:33] tool we build and also do lead capture on interested prospects. We're then
[36:34] on interested prospects. We're then going to slap this agent onto a website
[36:36] going to slap this agent onto a website widget so that you can chat to it via a
[36:38] widget so that you can chat to it via a website and via chat and text. And then
[36:40] website and via chat and text. And then we're going to take that exact same
[36:41] we're going to take that exact same agent and connect them to a phone line
[36:43] agent and connect them to a phone line so that we can call our agent over the
[36:44] so that we can call our agent over the phone and access all of the same
[36:45] phone and access all of the same functionality we just talked about. And
[36:47] functionality we just talked about. And finally, for build number four, we'll be
[36:49] finally, for build number four, we'll be using my own AI agent platform, Agent,
[36:51] using my own AI agent platform, Agent, to rapidly build a lead generation agent
[36:53] to rapidly build a lead generation agent and connect it to a WhatsApp number that
[36:55] and connect it to a WhatsApp number that we can chat to. The leads that we
[36:56] we can chat to. The leads that we collect are going to be automatically
[36:57] collect are going to be automatically sent into an Air Table database for
[36:59] sent into an Air Table database for later review. And please don't skip
[37:01] later review. And please don't skip around these builds as they're all kind
[37:02] around these builds as they're all kind of connected in some way where we're
[37:04] of connected in some way where we're reusing parts from build one and build
[37:05] reusing parts from build one and build two, etc. But without further ado, let's
[37:08] two, etc. But without further ado, let's get into building some agents. All
[37:09] get into building some agents. All right, people. Enough of the theory. Uh,
[37:12] right, people. Enough of the theory. Uh, now we get into the fun bit of actually
[37:14] now we get into the fun bit of actually building these agents out. So, I've done
[37:16] building these agents out. So, I've done a lot of work and my team has done a lot
[37:18] a lot of work and my team has done a lot of work. So, thank you to the my team
[37:19] of work. So, thank you to the my team members who have helped me put this
[37:20] members who have helped me put this together. Um, putting together four
[37:22] together. Um, putting together four different AI agent builds for you. And
[37:24] different AI agent builds for you. And this is really going to walk you through
[37:26] this is really going to walk you through an A to Z all the different platforms
[37:28] an A to Z all the different platforms that you really need to care about, all
[37:30] that you really need to care about, all the different kind of core use cases and
[37:32] the different kind of core use cases and functionality. There's a lot more of
[37:33] functionality. There's a lot more of course, but this is going to really give
[37:35] course, but this is going to really give you the foundation that you need to
[37:37] you the foundation that you need to succeed in the space. And hopefully
[37:39] succeed in the space. And hopefully it'll be the thing that kind of sparks
[37:40] it'll be the thing that kind of sparks your interest in it because I I want you
[37:43] your interest in it because I I want you guys to have fun with it. these big
[37:44] guys to have fun with it. these big tutorials for me. Honestly, when I put a
[37:46] tutorials for me. Honestly, when I put a lot of work into it, I build up the sort
[37:47] lot of work into it, I build up the sort of mental resistance to it because I
[37:49] of mental resistance to it because I know how much work there is going into
[37:50] know how much work there is going into it and I have to make this big whole
[37:52] it and I have to make this big whole session where I'm all uptight about it.
[37:53] session where I'm all uptight about it. But I'm just going to try and relax and
[37:55] But I'm just going to try and relax and enjoy this. And I really want you all to
[37:56] enjoy this. And I really want you all to do the same. So, set a bit of time
[37:58] do the same. So, set a bit of time aside. You can either pause this video,
[38:00] aside. You can either pause this video, put on your watch later, but I really
[38:02] put on your watch later, but I really want you to take your time with this.
[38:05] want you to take your time with this. I'm going to be doing this more. So,
[38:06] I'm going to be doing this more. So, when you do tutorials like this, there's
[38:07] when you do tutorials like this, there's a few different ways you can do it. I
[38:09] a few different ways you can do it. I can either do all the building and then
[38:11] can either do all the building and then give you the templates and kind of just
[38:12] give you the templates and kind of just spoon feed it to you. And that's more so
[38:14] spoon feed it to you. And that's more so what you do for someone if you're trying
[38:15] what you do for someone if you're trying to like really fast track them and they
[38:17] to like really fast track them and they don't want to learn all the skills, but
[38:18] don't want to learn all the skills, but um I I know what I'm trying to build
[38:20] um I I know what I'm trying to build here for you guys. And I'm going to give
[38:21] here for you guys. And I'm going to give you a sort of stream of consciousness.
[38:23] you a sort of stream of consciousness. You just get to see me kind of jamming
[38:25] You just get to see me kind of jamming out and building these things. And I'll
[38:26] out and building these things. And I'll be explaining my thought process and the
[38:28] be explaining my thought process and the concepts etc along the way to reinforce
[38:30] concepts etc along the way to reinforce what we've learned before. So I'm just
[38:32] what we've learned before. So I'm just going to dive into it with our first
[38:34] going to dive into it with our first agent.
[38:39] And so what I've done is put together a
[38:40] And so what I've done is put together a big Figma board here which is going to
[38:41] big Figma board here which is going to be breaking down all these different
[38:42] be breaking down all these different builds. So under here there's some
[38:43] builds. So under here there's some goodies you see. Oh, there's some
[38:45] goodies you see. Oh, there's some goodies under each of these that I've
[38:47] goodies under each of these that I've put together. Um and we're going to go
[38:48] put together. Um and we're going to go through them one by one. Starting off
[38:50] through them one by one. Starting off with agent one over here. I mean there's
[38:51] with agent one over here. I mean there's a lot of stuff here um that you guys are
[38:53] a lot of stuff here um that you guys are going to get. So you'll get the whole
[38:54] going to get. So you'll get the whole Figma and it includes all the templates.
[38:56] Figma and it includes all the templates. So if you do want to just kind of watch
[38:57] So if you do want to just kind of watch through this, pick it up. You can either
[38:59] through this, pick it up. You can either do it and follow it step by step with me
[39:00] do it and follow it step by step with me and see how I build it and really build
[39:02] and see how I build it and really build those flexible skills that you're going
[39:03] those flexible skills that you're going to need to succeed in the space or you
[39:05] to need to succeed in the space or you can just watch it and be like, "Okay, I
[39:07] can just watch it and be like, "Okay, I kind of get what he's doing and then
[39:09] kind of get what he's doing and then take all the templates from me at the
[39:10] take all the templates from me at the end." That's I mean, completely up to
[39:12] end." That's I mean, completely up to you. Depends if you want to be a really
[39:13] you. Depends if you want to be a really really nerdy builder about it and get
[39:14] really nerdy builder about it and get into the weed like like I like to do. Um
[39:17] into the weed like like I like to do. Um or you just want to be like, "Hey, I
[39:18] or you just want to be like, "Hey, I want to do this my business. I want to
[39:19] want to do this my business. I want to roughly understand how these things work
[39:21] roughly understand how these things work and what platforms." So, use this
[39:23] and what platforms." So, use this resource as you will. But we're going to
[39:24] resource as you will. But we're going to jump into agent build number one here,
[39:26] jump into agent build number one here, which is our sales co-pilot built with
[39:28] which is our sales co-pilot built with relevance AI. So, running through this
[39:30] relevance AI. So, running through this quickly, we have the purpose of this.
[39:32] quickly, we have the purpose of this. This is basically going to look a bit
[39:33] This is basically going to look a bit like this. It's going to be a co-pilot
[39:35] like this. It's going to be a co-pilot and co-pilots work in that you have a uh
[39:37] and co-pilots work in that you have a uh it's basically a specific AI agent that
[39:40] it's basically a specific AI agent that you build for a specific staff or staff
[39:42] you build for a specific staff or staff member or role. So, say this case, it's
[39:44] member or role. So, say this case, it's going to be a sales co-pilot. It'll be
[39:46] going to be a sales co-pilot. It'll be the thing that the sales rep uses to uh
[39:49] the thing that the sales rep uses to uh in their day-to-day as they're working
[39:50] in their day-to-day as they're working on their jobs. You can add tools like in
[39:52] on their jobs. You can add tools like in this case, you see we're going to have
[39:54] this case, you see we're going to have three different tools here for our
[39:55] three different tools here for our agent. One's going to be a company
[39:56] agent. One's going to be a company researcher tool. So this is when the
[39:58] researcher tool. So this is when the sales rep would be like, hey, I have a
[40:00] sales rep would be like, hey, I have a call coming up soon. Um, let's put in
[40:01] call coming up soon. Um, let's put in this I need to research this company cuz
[40:03] this I need to research this company cuz this is who I'm going to be on a call
[40:04] this is who I'm going to be on a call with. So they'll put in the company URL.
[40:06] with. So they'll put in the company URL. This tool that we're going to create is
[40:07] This tool that we're going to create is going to go and research that company.
[40:08] going to go and research that company. It's going to bring back and give a
[40:10] It's going to bring back and give a summary. And then it's like, okay, well
[40:11] summary. And then it's like, okay, well this is the LinkedIn URL of the person
[40:12] this is the LinkedIn URL of the person that we're going to be got on a call
[40:14] that we're going to be got on a call with shortly. It's going to pass in the
[40:16] with shortly. It's going to pass in the LinkedIn URL. It's going to take that
[40:17] LinkedIn URL. It's going to take that URL. It's going to pull all the
[40:18] URL. It's going to pull all the information and write a summary about
[40:20] information and write a summary about the person. So now we have the company
[40:21] the person. So now we have the company summary and we have the person summary.
[40:23] summary and we have the person summary. And the final step here is going to be
[40:24] And the final step here is going to be what I'm calling a pre-all report
[40:26] what I'm calling a pre-all report generator. And that's going to take both
[40:28] generator. And that's going to take both that company and prospect research that
[40:29] that company and prospect research that we've done. It's going to combine them
[40:31] we've done. It's going to combine them together and be for this specific
[40:34] together and be for this specific company. As you're going to see that
[40:35] company. As you're going to see that this hypothetical company we're building
[40:36] this hypothetical company we're building this sales co-pilot for, it's going to
[40:39] this sales co-pilot for, it's going to generate a basically a pre-core report
[40:41] generate a basically a pre-core report or a strategy uh a strategy prep for the
[40:43] or a strategy uh a strategy prep for the sales rep so that they go onto those
[40:44] sales rep so that they go onto those calls much more prepared and also sort
[40:47] calls much more prepared and also sort of a personalized guide on how to try to
[40:49] of a personalized guide on how to try to close this person. So, um, all of these
[40:51] close this person. So, um, all of these templates are going to be here. Each of
[40:53] templates are going to be here. Each of these are templates for the tools. And
[40:54] these are templates for the tools. And this is for the agent as well. Um, but
[40:57] this is for the agent as well. Um, but here's some more information. You guys
[40:58] here's some more information. You guys can pick through this as you wish. But,
[40:59] can pick through this as you wish. But, um, this is the kind of end result and
[41:01] um, this is the kind of end result and we're going to be able to chat to it.
[41:02] we're going to be able to chat to it. And this would be something you could
[41:03] And this would be something you could build for a client. You could build it
[41:04] build for a client. You could build it for your own business or you could just
[41:06] for your own business or you could just tinker around. You could build co-pilots
[41:07] tinker around. You could build co-pilots like this on relevance for yourself. So,
[41:09] like this on relevance for yourself. So, that's why I want to start with
[41:10] that's why I want to start with relevance because it also is a platform
[41:11] relevance because it also is a platform that we can build these tools on. So,
[41:13] that we can build these tools on. So, it's a really, really good one to start
[41:14] it's a really, really good one to start with and let's get into it. So, the
[41:16] with and let's get into it. So, the first step of course is to go to
[41:18] first step of course is to go to relevance AI. So, I'll put a little link
[41:19] relevance AI. So, I'll put a little link up here. You guys will be able to get
[41:20] up here. You guys will be able to get this Figma. It'll be on the school. Um,
[41:22] this Figma. It'll be on the school. Um, all of the information and all the
[41:23] all of the information and all the resources for this are going to be like
[41:24] resources for this are going to be like this Figma is going to be linked to the
[41:26] this Figma is going to be linked to the school. My free school community. If you
[41:27] school. My free school community. If you haven't already joined, biggest AI
[41:29] haven't already joined, biggest AI community on school, biggest AI business
[41:31] community on school, biggest AI business community probably in the whole world.
[41:33] community probably in the whole world. Um, so we can jump across that first
[41:35] Um, so we can jump across that first link in the description. You'll be able
[41:36] link in the description. You'll be able to find this in the YouTube resources
[41:37] to find this in the YouTube resources section. Um, pretty straightforward. Of
[41:39] section. Um, pretty straightforward. Of course, when you click on this, it's
[41:41] course, when you click on this, it's going to ask you to log into relevance.
[41:43] going to ask you to log into relevance. So, if you haven't already, you can make
[41:44] So, if you haven't already, you can make an account. Um, it's fairly low cost.
[41:46] an account. Um, it's fairly low cost. They have a free plan, then a team's
[41:48] They have a free plan, then a team's plan, I believe. Um, so it's not too
[41:49] plan, I believe. Um, so it's not too much, but it is a really, really
[41:50] much, but it is a really, really valuable tool as you're going to see.
[41:52] valuable tool as you're going to see. So, you can sign in here. I'm going to
[41:54] So, you can sign in here. I'm going to jump in with my Google account. There
[41:57] jump in with my Google account. There may be a bit of setup for your account,
[41:58] may be a bit of setup for your account, but I'm sure you guys are smart enough
[41:59] but I'm sure you guys are smart enough to figure out how to set up an account.
[42:00] to figure out how to set up an account. I'm sure relevance also makes it easy
[42:02] I'm sure relevance also makes it easy enough. So, then we get taken to this
[42:04] enough. So, then we get taken to this dashboard, but we see on this left hand
[42:05] dashboard, but we see on this left hand side, we have tools. So these are the
[42:07] side, we have tools. So these are the tools that I've talked about um where
[42:08] tools that I've talked about um where it's some kind of functionality that we
[42:10] it's some kind of functionality that we can create and we can build it all on
[42:11] can create and we can build it all on relevance no code and there's even sort
[42:13] relevance no code and there's even sort of extensibility or you can add more
[42:15] of extensibility or you can add more functionality in to relevance by adding
[42:18] functionality in to relevance by adding some low code components or even custom
[42:19] some low code components or even custom code. So relevance is a really great
[42:21] code. So relevance is a really great base for building not only tools but
[42:23] base for building not only tools but then the agents that you can connect
[42:24] then the agents that you can connect that into and we're going to use the
[42:25] that into and we're going to use the same relevance tools that we make now in
[42:27] same relevance tools that we make now in multiple of the different agents that
[42:28] multiple of the different agents that I'm going to make for the rest of this
[42:29] I'm going to make for the rest of this video. So first things first if we go
[42:30] video. So first things first if we go back to the Figma here we see we need to
[42:32] back to the Figma here we see we need to make three different tools. So tool one
[42:33] make three different tools. So tool one is company researcher. It's going to
[42:35] is company researcher. It's going to take in a company URL. It's going to
[42:36] take in a company URL. It's going to search the web and it's going to return
[42:37] search the web and it's going to return a summary. So, that's the functionality
[42:39] a summary. So, that's the functionality we need. Let's go and create a new tool.
[42:42] we need. Let's go and create a new tool. Going to call this um
[42:45] Going to call this um research company. We can give it a cool
[42:48] research company. We can give it a cool little I'm going to zoom this up for you
[42:49] little I'm going to zoom this up for you guys. Hopefully, that's the right size.
[42:51] guys. Hopefully, that's the right size. Um uh search. Have fun with this stuff,
[42:55] Um uh search. Have fun with this stuff, guys. Like, if if it's putting stupid
[42:57] guys. Like, if if it's putting stupid emojis on things to to enjoy it, then
[42:59] emojis on things to to enjoy it, then then that's what you need to do. Like,
[43:01] then that's what you need to do. Like, uh if you make it a chore, it's going to
[43:02] uh if you make it a chore, it's going to feel like a chore, right? Um, now we get
[43:04] feel like a chore, right? Um, now we get to descriptions. Um, this is something
[43:06] to descriptions. Um, this is something we're going to see recurring, but
[43:07] we're going to see recurring, but basically as as you know, as we learned
[43:09] basically as as you know, as we learned in the concept section, we need to have
[43:11] in the concept section, we need to have natural language descriptions of our
[43:13] natural language descriptions of our tools and of our APIs so that the agents
[43:15] tools and of our APIs so that the agents can read those descriptions and
[43:16] can read those descriptions and understand uh what the agent or what the
[43:18] understand uh what the agent or what the tool does and what those different parts
[43:20] tool does and what those different parts does. So, you'll see this recurring
[43:22] does. So, you'll see this recurring throughout this. But first things first,
[43:23] throughout this. But first things first, what does this research company tool do?
[43:26] what does this research company tool do? Um, takes and oh, I got caps lock on.
[43:30] Um, takes and oh, I got caps lock on. takes um and there's also some tutorials
[43:32] takes um and there's also some tutorials here if you want to go deeper. Relevance
[43:34] here if you want to go deeper. Relevance has some great documentation as well. Um
[43:36] has some great documentation as well. Um but takes in a
[43:40] but takes in a company
[43:43] company penny URL
[43:45] penny URL and scrapes the website then returns a
[43:51] and scrapes the website then returns a sum and AI generated summary. So then to
[43:55] sum and AI generated summary. So then to build a tool we need to have some kind
[43:57] build a tool we need to have some kind of input. You don't always need an
[43:58] of input. You don't always need an input. It can actually just be
[43:59] input. It can actually just be triggering, but generally you're going
[44:00] triggering, but generally you're going to have some kind of input that the
[44:02] to have some kind of input that the agent needs to pass into the tool. In
[44:03] agent needs to pass into the tool. In this case, to research company, it's
[44:05] this case, to research company, it's going to need to take in some text,
[44:07] going to need to take in some text, which is going to be a URL. Um, we're
[44:09] which is going to be a URL. Um, we're going to say comp company
[44:13] going to say comp company URL. And then again, here we have
[44:15] URL. And then again, here we have another description. You see, describe
[44:16] another description. You see, describe how to fill this input. This is again
[44:18] how to fill this input. This is again going to help our agent within relevance
[44:20] going to help our agent within relevance AI and elsewhere as you'll see in
[44:22] AI and elsewhere as you'll see in tutorial number four. Why this is so
[44:24] tutorial number four. Why this is so important to add in the descriptions,
[44:25] important to add in the descriptions, right? So this is a
[44:29] right? So this is a URL for a company to be
[44:34] URL for a company to be researched must be in the format https
[44:39] researched must be in the format https colon slash
[44:43] colon slash um dot dot dot dot dot. So we need to
[44:45] um dot dot dot dot dot. So we need to have the https for this to work. So
[44:48] have the https for this to work. So that's going to be our input. Now if
[44:49] that's going to be our input. Now if this seems a bit confusing just stick
[44:50] this seems a bit confusing just stick with me. It will make sense in a second.
[44:51] with me. It will make sense in a second. this stuff. If there's anything that
[44:53] this stuff. If there's anything that I've learned from picking up so many
[44:54] I've learned from picking up so many different tools, like when I first got
[44:56] different tools, like when I first got into Facebook ads, when I've got into
[44:57] into Facebook ads, when I've got into building these kinds of agents, it's you
[44:59] building these kinds of agents, it's you feel completely overwhelmed, but that's
[45:00] feel completely overwhelmed, but that's all just part of the process. And what
[45:02] all just part of the process. And what feels difficult now is not going to feel
[45:03] feels difficult now is not going to feel difficult forever. So, just please stick
[45:05] difficult forever. So, just please stick with me. Um, and it's a really, really
[45:07] with me. Um, and it's a really, really great feeling once you go and be like,
[45:08] great feeling once you go and be like, this was hard a few weeks ago and now
[45:10] this was hard a few weeks ago and now it's really easy. So, we've got our
[45:12] it's really easy. So, we've got our first input. That's what the research
[45:13] first input. That's what the research company tool is going to do. And then we
[45:15] company tool is going to do. And then we need to define our steps. So, the next
[45:17] need to define our steps. So, the next step, we can go add. I'm going to hide
[45:19] step, we can go add. I'm going to hide this so we get a bit more space. Add
[45:20] this so we get a bit more space. Add step. Now, the cool thing about
[45:22] step. Now, the cool thing about relevance is that it comes with a lot of
[45:23] relevance is that it comes with a lot of great functionality out of the box.
[45:25] great functionality out of the box. Here's one, extract website content, we
[45:27] Here's one, extract website content, we have LLMs, we have Google searching, we
[45:30] have LLMs, we have Google searching, we have all sorts of AI generations,
[45:32] have all sorts of AI generations, replicate um knowledge bases as well.
[45:35] replicate um knowledge bases as well. There's so much cool stuff on here and
[45:36] There's so much cool stuff on here and this is why I really rate relevance as
[45:38] this is why I really rate relevance as one of the best platforms. If you were
[45:39] one of the best platforms. If you were to go all in and want to upskill, you
[45:42] to go all in and want to upskill, you can build so much on this. Um, so I'm a
[45:44] can build so much on this. Um, so I'm a big fan. I love the the relevance team
[45:45] big fan. I love the the relevance team and what they're doing. So the initial
[45:47] and what they're doing. So the initial plan for this build I was going to use
[45:48] plan for this build I was going to use the extract website content which is
[45:50] the extract website content which is fairly straightforward. We can say oh
[45:52] fairly straightforward. We can say oh one other thing um the company URL we
[45:55] one other thing um the company URL we are going to be using this company URL
[45:56] are going to be using this company URL throughout our tool here. So we can
[45:58] throughout our tool here. So we can change this text to say something more
[46:00] change this text to say something more descriptive. So company
[46:03] descriptive. So company u URL. You guys are going to got going
[46:06] u URL. You guys are going to got going to think like think and write like
[46:07] to think like think and write like coders now cuz you need to uh use some
[46:09] coders now cuz you need to uh use some kind of syntax and use some kind of
[46:10] kind of syntax and use some kind of variable naming convention. This is a a
[46:13] variable naming convention. This is a a standard one or you can do things like
[46:15] standard one or you can do things like company URL camel case but I prefer this
[46:18] company URL camel case but I prefer this format as I'm I'm mainly a Python kind
[46:20] format as I'm I'm mainly a Python kind of guy myself. Now that we have that
[46:21] of guy myself. Now that we have that named we can use it in these kinds of
[46:23] named we can use it in these kinds of fields. So here you can see pops up use
[46:25] fields. So here you can see pops up use inputs. So basically when this tool is
[46:27] inputs. So basically when this tool is run it's going to take the inputs or the
[46:29] run it's going to take the inputs or the information we put in the inputs and
[46:30] information we put in the inputs and it's going to pass it to different steps
[46:32] it's going to pass it to different steps and use them as we describe within the
[46:33] and use them as we describe within the within the builder here. So let's run
[46:35] within the builder here. So let's run this quickly. Let's put in my company
[46:39] https/
[46:43] morningings.ai. Um, and then we can
[46:46] morningings.ai. Um, and then we can click uh run here. So, that's going to
[46:49] click uh run here. So, that's going to go to my website and scrape the
[46:51] go to my website and scrape the information off of it. There we go. So,
[46:54] information off of it. There we go. So, it's got all of this, but you see it's
[46:57] it's got all of this, but you see it's just pulling back the first page. Um,
[46:58] just pulling back the first page. Um, and this is why I actually I shuffled
[47:00] and this is why I actually I shuffled this around. And I want to show you guys
[47:02] this around. And I want to show you guys how to do something a bit more advanced.
[47:03] how to do something a bit more advanced. I know this is supposed to be a beginner
[47:04] I know this is supposed to be a beginner tutorial, but this is not really that
[47:06] tutorial, but this is not really that useful and I it's a very easy thing for
[47:08] useful and I it's a very easy thing for me to just bump this up to a little bit
[47:10] me to just bump this up to a little bit more valuable. Um, while relevance tool
[47:12] more valuable. Um, while relevance tool here is great, we can do better. So,
[47:14] here is great, we can do better. So, we're actually going to delete this. Um,
[47:16] we're actually going to delete this. Um, you can use that step for all sorts of
[47:18] you can use that step for all sorts of other things, but I really like what's
[47:20] other things, but I really like what's called fire crawl
[47:23] called fire crawl firecroll web scraper. This is a cool
[47:26] firecroll web scraper. This is a cool app. Um, firecrawl.dev. Shout out to the
[47:29] app. Um, firecrawl.dev. Shout out to the guys at firecraw. Basically, if we then
[47:31] guys at firecraw. Basically, if we then go HTT Oh, I should just see if they can
[47:33] go HTT Oh, I should just see if they can do it. Morningside
[47:37] doti and now do a free scrape for us
[47:40] doti and now do a free scrape for us here. So, this is just going to do the
[47:42] here. So, this is just going to do the single URL just like we got in
[47:43] single URL just like we got in relevance. But the difference here is if
[47:46] relevance. But the difference here is if we then go to crawl, if you hover over
[47:49] we then go to crawl, if you hover over this, it's going to crawl a URL and all
[47:51] this, it's going to crawl a URL and all of its accessible subpages outputting
[47:53] of its accessible subpages outputting the content from each page. So, instead
[47:55] the content from each page. So, instead of just taking that front page, it's
[47:56] of just taking that front page, it's actually going to crawl through multiple
[47:57] actually going to crawl through multiple things. So this is really the first cool
[48:00] things. So this is really the first cool thing or or first skill that I want to
[48:01] thing or or first skill that I want to put in your tool belt is that you have
[48:02] put in your tool belt is that you have things like fire call that you can use
[48:04] things like fire call that you can use their relevance. They have things like
[48:05] their relevance. They have things like map which is just going to output all
[48:06] map which is just going to output all the URLs that it finds. Then there's
[48:08] the URLs that it finds. Then there's other things here where you can use AI
[48:10] other things here where you can use AI to extract data. I'm not going to go
[48:11] to extract data. I'm not going to go into that. But what we want is this
[48:12] into that. But what we want is this crawling functionality from firecraw. So
[48:15] crawling functionality from firecraw. So I'll put a link in on the school post
[48:16] I'll put a link in on the school post that comes with this video. It again
[48:18] that comes with this video. It again first link in the description to go to
[48:19] first link in the description to go to the school and if you go to the YouTube
[48:21] the school and if you go to the YouTube resources section um there will be a uh
[48:23] resources section um there will be a uh a whole post on this and all the
[48:25] a whole post on this and all the resources will be in there. It'll also
[48:26] resources will be in there. It'll also be in my free course on school as well.
[48:28] be in my free course on school as well. So you can find it in the classroom
[48:29] So you can find it in the classroom section. So you want to sign up to FCL
[48:32] section. So you want to sign up to FCL so you can get API key. It's very easy.
[48:34] so you can get API key. It's very easy. We can just go through with Google.
[48:35] We can just go through with Google. Again, this is not sponsored and there
[48:37] Again, this is not sponsored and there is zero sponsoring going on through any
[48:39] is zero sponsoring going on through any of these tools. I guess I'm kind of
[48:40] of these tools. I guess I'm kind of sponsoring my own tool because I'm
[48:41] sponsoring my own tool because I'm putting it at the end. But I'm not
[48:43] putting it at the end. But I'm not getting paid a dime for any of this. I'm
[48:44] getting paid a dime for any of this. I'm really just trying to put you guys on
[48:45] really just trying to put you guys on what I like to use, what's made me
[48:47] what I like to use, what's made me money, what's made me a more valuable AI
[48:49] money, what's made me a more valuable AI automation expert or developer for my
[48:52] automation expert or developer for my companies and for the companies you work
[48:53] companies and for the companies you work with. continue and then you get to the
[48:56] with. continue and then you get to the dashboard here. It might look a bit
[48:57] dashboard here. It might look a bit scary, but what you can do is go to the
[48:58] scary, but what you can do is go to the API keys. So, you can click on create an
[49:00] API keys. So, you can click on create an API key here,
[49:03] API key here, YouTube. I'm having issues with mine. It
[49:05] YouTube. I'm having issues with mine. It should be fine for you. I've already got
[49:06] should be fine for you. I've already got an API key, but once you get the API
[49:07] an API key, but once you get the API key, what you can do is take it and come
[49:09] key, what you can do is take it and come back here to
[49:11] back here to relevance. And you can go into the side
[49:13] relevance. And you can go into the side panel here. Where is it? Settings. And
[49:16] panel here. Where is it? Settings. And then we have our API keys. So, we're
[49:17] then we have our API keys. So, we're going to need to add more into this
[49:18] going to need to add more into this later. So, keep an eye on this. This is
[49:20] later. So, keep an eye on this. This is something you need to be familiar with.
[49:22] something you need to be familiar with. Um, and you can scroll down to firecrawl
[49:23] Um, and you can scroll down to firecrawl and you just pop it into this firecall
[49:25] and you just pop it into this firecall API key section here and you're good to
[49:28] API key section here and you're good to go. And you can come back. Oh no, we
[49:29] go. And you can come back. Oh no, we don't want to duplicate
[49:32] don't want to duplicate that. Now we've got our firewall set up.
[49:35] that. Now we've got our firewall set up. We need to make a couple things. We need
[49:37] We need to make a couple things. We need to do a couple tweaks here. We have, of
[49:39] to do a couple tweaks here. We have, of course, the if you want to get those
[49:41] course, the if you want to get those variables up, you can go bracket bracket
[49:43] variables up, you can go bracket bracket um or curly bracket curly bracket, which
[49:44] um or curly bracket curly bracket, which is shift um to get those. I don't know
[49:46] is shift um to get those. I don't know why it's not popping up. There we go.
[49:49] why it's not popping up. There we go. Company URL. And if we hover over this,
[49:50] Company URL. And if we hover over this, we can see it says scrape the provided
[49:52] we can see it says scrape the provided URL only. Uncheck if we want to crawl
[49:54] URL only. Uncheck if we want to crawl instead. So if we want to get that crawl
[49:56] instead. So if we want to get that crawl functionality that we just saw that we
[49:58] functionality that we just saw that we think we want to get all the data, we
[50:00] think we want to get all the data, we can uh uncheck
[50:02] can uh uncheck it. And then we want to extract the main
[50:05] it. And then we want to extract the main content. So you might have to just trust
[50:06] content. So you might have to just trust me on that one that we don't want to
[50:07] me on that one that we don't want to have all of the other rubbish. We just
[50:09] have all of the other rubbish. We just want the body of the website. Um a
[50:11] want the body of the website. Um a number of pages. We don't want this to
[50:12] number of pages. We don't want this to take too long. You can expand this much
[50:13] take too long. You can expand this much more. Um but I'm just going to go for
[50:15] more. Um but I'm just going to go for say five for now just to keep it uh keep
[50:18] say five for now just to keep it uh keep it quick.
[50:21] it quick. And then now what we can do is run this
[50:23] And then now what we can do is run this again. We've still got my URL up here.
[50:24] again. We've still got my URL up here. We can go run
[50:27] We can go run step. Give it a second. You will at some
[50:29] step. Give it a second. You will at some point have to pay firecrol. Of course,
[50:31] point have to pay firecrol. Of course, it's not a free service, but they do
[50:32] it's not a free service, but they do have a free plan, so you should have no
[50:33] have a free plan, so you should have no issues with getting that. So here you
[50:34] issues with getting that. So here you can see we're getting a lot more data
[50:35] can see we're getting a lot more data back from this web scrape than we were
[50:37] back from this web scrape than we were with just the relevance version, which
[50:39] with just the relevance version, which is great. So the next step is we have
[50:41] is great. So the next step is we have this data. We want to generate some kind
[50:42] this data. We want to generate some kind of research summary um so that we can
[50:44] of research summary um so that we can send that to our sales script once they
[50:46] send that to our sales script once they have requested it. So now it gets into
[50:48] have requested it. So now it gets into the fun part of writing LLM prompts. For
[50:51] the fun part of writing LLM prompts. For this one, sometimes you need to really
[50:53] this one, sometimes you need to really go and and make a big effort, which we
[50:54] go and and make a big effort, which we are going to do later as you'll see. But
[50:56] are going to do later as you'll see. But in this case, we just want a quick
[50:57] in this case, we just want a quick summary. I'm going to throw one in here
[50:59] summary. I'm going to throw one in here that I made earlier. All of this will be
[51:00] that I made earlier. All of this will be available on the Figma or it'll be given
[51:02] available on the Figma or it'll be given somewhere in the resources, right? But
[51:03] somewhere in the resources, right? But um if we just need something quick and
[51:05] um if we just need something quick and dirty here, it's not really a massive
[51:06] dirty here, it's not really a massive part of the project, so it's okay to
[51:08] part of the project, so it's okay to just whack one in there. So bang, I've
[51:09] just whack one in there. So bang, I've got it in there. Can you please take
[51:10] got it in there. Can you please take this website content and summarize it
[51:12] this website content and summarize it into a 300word natural language summary,
[51:14] into a 300word natural language summary, which clearly outlines rad where they're
[51:15] which clearly outlines rad where they're based, their values, etc. anything that
[51:17] based, their values, etc. anything that would be helpful to know for a sales rep
[51:19] would be helpful to know for a sales rep who will soon be on a call with them. Uh
[51:20] who will soon be on a call with them. Uh break it into key areas like overview,
[51:22] break it into key areas like overview, products and services team etc. And I've
[51:24] products and services team etc. And I've got a couple things here to make sure
[51:25] got a couple things here to make sure that it doesn't mess up which I it was
[51:27] that it doesn't mess up which I it was doing for me a bit in testing. So we do
[51:29] doing for me a bit in testing. So we do want to put in if we go curly bracket
[51:30] want to put in if we go curly bracket curly bracket we want to put in the fire
[51:32] curly bracket we want to put in the fire call data here which is going to be uh
[51:34] call data here which is going to be uh all the website data that came back from
[51:36] all the website data that came back from our scrape. We want to then insert it
[51:38] our scrape. We want to then insert it into this prompt here. So I hope you're
[51:39] into this prompt here. So I hope you're starting to the things in your your cogs
[51:40] starting to the things in your your cogs and your brain are starting to click
[51:42] and your brain are starting to click into gear here. And then we get to
[51:43] into gear here. And then we get to select the model for this. It's pretty
[51:45] select the model for this. It's pretty basic task. So, I want something quick
[51:46] basic task. So, I want something quick and cheap. Um, for many of you, it's
[51:48] and cheap. Um, for many of you, it's going to be easiest to work with the
[51:49] going to be easiest to work with the Open AI APIs because you've probably
[51:51] Open AI APIs because you've probably already played around with your API key
[51:52] already played around with your API key before, which I'll show you how to do in
[51:54] before, which I'll show you how to do in a second. But, let's go with GPT40 Mini,
[51:56] a second. But, let's go with GPT40 Mini, but Relevance, of course, does have
[51:58] but Relevance, of course, does have support for all of uh the other models.
[52:00] support for all of uh the other models. But my tendency for most tasks now is to
[52:02] But my tendency for most tasks now is to actually go for some of the Google
[52:03] actually go for some of the Google models that have come out. Again, you
[52:05] models that have come out. Again, you guys might be watching this in a year or
[52:06] guys might be watching this in a year or whatever. It might be quite different,
[52:08] whatever. It might be quite different, but at the moment, Google is really
[52:09] but at the moment, Google is really leading the way with making the cheapest
[52:11] leading the way with making the cheapest models possible, and they're actually
[52:12] models possible, and they're actually really good as well. the the price
[52:14] really good as well. the the price decrease on using things like uh Google
[52:16] decrease on using things like uh Google Gemini Flash Light and Google Gemini
[52:17] Gemini Flash Light and Google Gemini Flash 2.0 and stuff like that. It's
[52:20] Flash 2.0 and stuff like that. It's ridiculously cheap and it's also a
[52:21] ridiculously cheap and it's also a really good model. So, it's a bit more
[52:22] really good model. So, it's a bit more difficult to get APIs on the Google
[52:24] difficult to get APIs on the Google side. So, I'm just going to stick with
[52:25] side. So, I'm just going to stick with OpenAI for this tutorial. Um, so let's
[52:26] OpenAI for this tutorial. Um, so let's go GPT4 mini. And then we need to of
[52:29] go GPT4 mini. And then we need to of course set up our API key. Um, if you
[52:31] course set up our API key. Um, if you scroll down, where is the OpenAI? So, to
[52:33] scroll down, where is the OpenAI? So, to get your OpenAI API key, you need to go
[52:38] platform.openai.com.playground/playgroundplayground,
[52:39] platform.openai.com.playground/playgroundplayground, sorry. Um, this will again be linked in
[52:41] sorry. Um, this will again be linked in the resources or you can just type up
[52:43] the resources or you can just type up platform.openai.com. I'm sure you'll
[52:44] platform.openai.com. I'm sure you'll find it. If you haven't already, create
[52:46] find it. If you haven't already, create an account um, and sign in. And then you
[52:48] an account um, and sign in. And then you need to go to your dashboard here. You
[52:50] need to go to your dashboard here. You go on the left side, you go to API keys,
[52:52] go on the left side, you go to API keys, and you click create a new secret key.
[52:54] and you click create a new secret key. And then you're going to be able to copy
[52:55] And then you're going to be able to copy that key and bring it back into uh,
[52:57] that key and bring it back into uh, relevance. Paste it in here. And then
[52:59] relevance. Paste it in here. And then you're good to go and start using the
[53:00] you're good to go and start using the OpenAI suite of models. It's pretty
[53:02] OpenAI suite of models. It's pretty easy, right? So now we have our
[53:04] easy, right? So now we have our information back from the scrape. We
[53:06] information back from the scrape. We have our prompt in here. And then we can
[53:09] have our prompt in here. And then we can go run step and see what this company
[53:11] go run step and see what this company research tool is going to output for us.
[53:12] research tool is going to output for us. Boom. Morningside AI is a leading
[53:14] Boom. Morningside AI is a leading artificial intelligence development
[53:15] artificial intelligence development company dedicated to empowering
[53:16] company dedicated to empowering businesses autonomous AI agent
[53:18] businesses autonomous AI agent development, enterprise consulting,
[53:19] development, enterprise consulting, chatbot development team. Uh they
[53:23] chatbot development team. Uh they got keep me out of my own team page.
[53:25] got keep me out of my own team page. Damn. But uh yeah, so there you go.
[53:27] Damn. But uh yeah, so there you go. That's the that's the company research
[53:28] That's the that's the company research tool. That's step one. Um I hope you
[53:30] tool. That's step one. Um I hope you guys can kind of see how that works. Now
[53:32] guys can kind of see how that works. Now a cool thing about relevance is there is
[53:33] a cool thing about relevance is there is this build section which we've just gone
[53:35] this build section which we've just gone through. But you can also go to use and
[53:36] through. But you can also go to use and this can be really helpful when sharing
[53:38] this can be really helpful when sharing these kinds of tools. So not this is not
[53:39] these kinds of tools. So not this is not really only just an AI agent tutorial.
[53:41] really only just an AI agent tutorial. I'm also teaching you how to build tools
[53:42] I'm also teaching you how to build tools because you can build very valuable
[53:43] because you can build very valuable tools and something like relevance. And
[53:45] tools and something like relevance. And then you can go share. You can go
[53:48] then you can go share. You can go publicly
[53:49] publicly available. Oh, and I can click this and
[53:52] available. Oh, and I can click this and then I can give to my employees. I can
[53:54] then I can give to my employees. I can give to the companies that I'm working
[53:56] give to the companies that I'm working with, the clients that I've sold these
[53:58] with, the clients that I've sold these kind of services on. And then they get a
[53:59] kind of services on. And then they get a nice and handy tool like this. I mean, I
[54:01] nice and handy tool like this. I mean, I use these throughout my organization for
[54:02] use these throughout my organization for like description generation, a lot of
[54:04] like description generation, a lot of content repurposing. There's tons and
[54:06] content repurposing. There's tons and tons of different use cases for building
[54:07] tons of different use cases for building these kinds of tools. And then you can
[54:08] these kinds of tools. And then you can take this URL and you can share it
[54:09] take this URL and you can share it around to whoever you want. So, this is
[54:11] around to whoever you want. So, this is a uh a great way to use relevance. Let's
[54:13] a uh a great way to use relevance. Let's go back to our tool here. But for now,
[54:15] go back to our tool here. But for now, we need to keep moving along so we can
[54:17] we need to keep moving along so we can get this this first agent done. So,
[54:18] get this this first agent done. So, that's the first tool. I'm going to run
[54:19] that's the first tool. I'm going to run through it a bit quicker now that we
[54:20] through it a bit quicker now that we know how these kind of tool buildings
[54:22] know how these kind of tool buildings work. I'm going to create a new tool
[54:24] work. I'm going to create a new tool here. I'm going to call it this time if
[54:26] here. I'm going to call it this time if we go back to our Figma. And I recommend
[54:28] we go back to our Figma. And I recommend when you guys are building your agents,
[54:29] when you guys are building your agents, you're building systems and planning
[54:30] you're building systems and planning them out. This kind of laying out in a
[54:32] them out. This kind of laying out in a Figma, if you're not familiar, this is
[54:34] Figma, if you're not familiar, this is Figma. It's like a design software, but
[54:35] Figma. It's like a design software, but you can also use it for kind of
[54:36] you can also use it for kind of whiteboarding. It's called a Fig Jam
[54:38] whiteboarding. It's called a Fig Jam board. It's one of the types of uh
[54:39] board. It's one of the types of uh boards you can do. And I use this all
[54:41] boards you can do. And I use this all the time with my team as well. It's like
[54:43] the time with my team as well. It's like if you can't take what I'm telling you,
[54:45] if you can't take what I'm telling you, lay it out on a board so that I can
[54:46] lay it out on a board so that I can review it and give you notes and and
[54:47] review it and give you notes and and then we all agree this is the build. Um
[54:50] then we all agree this is the build. Um there's often a lot of uh communication
[54:51] there's often a lot of uh communication issues with explaining functionality. So
[54:53] issues with explaining functionality. So this AI agent layout, it's really
[54:55] this AI agent layout, it's really helpful. You can if it's maybe a
[54:57] helpful. You can if it's maybe a workflow automation, you can do box box
[54:58] workflow automation, you can do box box arrow arrow arrow all of this laying out
[55:00] arrow arrow arrow all of this laying out how it's going to be built. Here I've
[55:02] how it's going to be built. Here I've done it for you in a very basic format.
[55:04] done it for you in a very basic format. So we've done this first one. Maybe I
[55:05] So we've done this first one. Maybe I just make this green. Um second one is
[55:07] just make this green. Um second one is going to be prospect researcher. So this
[55:09] going to be prospect researcher. So this takes in a LinkedIn URL, searches the
[55:11] takes in a LinkedIn URL, searches the web, and returns a summary. And you're
[55:13] web, and returns a summary. And you're going to see how I tie this all into an
[55:14] going to see how I tie this all into an agent
[55:15] agent shortly. So we're going to go research
[55:18] shortly. So we're going to go research prospect. Sil takes in a linked in URL
[55:22] prospect. Sil takes in a linked in URL scrapes the profile and then generates
[55:25] scrapes the profile and then generates an of the prospect input. We're going to
[55:28] an of the prospect input. We're going to need a link and URL the link linked and
[55:32] need a link and URL the link linked and URL of the prospect.
[55:35] URL of the prospect. and we rename
[55:40] this. Now, we're going to add a step and
[55:43] this. Now, we're going to add a step and relevance has got us here linked
[55:46] relevance has got us here linked um get a LinkedIn profile or company
[55:50] um get a LinkedIn profile or company post. So, this is cool cuz then we can
[55:52] post. So, this is cool cuz then we can pop in our LinkedIn URL
[55:55] pop in our LinkedIn URL here. Oh, we don't need two of
[56:01] them. So, we're going to get the user
[56:03] them. So, we're going to get the user profile here. Then if I put in
[56:08] mine my LinkedIn profile, if you guys
[56:10] mine my LinkedIn profile, if you guys want to connect with me on LinkedIn,
[56:12] want to connect with me on LinkedIn, more than welcome to do so. I'll put in
[56:13] more than welcome to do so. I'll put in the description below. Um, we can do a
[56:17] the description below. Um, we can do a little run step here. So, if we go back
[56:19] little run step here. So, if we go back over to data here, that's great. We've
[56:22] over to data here, that's great. We've got my about section. So, this goes very
[56:24] got my about section. So, this goes very long way across because it's in uh it's
[56:26] long way across because it's in uh it's in JSON here. It's got my company. It's
[56:29] in JSON here. It's got my company. It's got my company domain, where I'm from,
[56:33] got my company domain, where I'm from, years, company, founded, tons and tons
[56:34] years, company, founded, tons and tons of great information that you guys can
[56:36] of great information that you guys can use and we are going to use shortly. So,
[56:37] use and we are going to use shortly. So, this is really cool. I would probably
[56:39] this is really cool. I would probably add one more step to this if I was
[56:40] add one more step to this if I was taking this um and building it for for
[56:42] taking this um and building it for for my own team. I would add in another
[56:44] my own team. I would add in another LinkedIn scrape here um where we just do
[56:46] LinkedIn scrape here um where we just do the same thing, but we also get the
[56:48] the same thing, but we also get the posts because posts can give you a bit
[56:50] posts because posts can give you a bit more up to date um information on what
[56:51] more up to date um information on what they've been doing recently. that you
[56:53] they've been doing recently. that you can guys can add that and you just go
[56:54] can guys can add that and you just go add a step LinkedIn and you do the same
[56:57] add a step LinkedIn and you do the same thing as we've done here but you change
[56:59] thing as we've done here but you change this to LinkedIn post get user post so
[57:02] this to LinkedIn post get user post so that may be a cool thing for you guys to
[57:03] that may be a cool thing for you guys to add the uh functionality on at the end
[57:05] add the uh functionality on at the end is a bit of a challenge you can pause
[57:06] is a bit of a challenge you can pause this video and do that and then we need
[57:07] this video and do that and then we need a llm step to take this again I'm going
[57:10] a llm step to take this again I'm going to grab a pre-written prompt that I did
[57:12] to grab a pre-written prompt that I did just to save some time going to drop
[57:13] just to save some time going to drop this in here says fairly similar stuff
[57:17] this in here says fairly similar stuff um LinkedIn data I'm going to put all
[57:21] um LinkedIn data I'm going to put all the data in
[57:23] the data in there. And then we're going to use a
[57:25] there. And then we're going to use a GPT4 mini again. And we can give that a
[57:28] GPT4 mini again. And we can give that a run because we've already got this data
[57:30] run because we've already got this data queued up here. And there we go. We've
[57:31] queued up here. And there we go. We've got a nice summary. Um, if I change this
[57:34] got a nice summary. Um, if I change this to nice and formatted. So there's a
[57:36] to nice and formatted. So there's a little button down there between raw or
[57:38] little button down there between raw or formatted. And you can copy the stuff
[57:39] formatted. And you can copy the stuff out of here, of course. So Liam Mley, my
[57:41] out of here, of course. So Liam Mley, my followers. Damn, I got a lot more than I
[57:43] followers. Damn, I got a lot more than I thought. So there we have the summary,
[57:44] thought. So there we have the summary, my name, where I'm based, uh,
[57:46] my name, where I'm based, uh, information, my career experience. Super
[57:48] information, my career experience. Super handy stuff. And this is going to be
[57:50] handy stuff. And this is going to be super helpful in the next step when we
[57:51] super helpful in the next step when we generate that pre-core report. So very
[57:53] generate that pre-core report. So very quickly, we've created one more tool.
[57:55] quickly, we've created one more tool. I'm going to save this. So now we've
[57:56] I'm going to save this. So now we've got, if we go back to our Figma, we have
[57:59] got, if we go back to our Figma, we have two of these done. Now the final one is
[58:02] two of these done. Now the final one is going to take in the company and
[58:03] going to take in the company and prospect research and generate a
[58:05] prospect research and generate a pre-call report. So this one's going to
[58:06] pre-call report. So this one's going to be a little bit different. If I go
[58:08] be a little bit different. If I go create a new
[58:11] create a new tool, preall report
[58:16] tool, preall report tool. Okay, free call takes in company
[58:19] tool. Okay, free call takes in company and prospect summary and generates a
[58:21] and prospect summary and generates a free call report for sales
[58:24] free call report for sales direct. And now for the inputs for this,
[58:26] direct. And now for the inputs for this, we need long text, not just normal text
[58:28] we need long text, not just normal text because we're going to be taking in that
[58:29] because we're going to be taking in that big company and uh and prospect
[58:31] big company and uh and prospect research. So we go prospect summary
[58:34] research. So we go prospect summary summary of the prospect based on length
[58:37] summary of the prospect based on length and profile
[58:41] that and a prospect in this case is
[58:43] that and a prospect in this case is someone who's a potential customer. Just
[58:45] someone who's a potential customer. Just to clarify that if you're new to
[58:47] to clarify that if you're new to business and don't really get these
[58:48] business and don't really get these terms. Company summary, uh,
[58:56] summary, right? We have our prospect
[58:58] summary, right? We have our prospect summary and company summary in there. I
[59:00] summary and company summary in there. I hope you're following along. Next step
[59:01] hope you're following along. Next step is just an LLM step and we want to
[59:03] is just an LLM step and we want to combine these two together. Again, I've
[59:04] combine these two together. Again, I've got a little handy prompt for this to
[59:06] got a little handy prompt for this to save us time. Now, in this case, you
[59:07] save us time. Now, in this case, you will see that the prompt is a bit
[59:08] will see that the prompt is a bit bigger, right? So this is um for more
[59:11] bigger, right? So this is um for more important parts when you are creating
[59:12] important parts when you are creating tools whether it's it's for agents or
[59:14] tools whether it's it's for agents or just generally when you're using prompt
[59:15] just generally when you're using prompt engineering and LLMs to create value. In
[59:17] engineering and LLMs to create value. In this case we are creating value because
[59:19] this case we are creating value because in this case we're taking in this
[59:20] in this case we're taking in this prospect summary and this company
[59:22] prospect summary and this company summary. We're also giving it the the
[59:24] summary. We're also giving it the the context of this fantasy or or
[59:26] context of this fantasy or or hypothetical business that we are
[59:28] hypothetical business that we are selling this agent to as like a co-pilot
[59:30] selling this agent to as like a co-pilot system. We've got Big Boy Recruits which
[59:32] system. We've got Big Boy Recruits which is Dallas based recruitment firm
[59:33] is Dallas based recruitment firm specializing in software industry talent
[59:35] specializing in software industry talent acquisition for SMBs. You're going to
[59:37] acquisition for SMBs. You're going to see this kind of recur across the
[59:38] see this kind of recur across the different projects we do, but basically
[59:39] different projects we do, but basically we're helping these big boy recruits to
[59:41] we're helping these big boy recruits to automate their business with AI. So,
[59:43] automate their business with AI. So, this takes in some context on that
[59:45] this takes in some context on that business and it's going to generate a a
[59:47] business and it's going to generate a a report that's going to help the sales
[59:48] report that's going to help the sales rep say, "Okay, this is the company.
[59:49] rep say, "Okay, this is the company. This is what we sell. This is what we
[59:51] This is what we sell. This is what we specialize in. This is the company that
[59:52] specialize in. This is the company that we're trying to sell to. This is who
[59:54] we're trying to sell to. This is who we're going to be talking to. What's
[59:55] we're going to be talking to. What's some how can I personalize this call or
[59:57] some how can I personalize this call or what's the strategy I can go into this
[59:58] what's the strategy I can go into this with? What are some angles that I can
[01:00:00] with? What are some angles that I can attack this call from?" And so to do
[01:00:02] attack this call from?" And so to do this, I have a prompt writing tool that
[01:00:04] this, I have a prompt writing tool that I use quite regularly and my team uses
[01:00:06] I use quite regularly and my team uses it as well. Um, perfect
[01:00:09] it as well. Um, perfect prompt. So, this tool does a lot of leg
[01:00:11] prompt. So, this tool does a lot of leg work for myself and my team all the
[01:00:13] work for myself and my team all the time. I'm going to give it to you guys
[01:00:14] time. I'm going to give it to you guys to use for free. You'll be able to clone
[01:00:15] to use for free. You'll be able to clone it into your relevance account.
[01:00:17] it into your relevance account. Basically, what I'll usually do is I'll
[01:00:18] Basically, what I'll usually do is I'll put on uh the dictation thing. You've
[01:00:20] put on uh the dictation thing. You've got it on one of these keyboards. You've
[01:00:22] got it on one of these keyboards. You've got this little thing. basically
[01:00:24] got this little thing. basically whatever on your computer allows you to
[01:00:26] whatever on your computer allows you to speak into the computer and it takes in
[01:00:28] speak into the computer and it takes in your voice and transcribes it into into
[01:00:30] your voice and transcribes it into into text on the screen. I'll press that and
[01:00:32] text on the screen. I'll press that and then I'll explain as you can see here
[01:00:33] then I'll explain as you can see here what is this prompt doing and why and
[01:00:35] what is this prompt doing and why and I'll go this prompt needs to do this
[01:00:36] I'll go this prompt needs to do this this this is going to take in this
[01:00:37] this this is going to take in this information it's going to do this the
[01:00:39] information it's going to do this the reason we're doing this is this this and
[01:00:40] reason we're doing this is this this and I'll do like a big big body of text in
[01:00:43] I'll do like a big big body of text in there and then the next one if I have
[01:00:44] there and then the next one if I have them I'll give some good examples of
[01:00:46] them I'll give some good examples of input and output pairs of how I want it
[01:00:48] input and output pairs of how I want it to take in data and how I want it to
[01:00:49] to take in data and how I want it to spit it out. If you give it both of
[01:00:51] spit it out. If you give it both of these and you hit run, it's going to
[01:00:52] these and you hit run, it's going to print you out using the researchbacked
[01:00:54] print you out using the researchbacked prompting techniques that we use at
[01:00:55] prompting techniques that we use at Morningside. It's all crammed in here.
[01:00:57] Morningside. It's all crammed in here. There's a video that I recommend all of
[01:00:59] There's a video that I recommend all of you watch. It's going to be in the free
[01:01:00] you watch. It's going to be in the free course anyway on school. So, when you
[01:01:01] course anyway on school. So, when you get in there and watch my prompt
[01:01:02] get in there and watch my prompt engineering guide, um, this is basically
[01:01:04] engineering guide, um, this is basically the entire information of that prompt
[01:01:05] the entire information of that prompt engineering guide smashed into this LLM
[01:01:08] engineering guide smashed into this LLM step here. So, when you pass this
[01:01:09] step here. So, when you pass this information in, it applies all of that
[01:01:10] information in, it applies all of that and it gives you out a prompt that is
[01:01:12] and it gives you out a prompt that is fully researched back and performs very,
[01:01:14] fully researched back and performs very, very well right out of the box. So,
[01:01:15] very well right out of the box. So, that's a little bit of extra value I
[01:01:16] that's a little bit of extra value I wanted to throw in there for you guys.
[01:01:17] wanted to throw in there for you guys. this is going to be available on the
[01:01:18] this is going to be available on the school um with the rest of the resources
[01:01:20] school um with the rest of the resources as well. So basically I put in the
[01:01:22] as well. So basically I put in the information here about what this
[01:01:23] information here about what this particular uh task was. I said it's
[01:01:26] particular uh task was. I said it's going to take in the prospect
[01:01:27] going to take in the prospect information. It's going to take in the
[01:01:28] information. It's going to take in the prospect summary and the company
[01:01:29] prospect summary and the company information and it spat out this
[01:01:31] information and it spat out this basically first go and I just had to
[01:01:33] basically first go and I just had to insert these variables. So this prompt
[01:01:34] insert these variables. So this prompt and everything else will be on the on
[01:01:35] and everything else will be on the on the score resources as well. So in this
[01:01:37] the score resources as well. So in this case because we are doing a bit of
[01:01:38] case because we are doing a bit of strategy and sort of high level thinking
[01:01:40] strategy and sort of high level thinking rather than just summarizing and we may
[01:01:41] rather than just summarizing and we may want to change the model here to
[01:01:43] want to change the model here to something a bit smarter. We could go to
[01:01:44] something a bit smarter. We could go to 03 mini which is one of the later ones.
[01:01:46] 03 mini which is one of the later ones. Um, again, when you're watching this, it
[01:01:48] Um, again, when you're watching this, it might be 06 or 010 or whatever the hell
[01:01:50] might be 06 or 010 or whatever the hell they come up with next, but there's
[01:01:52] they come up with next, but there's probably going to be some much better
[01:01:53] probably going to be some much better models. So, just use a smart one because
[01:01:54] models. So, just use a smart one because it's really strategizing on how big boy
[01:01:57] it's really strategizing on how big boy recruits can position themselves for
[01:01:58] recruits can position themselves for this call. So, enough of me yapping
[01:02:00] this call. So, enough of me yapping about that. Let me grab some inputs for
[01:02:02] about that. Let me grab some inputs for this and we can test
[01:02:05] [Music]
[01:02:06] [Music] it. Shout out muscle. All right. So,
[01:02:08] it. Shout out muscle. All right. So, I've got this information here about
[01:02:10] I've got this information here about myself, my LinkedIn profile, and my
[01:02:12] myself, my LinkedIn profile, and my company. And so again, remember that
[01:02:13] company. And so again, remember that this is for Big Boy Recruits, a Dallas
[01:02:15] this is for Big Boy Recruits, a Dallas recruitment firm specialized in software
[01:02:16] recruitment firm specialized in software industry talent. So it's going to look
[01:02:18] industry talent. So it's going to look at my company, Morningside AI. It's
[01:02:20] at my company, Morningside AI. It's going to look at me and my background
[01:02:21] going to look at me and my background and my profile on LinkedIn. Then it's
[01:02:23] and my profile on LinkedIn. Then it's going to spin, as we see here, um,
[01:02:25] going to spin, as we see here, um, review this, analyze this, map big boys
[01:02:27] review this, analyze this, map big boys unique value proposition, ra, and it's
[01:02:29] unique value proposition, ra, and it's going to try and create a report that's
[01:02:32] going to try and create a report that's going to allow the sales rep to sell me
[01:02:33] going to allow the sales rep to sell me or close me better on there or find some
[01:02:35] or close me better on there or find some angles to sell to at least. So if we go
[01:02:37] angles to sell to at least. So if we go run tool, and now you see that I'm using
[01:02:38] run tool, and now you see that I'm using a lot of just basic web scraping and LLM
[01:02:40] a lot of just basic web scraping and LLM steps. I just want to show you guys the
[01:02:41] steps. I just want to show you guys the basics. The thing is tools can get very
[01:02:43] basics. The thing is tools can get very very advanced when you have like CRM you
[01:02:45] very advanced when you have like CRM you want to integrate into, but relevance
[01:02:47] want to integrate into, but relevance allows you to do all of that. It's just
[01:02:48] allows you to do all of that. It's just within the scope of tutorial, it can be
[01:02:50] within the scope of tutorial, it can be pretty difficult to be pulling
[01:02:51] pretty difficult to be pulling information from all over the here cuz I
[01:02:52] information from all over the here cuz I have to set up a database, show you guys
[01:02:54] have to set up a database, show you guys how to do it, too. So, this this keeps
[01:02:56] how to do it, too. So, this this keeps it quite confined, but it still gives
[01:02:57] it quite confined, but it still gives you a good taste of it. So, if we look
[01:02:59] you a good taste of it. So, if we look at this view, all key business
[01:03:01] at this view, all key business challenges and opportunity, Morningside
[01:03:03] challenges and opportunity, Morningside AI, this Liam's profile gives me a bit
[01:03:05] AI, this Liam's profile gives me a bit of a rundown of this mapping big boy
[01:03:07] of a rundown of this mapping big boy recruits unique value proposition. Maybe
[01:03:08] recruits unique value proposition. Maybe it's going to be better if I change this
[01:03:10] it's going to be better if I change this to the format. There we go. Talks about
[01:03:13] to the format. There we go. Talks about mapping big boys recruits, strategic
[01:03:15] mapping big boys recruits, strategic talking points. I've been following your
[01:03:17] talking points. I've been following your journey of digital marketing, AI, ra um
[01:03:20] journey of digital marketing, AI, ra um dive into opportunity. I work at big
[01:03:21] dive into opportunity. I work at big boys. This assist, and it's even gone
[01:03:23] boys. This assist, and it's even gone and done a section on anticipated
[01:03:24] and done a section on anticipated objections. So, the idea is that the
[01:03:26] objections. So, the idea is that the sales rep is going to have a skimmer of
[01:03:27] sales rep is going to have a skimmer of this before the call, which ties into
[01:03:29] this before the call, which ties into the value that I've listed here, which
[01:03:31] the value that I've listed here, which I'm going to do for all of these builds,
[01:03:32] I'm going to do for all of these builds, by the way, which comes down to
[01:03:33] by the way, which comes down to ultimately a better prepared sales rep
[01:03:35] ultimately a better prepared sales rep should close more deals, right? if they
[01:03:37] should close more deals, right? if they know more about the prospect and the
[01:03:38] know more about the prospect and the company and you have an angle to try
[01:03:40] company and you have an angle to try sell through or suggestions at least. It
[01:03:42] sell through or suggestions at least. It should increase the conversion rate of
[01:03:43] should increase the conversion rate of the sales team. So, we've built this
[01:03:44] the sales team. So, we've built this tool. We can change this to green now.
[01:03:47] tool. We can change this to green now. And the final step is going to be
[01:03:48] And the final step is going to be heading over to our agent builder within
[01:03:50] heading over to our agent builder within relevance. I'm going to save this. If
[01:03:52] relevance. I'm going to save this. If you pop over in the left panel here, you
[01:03:54] you pop over in the left panel here, you can go into our agents. And what we want
[01:03:56] can go into our agents. And what we want to do is create a new
[01:03:59] to do is create a new agent. We're going to call it our sales
[01:04:03] agent. We're going to call it our sales co-pilot.
[01:04:05] co-pilot. Um, big
[01:04:07] Um, big boy big boy sales co-pilot. Sorry, I
[01:04:11] boy big boy sales co-pilot. Sorry, I got, like I said, I got to have fun with
[01:04:12] got, like I said, I got to have fun with the stuff where I go kind of insane. Um,
[01:04:14] the stuff where I go kind of insane. Um, this this agent is
[01:04:18] this this agent is our sales co-pilot that helps reps to be
[01:04:25] our sales co-pilot that helps reps to be better prepared for sales
[01:04:28] better prepared for sales [Music]
[01:04:30] [Music] calls. Triggers, we don't need to do any
[01:04:32] calls. Triggers, we don't need to do any of that. We go to core instructions. I'm
[01:04:34] of that. We go to core instructions. I'm going to again paste in some of the
[01:04:35] going to again paste in some of the stuff that I've prepped earlier. So, if
[01:04:36] stuff that I've prepped earlier. So, if I paste this in here, you'll see that
[01:04:37] I paste this in here, you'll see that it's structured fairly similarly to the
[01:04:39] it's structured fairly similarly to the prompt that we just did before for the
[01:04:41] prompt that we just did before for the uh pre-core report generator. And this
[01:04:43] uh pre-core report generator. And this is again using another tool that I've
[01:04:44] is again using another tool that I've created um for AI agent prompting. Um
[01:04:47] created um for AI agent prompting. Um so, it's fairly similar stuff that I I
[01:04:49] so, it's fairly similar stuff that I I include in that other prompting tool,
[01:04:50] include in that other prompting tool, but the agents is slightly different um
[01:04:53] but the agents is slightly different um to just regular LLM steps within
[01:04:55] to just regular LLM steps within different tools and workflow
[01:04:56] different tools and workflow automations. So, I will include this as
[01:04:58] automations. So, I will include this as well. It's my AI agent perfect prompt
[01:05:00] well. It's my AI agent perfect prompt generator and it's fairly
[01:05:01] generator and it's fairly straightforward to use. I'll include
[01:05:02] straightforward to use. I'll include that in there as well. But basically,
[01:05:04] that in there as well. But basically, you put in all the information about
[01:05:05] you put in all the information about what the agent is, why it's doing it,
[01:05:06] what the agent is, why it's doing it, the different tools that you're
[01:05:07] the different tools that you're connecting to it, and then it prints out
[01:05:09] connecting to it, and then it prints out this for you. So, I'll just run through
[01:05:10] this for you. So, I'll just run through it. We've got a role here telling it who
[01:05:11] it. We've got a role here telling it who it is, um, and kind of hyping it up and
[01:05:13] it is, um, and kind of hyping it up and saying how good it is. Explains the
[01:05:15] saying how good it is. Explains the task, um, talking about how it's helping
[01:05:16] task, um, talking about how it's helping to conduct detailed research on
[01:05:18] to conduct detailed research on companies and prospects. Um, some
[01:05:20] companies and prospects. Um, some specifics. Uh, don't need to worry about
[01:05:21] specifics. Uh, don't need to worry about those too much. Just reiterating the
[01:05:23] those too much. Just reiterating the task. And now here we can enter in the
[01:05:25] task. And now here we can enter in the references to tools. So if we go slash
[01:05:27] references to tools. So if we go slash tool and see in order to get the agent
[01:05:29] tool and see in order to get the agent to function as well as possible, we need
[01:05:31] to function as well as possible, we need to tell it what tools it has available.
[01:05:33] to tell it what tools it has available. This is really key across all the agents
[01:05:35] This is really key across all the agents you build, especially if they're more
[01:05:36] you build, especially if they're more conversational. You need to explain to
[01:05:38] conversational. You need to explain to them what tools they have and how and
[01:05:40] them what tools they have and how and when they should use them. So if I go,
[01:05:41] when they should use them. So if I go, you have three powerful tools. Research
[01:05:45] company. Um, yep, that's right. Purpose,
[01:05:48] company. Um, yep, that's right. Purpose, input, company URL, use when needing to
[01:05:50] input, company URL, use when needing to gather company information. This one of
[01:05:52] gather company information. This one of course is the uh
[01:05:56] prospect. And then this last one is our
[01:06:01] prospect. And then this last one is our [Music]
[01:06:02] [Music] pre. There we go. So that's all whacked
[01:06:04] pre. There we go. So that's all whacked in there. Don't need to worry about that
[01:06:05] in there. Don't need to worry about that too much. But again, this will be
[01:06:07] too much. But again, this will be included um this prompt and everything
[01:06:08] included um this prompt and everything if you want to follow along and also if
[01:06:10] if you want to follow along and also if you just want to clone the whole agent
[01:06:11] you just want to clone the whole agent um and use it in your own business or
[01:06:13] um and use it in your own business or sell it or whatever you want to do. We
[01:06:14] sell it or whatever you want to do. We also get to select the model here. Um
[01:06:16] also get to select the model here. Um I'm just going to keep it as GPT4 mini.
[01:06:18] I'm just going to keep it as GPT4 mini. I like some pretty fast responses here
[01:06:19] I like some pretty fast responses here because agents as someone's using it, it
[01:06:21] because agents as someone's using it, it can feel really irritating if it's not
[01:06:23] can feel really irritating if it's not responding quickly. So, we've got all
[01:06:25] responding quickly. So, we've got all that built out. That's the core
[01:06:26] that built out. That's the core instructions in the prompt of the agent.
[01:06:28] instructions in the prompt of the agent. Um, we can go down to the uh tools
[01:06:31] Um, we can go down to the uh tools section. It's got all the tools
[01:06:33] section. It's got all the tools connected in here because we mentioned
[01:06:34] connected in here because we mentioned them in the prompt. And we can just go
[01:06:36] them in the prompt. And we can just go through and do some quick settings on
[01:06:37] through and do some quick settings on here. Um, I don't want to have to do an
[01:06:39] here. Um, I don't want to have to do an approval for it. Some tools you can say,
[01:06:41] approval for it. Some tools you can say, look, they've got to give it a thumbs up
[01:06:42] look, they've got to give it a thumbs up before it can actually uh trigger it.
[01:06:44] before it can actually uh trigger it. Um, prompt for how to use. Just some
[01:06:46] Um, prompt for how to use. Just some quick descriptions we can pop in here.
[01:06:48] quick descriptions we can pop in here. I'm not sure why relevance doesn't carry
[01:06:49] I'm not sure why relevance doesn't carry that over from the tool. I guess they're
[01:06:50] that over from the tool. I guess they're asking us to do it again for some
[01:06:52] asking us to do it again for some reason. Um when you need to research a
[01:06:54] reason. Um when you need to research a uh
[01:06:55] uh prospect linked and URL, we're going to
[01:07:00] prospect linked and URL, we're going to say this is auto run as well. Um and
[01:07:03] say this is auto run as well. Um and then preall change this to auto run as
[01:07:05] then preall change this to auto run as well.
[01:07:07] well. Use this when you need to generate a pre
[01:07:11] Use this when you need to generate a pre call report from the company and
[01:07:15] call report from the company and prospect
[01:07:18] research. All righty. Um, and there's
[01:07:20] research. All righty. Um, and there's all sorts of other cool stuff.
[01:07:21] all sorts of other cool stuff. Relevance, as you can see, is like
[01:07:23] Relevance, as you can see, is like abilities, sub aents, metadata, extra
[01:07:24] abilities, sub aents, metadata, extra stuff that you can build onto. Um, but I
[01:07:26] stuff that you can build onto. Um, but I just want to get you guys started with
[01:07:27] just want to get you guys started with the core of this. Um, all right. So, we
[01:07:30] the core of this. Um, all right. So, we can confirm
[01:07:33] that. And boom, we have our agent here
[01:07:36] that. And boom, we have our agent here ready to go. So this is where you can
[01:07:37] ready to go. So this is where you can test your agents and use them if you
[01:07:38] test your agents and use them if you want to. But in this case, I'm just
[01:07:40] want to. But in this case, I'm just going to give it a quick rundown and say
[01:07:42] going to give it a quick rundown and say see if the functionality is working as
[01:07:43] see if the functionality is working as we as we planned. Um, hi, I am getting
[01:07:47] we as we planned. Um, hi, I am getting on a call with Liam Otley from morning
[01:07:53] on a call with Liam Otley from morning side
[01:07:55] side AI. Here uh has
[01:07:59] AI. Here uh has details or we can just go
[01:08:06] [Music]
[01:08:15] lenol report please to prep for the
[01:08:19] lenol report please to prep for the call. Sending your task to big boy sales
[01:08:22] call. Sending your task to big boy sales copilot. And then we get to see all the
[01:08:24] copilot. And then we get to see all the debug and how it's actually walking
[01:08:26] debug and how it's actually walking through these different steps. Oh, let's
[01:08:28] through these different steps. Oh, let's see what he
[01:08:31] does. Yep. Okay, that's great. It's
[01:08:34] does. Yep. Okay, that's great. It's using the research company as we wanted
[01:08:36] using the research company as we wanted it
[01:08:37] it to. Should add in one more step there to
[01:08:40] to. Should add in one more step there to research the prospect as
[01:08:42] research the prospect as well. There we go. Using the second
[01:08:44] well. There we go. Using the second tool. It is pretty satisfying when this
[01:08:46] tool. It is pretty satisfying when this stuff works. And this is just a really
[01:08:48] stuff works. And this is just a really basic one, guys. I don't want you to
[01:08:49] basic one, guys. I don't want you to think this is like, oh, well, that's
[01:08:51] think this is like, oh, well, that's pretty underwhelming, Liam. I'm trying
[01:08:52] pretty underwhelming, Liam. I'm trying to teach you the basics so that you can
[01:08:54] to teach you the basics so that you can actually build on top of this. So if you
[01:08:56] actually build on top of this. So if you get the bug, if you get the like you get
[01:08:58] get the bug, if you get the like you get a travel bug, if you get the agent bug
[01:09:00] a travel bug, if you get the agent bug and you see the stuff and you're really
[01:09:01] and you see the stuff and you're really interested. Oh, look, there it is. Now
[01:09:03] interested. Oh, look, there it is. Now it's filling out the prospect summary as
[01:09:04] it's filling out the prospect summary as the inputs. Surely we don't have to
[01:09:06] the inputs. Surely we don't have to watch it do that. It's going to take a
[01:09:09] watch it do that. It's going to take a while.
[01:09:11] while. [Music]
[01:09:12] [Music] Um, I really write that out word for
[01:09:15] Um, I really write that out word for word like that. But when you start to
[01:09:16] word like that. But when you start to see this magic and you add in other cool
[01:09:18] see this magic and you add in other cool tools and functionality, you test it on
[01:09:20] tools and functionality, you test it on yourself. You can build like things for
[01:09:21] yourself. You can build like things for maybe you want to do content, you make
[01:09:22] maybe you want to do content, you make yourself a little content co-pilot,
[01:09:25] yourself a little content co-pilot, etc. There we go. To use all the tools
[01:09:28] etc. There we go. To use all the tools and it should be spitting back and bam,
[01:09:29] and it should be spitting back and bam, there we go. So, I hope that was worth
[01:09:31] there we go. So, I hope that was worth the wait. Let's go through it now.
[01:09:32] the wait. Let's go through it now. Here's your comprehensive precore report
[01:09:34] Here's your comprehensive precore report for your upcoming conversation with Liam
[01:09:35] for your upcoming conversation with Liam Mley from Morningside AI. Pre-core
[01:09:37] Mley from Morningside AI. Pre-core report. Talent acquisition under
[01:09:39] report. Talent acquisition under pressure. Morningside AI operates in a
[01:09:40] pressure. Morningside AI operates in a highly competitive AI and tech market as
[01:09:42] highly competitive AI and tech market as they scale. Finding specialized talent,
[01:09:44] they scale. Finding specialized talent, engineers, data scientists, AI with a
[01:09:46] engineers, data scientists, AI with a proven record can be challenging. That's
[01:09:49] proven record can be challenging. That's scarily accurate because that is
[01:09:50] scarily accurate because that is literally one of the biggest constraints
[01:09:51] literally one of the biggest constraints that we have had to scaling Morningside
[01:09:53] that we have had to scaling Morningside long-term is that it's just really
[01:09:54] long-term is that it's just really really hard even with my channel. It's
[01:09:56] really hard even with my channel. It's so hard to find the right people and get
[01:09:58] so hard to find the right people and get them to commit as as developers as well.
[01:10:00] them to commit as as developers as well. So if you want to build a very big
[01:10:01] So if you want to build a very big general AI development firm, an AI
[01:10:03] general AI development firm, an AI automation agency, you need the best
[01:10:05] automation agency, you need the best talent and you need to get a lot of it
[01:10:06] talent and you need to get a lot of it in um so that you can scale up. So
[01:10:08] in um so that you can scale up. So that's bloody spot on. Obviously this
[01:10:10] that's bloody spot on. Obviously this thing knows that's a good angle to sell
[01:10:12] thing knows that's a good angle to sell through. Um but yeah, prospect analysis.
[01:10:14] through. Um but yeah, prospect analysis. Liam's a dynamic entrepreneur and
[01:10:16] Liam's a dynamic entrepreneur and thought
[01:10:17] thought leader with a robust background in
[01:10:19] leader with a robust background in e-commerce, digital marketing and AI.
[01:10:21] e-commerce, digital marketing and AI. His journey reflects a passion for
[01:10:22] His journey reflects a passion for innovation and commitment to continuous
[01:10:24] innovation and commitment to continuous learning. Again, that's pretty bloody
[01:10:26] learning. Again, that's pretty bloody spot on um hands-on experience. So there
[01:10:29] spot on um hands-on experience. So there you go. That is the big boy sales
[01:10:31] you go. That is the big boy sales co-pilot for big boy recruits. The cool
[01:10:33] co-pilot for big boy recruits. The cool thing you can do now once you have built
[01:10:34] thing you can do now once you have built this um is you can go share um there's a
[01:10:38] this um is you can go share um there's a chat UI which I'm going to turn on now.
[01:10:40] chat UI which I'm going to turn on now. There are chat widgets so you can put
[01:10:41] There are chat widgets so you can put them on websites and stuff like that.
[01:10:43] them on websites and stuff like that. What I want to do is just pull this up
[01:10:44] What I want to do is just pull this up because this is what you'd be giving to
[01:10:46] because this is what you'd be giving to your client likely or if you guys are
[01:10:48] your client likely or if you guys are going to start selling these to
[01:10:49] going to start selling these to businesses which again we're touching on
[01:10:50] businesses which again we're touching on selling in the last section of this
[01:10:52] selling in the last section of this video. So how do you turn these into
[01:10:53] video. So how do you turn these into into a business and start making money
[01:10:55] into a business and start making money from it and selling these as a as a
[01:10:56] from it and selling these as a as a service and building these businesses
[01:10:58] service and building these businesses which is really where the money's money
[01:10:59] which is really where the money's money is made. So there you go. This URL you
[01:11:00] is made. So there you go. This URL you can obviously send to your client. If
[01:11:02] can obviously send to your client. If you're building it for your own team,
[01:11:03] you're building it for your own team, you can send this to your team and say,
[01:11:04] you can send this to your team and say, "Hey, pin this because you're going to
[01:11:06] "Hey, pin this because you're going to be able to use it. Add more
[01:11:07] be able to use it. Add more functionality into it, etc. That is how
[01:11:09] functionality into it, etc. That is how you build a co-pilot on relevance AI.
[01:11:16] All righty, that is build number one out
[01:11:18] All righty, that is build number one out of the way and we are jumping into AI
[01:11:20] of the way and we are jumping into AI agent build number two, which if you're
[01:11:22] agent build number two, which if you're listening closely at the start of the
[01:11:23] listening closely at the start of the section, we are talking about an
[01:11:26] section, we are talking about an NATbased inbound lead qualification
[01:11:28] NATbased inbound lead qualification agent that's going to be doing some
[01:11:29] agent that's going to be doing some pretty cool stuff for us, which is a
[01:11:31] pretty cool stuff for us, which is a really important function within a
[01:11:32] really important function within a business um around lead qualification.
[01:11:34] business um around lead qualification. Um, so this is a really cool one. Again,
[01:11:36] Um, so this is a really cool one. Again, in this case, this is what we call an
[01:11:37] in this case, this is what we call an automated agent, not a conversational
[01:11:38] automated agent, not a conversational one. What we just built is a
[01:11:40] one. What we just built is a conversational agent. humans are
[01:11:41] conversational agent. humans are directly talking to it and chatting back
[01:11:43] directly talking to it and chatting back and forth and using it and we are
[01:11:44] and forth and using it and we are operating it ourselves. In this case, as
[01:11:46] operating it ourselves. In this case, as you can see on this little flow uh flow
[01:11:48] you can see on this little flow uh flow diagram here, this is a screenshot from
[01:11:49] diagram here, this is a screenshot from the final product. We are actually
[01:11:51] the final product. We are actually baking this into a workflow that's going
[01:11:53] baking this into a workflow that's going to be triggered on a form submission.
[01:11:55] to be triggered on a form submission. We're going to do some research and then
[01:11:56] We're going to do some research and then we're going to use the handy AI agent
[01:11:58] we're going to use the handy AI agent and tools agent within NA10 to trigger
[01:12:00] and tools agent within NA10 to trigger another workflow and then send some
[01:12:02] another workflow and then send some emails off. So, this capability of using
[01:12:04] emails off. So, this capability of using AI agents in workflow automation really
[01:12:06] AI agents in workflow automation really expands the possibilities of what you
[01:12:08] expands the possibilities of what you can build. And the software NAN that I'm
[01:12:10] can build. And the software NAN that I'm going to teach you how to use is really
[01:12:11] going to teach you how to use is really at the the cutting edge and leading the
[01:12:13] at the the cutting edge and leading the charge when it comes to these automated
[01:12:14] charge when it comes to these automated uh AI agent workflows. And just quickly,
[01:12:16] uh AI agent workflows. And just quickly, it's good that we walk through the
[01:12:17] it's good that we walk through the purpose and the value behind this
[01:12:18] purpose and the value behind this automation so that we know why we're
[01:12:19] automation so that we know why we're doing it. Right? So this inbound lead
[01:12:21] doing it. Right? So this inbound lead qualification use case is based on the
[01:12:22] qualification use case is based on the fact that companies who market
[01:12:23] fact that companies who market themselves well soon have far too many
[01:12:25] themselves well soon have far too many people reaching out to them. Many of
[01:12:27] people reaching out to them. Many of which are not a good fit or what you'd
[01:12:28] which are not a good fit or what you'd call qualified for what they sell. Eg
[01:12:31] call qualified for what they sell. Eg they're too small or they're not the
[01:12:32] they're too small or they're not the right industry. Like you you have a
[01:12:33] right industry. Like you you have a business and they say we only help XYZ
[01:12:36] business and they say we only help XYZ kinds of businesses. And if leads come
[01:12:37] kinds of businesses. And if leads come to that business who are not qualified,
[01:12:38] to that business who are not qualified, then they obviously don't want to be
[01:12:40] then they obviously don't want to be taking calls or or doing anything
[01:12:41] taking calls or or doing anything further with them. So this process of
[01:12:43] further with them. So this process of researching a new lead and deciding
[01:12:44] researching a new lead and deciding whether or not to take a call is known
[01:12:46] whether or not to take a call is known as qualification, which is what this
[01:12:48] as qualification, which is what this agent aims to automate. So the value
[01:12:50] agent aims to automate. So the value here is that instead of having to pay
[01:12:51] here is that instead of having to pay someone to manually qualify and go
[01:12:52] someone to manually qualify and go through all of these leads or using
[01:12:54] through all of these leads or using arbitrary rules, which is what some
[01:12:56] arbitrary rules, which is what some businesses have to go to, it's like
[01:12:57] businesses have to go to, it's like look, oh look, we've got so many leads.
[01:12:59] look, oh look, we've got so many leads. Let's just say if they don't want if
[01:13:00] Let's just say if they don't want if they say that they're not on this, then
[01:13:01] they say that they're not on this, then we'll just cut them out. And that's
[01:13:02] we'll just cut them out. And that's potentially leaving money on the table
[01:13:04] potentially leaving money on the table by cutting out leads who would have
[01:13:05] by cutting out leads who would have actually been a good deal, but the rules
[01:13:07] actually been a good deal, but the rules kind of didn't see enough detail to be
[01:13:09] kind of didn't see enough detail to be able to determine if they're a good fit
[01:13:10] able to determine if they're a good fit or not. So, this automation is
[01:13:12] or not. So, this automation is essentially immediately qualifying and
[01:13:14] essentially immediately qualifying and triggering the next steps to the sales
[01:13:15] triggering the next steps to the sales team and allowing them to do that human
[01:13:17] team and allowing them to do that human style research on these leads at scale.
[01:13:19] style research on these leads at scale. So, enough talking. Here's a little bit
[01:13:21] So, enough talking. Here's a little bit more information. Again, with all of
[01:13:22] more information. Again, with all of these, it's going to be on the figure on
[01:13:23] these, it's going to be on the figure on the school. Then, I've also broken down
[01:13:24] the school. Then, I've also broken down how this agent would actually operate in
[01:13:26] how this agent would actually operate in the real world and sort of real time. A
[01:13:28] the real world and sort of real time. A lead's going to be submitting the form,
[01:13:30] lead's going to be submitting the form, which is going to be this here. um the
[01:13:32] which is going to be this here. um the relevance company AI researcher. So
[01:13:33] relevance company AI researcher. So something that we've just built in
[01:13:34] something that we've just built in relevance, we're going to reuse in here,
[01:13:36] relevance, we're going to reuse in here, which is handy that you can start to
[01:13:37] which is handy that you can start to move these components around and see how
[01:13:38] move these components around and see how they can fit into different automation
[01:13:39] they can fit into different automation platforms. Um then the AI agent is going
[01:13:42] platforms. Um then the AI agent is going to look at this information from the
[01:13:43] to look at this information from the research. Then it's going to determine
[01:13:44] research. Then it's going to determine based on a qualification criteria we
[01:13:46] based on a qualification criteria we give them um inside the prompt of this
[01:13:48] give them um inside the prompt of this agent whether they are qualified or not.
[01:13:50] agent whether they are qualified or not. If they are qualified, it's going to uh
[01:13:53] If they are qualified, it's going to uh use this tool here and call this second
[01:13:55] use this tool here and call this second workflow. when we're going to
[01:13:56] workflow. when we're going to essentially analyze that further and do
[01:13:58] essentially analyze that further and do a notification to either our agency team
[01:14:00] a notification to either our agency team or our our SAS team and if they are not
[01:14:03] or our our SAS team and if they are not qualified we will use this tool here
[01:14:05] qualified we will use this tool here which will just send an email straight
[01:14:06] which will just send an email straight back to the person who submitted the
[01:14:07] back to the person who submitted the form say hey sorry we're not open to
[01:14:09] form say hey sorry we're not open to working with businesses like yourself at
[01:14:10] working with businesses like yourself at the moment let us know if we can help
[01:14:12] the moment let us know if we can help you any other way so that's a rough
[01:14:14] you any other way so that's a rough rundown of the build let's jump into it
[01:14:15] rundown of the build let's jump into it so to kick things off of course you need
[01:14:16] so to kick things off of course you need a platform on natn.io
[01:14:20] a platform on natn.io io. All links and resources will of
[01:14:21] io. All links and resources will of course be on the school uh post for this
[01:14:23] course be on the school uh post for this video. And once you're on this page, you
[01:14:24] video. And once you're on this page, you can go to get started and you can create
[01:14:27] can go to get started and you can create an account for free and just go through
[01:14:29] an account for free and just go through the setup process that they do. I'm sure
[01:14:30] the setup process that they do. I'm sure you can figure that out. They do have a
[01:14:32] you can figure that out. They do have a 14-day free trial as of this filming. So
[01:14:34] 14-day free trial as of this filming. So that's very good if you're just jumping
[01:14:35] that's very good if you're just jumping in, not having to pay anything. And they
[01:14:36] in, not having to pay anything. And they give you quite a lot of usage up here.
[01:14:37] give you quite a lot of usage up here. As you can see, 1,000 executions. So
[01:14:39] As you can see, 1,000 executions. So what we're going to do, of course, is
[01:14:40] what we're going to do, of course, is click on create workflow up here. I will
[01:14:42] click on create workflow up here. I will be giving you the template. So if you
[01:14:43] be giving you the template. So if you want to just import it, you can. That
[01:14:45] want to just import it, you can. That will be on the Figma there. But just
[01:14:46] will be on the Figma there. But just like the last tutorial, I'm actually
[01:14:47] like the last tutorial, I'm actually going to be showing you the process of
[01:14:49] going to be showing you the process of building these up from scratch that you
[01:14:50] building these up from scratch that you can see how I how you go through the
[01:14:52] can see how I how you go through the process of building these automations
[01:14:54] process of building these automations and the the testing and back and forth
[01:14:56] and the the testing and back and forth you need to do in order to get to the
[01:14:57] you need to do in order to get to the end result. That's probably actually a
[01:14:58] end result. That's probably actually a lot more important if you are to go out
[01:15:00] lot more important if you are to go out if I'm trying to teach you to fish, not
[01:15:01] if I'm trying to teach you to fish, not just give you a fish, is to see how I
[01:15:03] just give you a fish, is to see how I deal with problems when we're building
[01:15:04] deal with problems when we're building these. So, let's get started by starting
[01:15:06] these. So, let's get started by starting off our trigger. We're going to go
[01:15:09] off our trigger. We're going to go form has a nice
[01:15:12] form has a nice form on new inn form event. And here we
[01:15:15] form on new inn form event. And here we get to create an N8N form. So we can
[01:15:17] get to create an N8N form. So we can call it uh work with
[01:15:21] call it uh work with us. Provide
[01:15:26] your. So now we get to pick the field
[01:15:29] your. So now we get to pick the field names. So we want to have the first one
[01:15:31] names. So we want to have the first one which is what
[01:15:35] is make that a required field. We add
[01:15:37] is make that a required field. We add another one. What is your company
[01:15:40] another one. What is your company website?
[01:15:42] website? DG HTTP this morning. Require
[01:15:51] field. Right. So, we've just built out a
[01:15:53] field. Right. So, we've just built out a basic form here with first name, company
[01:15:55] basic form here with first name, company website, which we're going to need for
[01:15:56] website, which we're going to need for the next step. I've put a placeholder in
[01:15:58] the next step. I've put a placeholder in here so they know that it needs to have
[01:15:59] here so they know that it needs to have https um at the front of it. And I'm
[01:16:02] https um at the front of it. And I'm asking for them to provide some
[01:16:03] asking for them to provide some information about your inquiry like and
[01:16:05] information about your inquiry like and maybe you can say what can we help
[01:16:07] maybe you can say what can we help you? Um and that's going to be text
[01:16:10] you? Um and that's going to be text area. So, they've got a bit more room.
[01:16:11] area. So, they've got a bit more room. So, we can go test step here. Make sure
[01:16:12] So, we can go test step here. Make sure that it's all looking nice. This is what
[01:16:14] that it's all looking nice. This is what the form's going to look like. What's
[01:16:15] the form's going to look like. What's your name?
[01:16:20] Obby. There we go. We've submitted that
[01:16:22] Obby. There we go. We've submitted that form. If you go back, there we go. We
[01:16:24] form. If you go back, there we go. We have the data in. So, this shows you the
[01:16:26] have the data in. So, this shows you the output. NAM works by having kind of this
[01:16:28] output. NAM works by having kind of this middle island here, which is what you
[01:16:29] middle island here, which is what you set up. And then the left side is the
[01:16:31] set up. And then the left side is the input and the right side is the output.
[01:16:33] input and the right side is the output. So, we've tested it and these are the
[01:16:34] So, we've tested it and these are the outputs that our form is giving, which
[01:16:36] outputs that our form is giving, which is what we are looking for. And the next
[01:16:38] is what we are looking for. And the next step in this lead qualification process
[01:16:39] step in this lead qualification process is to do some research on the lead. So
[01:16:42] is to do some research on the lead. So we have the company URL and this is when
[01:16:44] we have the company URL and this is when we're going to go and make an HTTP
[01:16:46] we're going to go and make an HTTP request. So this is basically calling
[01:16:48] request. So this is basically calling any API over the internet. And in order
[01:16:50] any API over the internet. And in order to set this up, we actually need to go
[01:16:51] to set this up, we actually need to go back to
[01:16:55] relevance and we're going to find the
[01:16:57] relevance and we're going to find the company researcher tool that we made
[01:16:58] company researcher tool that we made with relevance. And now you're going to
[01:16:59] with relevance. And now you're going to start to see how this all fits together.
[01:17:01] start to see how this all fits together. um that building tools and relevance can
[01:17:03] um that building tools and relevance can also be very useful and an extremely
[01:17:05] also be very useful and an extremely useful skill in all areas of AI
[01:17:07] useful skill in all areas of AI automation because now I can come on to
[01:17:09] automation because now I can come on to research company and not only can I use
[01:17:11] research company and not only can I use it here this I mean this is why I think
[01:17:13] it here this I mean this is why I think relevance is such a great platform um
[01:17:15] relevance is such a great platform um you have the use here so I can send this
[01:17:17] you have the use here so I can send this across to a client I can share it with
[01:17:18] across to a client I can share it with it as I showed before I can use it just
[01:17:20] it as I showed before I can use it just here myself I can run it in bulk on a
[01:17:22] here myself I can run it in bulk on a spreadsheet or but more importantly in
[01:17:24] spreadsheet or but more importantly in this case I can go to the API and now I
[01:17:27] this case I can go to the API and now I can call this might look scary just
[01:17:29] can call this might look scary just don't worry I can call this
[01:17:31] don't worry I can call this functionality basically send in a
[01:17:33] functionality basically send in a company URL and get back the research. I
[01:17:35] company URL and get back the research. I can access this over the internet
[01:17:36] can access this over the internet through an API and they give me it here
[01:17:38] through an API and they give me it here and they tell me exactly how to call it.
[01:17:40] and they tell me exactly how to call it. So now we this is on actually a post
[01:17:41] So now we this is on actually a post request. So we can copy this. Remember
[01:17:44] request. So we can copy this. Remember how we talked about get and post
[01:17:46] how we talked about get and post request. This is a post request because
[01:17:47] request. This is a post request because we're posting some data to relevant AI.
[01:17:49] we're posting some data to relevant AI. So we change this method to post. We put
[01:17:52] So we change this method to post. We put the URL in here. We do not need
[01:17:54] the URL in here. We do not need authentication in this case but you can
[01:17:56] authentication in this case but you can turn it on. So you can make a private
[01:17:57] turn it on. So you can make a private here and then you can have an
[01:17:58] here and then you can have an authenticated. might sound a bit
[01:17:59] authenticated. might sound a bit complicated but for now don't worry
[01:18:00] complicated but for now don't worry about it we don't need to have an
[01:18:02] about it we don't need to have an authentication step on
[01:18:04] authentication step on this and then if we look at the request
[01:18:07] this and then if we look at the request body here it tells us how we can send
[01:18:09] body here it tells us how we can send data to relevant AI and if we go copy
[01:18:13] data to relevant AI and if we go copy here come back we're going to send a
[01:18:16] here come back we're going to send a body it's going to be in
[01:18:20] JSON and we can change this to using
[01:18:23] JSON and we can change this to using JSON and then we can paste in basically
[01:18:26] JSON and then we can paste in basically what we have been given from relevant AI
[01:18:27] what we have been given from relevant AI now this looks a messy. Let's pop this
[01:18:29] now this looks a messy. Let's pop this open a bit
[01:18:31] open a bit more. And we actually need to change it
[01:18:33] more. And we actually need to change it to an expression here. So fixed means
[01:18:35] to an expression here. So fixed means that we're not accepting any dynamic
[01:18:37] that we're not accepting any dynamic data in. So when the form is submitted,
[01:18:39] data in. So when the form is submitted, we actually need to take in some data
[01:18:40] we actually need to take in some data from that form which we have over here.
[01:18:42] from that form which we have over here. We need to inject it into this uh HTTP
[01:18:44] We need to inject it into this uh HTTP request to relevant AI to get this
[01:18:46] request to relevant AI to get this company research done. So we can't have
[01:18:48] company research done. So we can't have it as a fixed um JSON body here. Need to
[01:18:51] it as a fixed um JSON body here. Need to change it to expression and then we can
[01:18:53] change it to expression and then we can pop this out here and it gets a bit
[01:18:54] pop this out here and it gets a bit easier. So, we have params. We have the
[01:18:56] easier. So, we have params. We have the company URL. And then we need to pop in
[01:18:59] company URL. And then we need to pop in here. Oh, the company
[01:19:03] here. Oh, the company URL. Pop that in there. And here on the
[01:19:05] URL. Pop that in there. And here on the right side, we get to see what that
[01:19:06] right side, we get to see what that would look like given the test data that
[01:19:08] would look like given the test data that we've just put through. So, you can see
[01:19:10] we've just put through. So, you can see I've got the company URL, https
[01:19:12] I've got the company URL, https morningside.ai in quotations here, which
[01:19:13] morningside.ai in quotations here, which is what we want. So, we can go back now.
[01:19:15] is what we want. So, we can go back now. And now we can give it a test to see if
[01:19:17] And now we can give it a test to see if it's going to be able to communicate
[01:19:18] it's going to be able to communicate with relevant AI and get us the data we
[01:19:21] with relevant AI and get us the data we want. There we go. We have our result
[01:19:24] want. There we go. We have our result back from relevant AI which is the
[01:19:26] back from relevant AI which is the summary. As you can see when we go back
[01:19:28] summary. As you can see when we go back to this um and back to build this is
[01:19:31] to this um and back to build this is exactly what we'd expect. You know you
[01:19:33] exactly what we'd expect. You know you put in the URL does this scrape a fire
[01:19:35] put in the URL does this scrape a fire call writes the summary spits out the
[01:19:37] call writes the summary spits out the summary and this summary is what we're
[01:19:38] summary and this summary is what we're getting back out over here which is what
[01:19:40] getting back out over here which is what we want. So bank that's great another
[01:19:42] we want. So bank that's great another step
[01:19:43] step done. And those of you who are a bit
[01:19:45] done. And those of you who are a bit confused about what this is this is just
[01:19:46] confused about what this is this is just the body of the request. So because we
[01:19:48] the body of the request. So because we are sending a post request remember how
[01:19:50] are sending a post request remember how we have get and post request. Get
[01:19:51] we have get and post request. Get requests are typically just with a URL
[01:19:53] requests are typically just with a URL and with a bunch of stuff tacked on. A
[01:19:54] and with a bunch of stuff tacked on. A post request, we need to send a a JSON
[01:19:57] post request, we need to send a a JSON body like this. And it does look quite
[01:19:59] body like this. And it does look quite confusing, but if I take this and go
[01:20:01] confusing, but if I take this and go JSON
[01:20:06] form, paste this in and beautify it. And
[01:20:09] form, paste this in and beautify it. And you can see how we have basically the
[01:20:10] you can see how we have basically the project which is the relevant project
[01:20:12] project which is the relevant project that we are calling. And this tells the
[01:20:14] that we are calling. And this tells the API this is the project that we want to
[01:20:15] API this is the project that we want to interact with. and the project expects
[01:20:18] interact with. and the project expects the params, the inputs, which is the
[01:20:20] the params, the inputs, which is the company URL, and we're injecting that
[01:20:22] company URL, and we're injecting that company URL from our information here in
[01:20:25] company URL from our information here in NA10 that we've dragged across. It might
[01:20:26] NA10 that we've dragged across. It might seem tricky a few times, but trust me,
[01:20:28] seem tricky a few times, but trust me, this stuff becomes like riding a bike
[01:20:29] this stuff becomes like riding a bike once you get up and running. So, um, a
[01:20:31] once you get up and running. So, um, a few more of these and you'll be you'll
[01:20:32] few more of these and you'll be you'll be completely fine. All right. And so
[01:20:34] be completely fine. All right. And so now that we have our company
[01:20:34] now that we have our company information, the next step is going to
[01:20:36] information, the next step is going to be setting up the agent, which is really
[01:20:38] be setting up the agent, which is really the coolest part in my opinion about
[01:20:39] the coolest part in my opinion about make right now is that we come in here
[01:20:41] make right now is that we come in here and we can click on um agent and we can
[01:20:44] and we can click on um agent and we can set it to as a tools agent, which means
[01:20:46] set it to as a tools agent, which means we connect our own tools. And if we just
[01:20:48] we connect our own tools. And if we just back out of
[01:20:49] back out of this, we can do cool things like set up
[01:20:52] this, we can do cool things like set up the model. And right here, this is so
[01:20:53] the model. And right here, this is so cool because we get to see exactly what
[01:20:55] cool because we get to see exactly what we were just talking about earlier in
[01:20:57] we were just talking about earlier in this video, but we have the different
[01:20:59] this video, but we have the different parts of an agent, the different
[01:21:00] parts of an agent, the different ingredients, right? So here's the chat
[01:21:01] ingredients, right? So here's the chat model. This is the brain. This is the
[01:21:03] model. This is the brain. This is the LLM that's going to be powering the
[01:21:04] LLM that's going to be powering the whole agent using the soup example. Like
[01:21:06] whole agent using the soup example. Like this is the one meat that we get to
[01:21:08] this is the one meat that we get to choose, right? This is a specific model.
[01:21:10] choose, right? This is a specific model. In this case, we going to be using
[01:21:11] In this case, we going to be using OpenAI again because you already have
[01:21:13] OpenAI again because you already have your API key and I can't really be
[01:21:14] your API key and I can't really be bothered going and showing you a whole
[01:21:15] bothered going and showing you a whole another provider, but it's the same
[01:21:16] another provider, but it's the same process for all of them. You can if you
[01:21:18] process for all of them. You can if you want anthropic, you can then pick all
[01:21:20] want anthropic, you can then pick all the anthropic models. Uh but in this
[01:21:22] the anthropic models. Uh but in this case, just to keep it simple, let's just
[01:21:23] case, just to keep it simple, let's just go back
[01:21:26] to and open AI model.
[01:21:30] to and open AI model. And if we go back again, you can see
[01:21:32] And if we go back again, you can see that we now have uh the memory and the
[01:21:34] that we now have uh the memory and the tools that we can connect. So, of
[01:21:35] tools that we can connect. So, of course, we have the tools, which we've
[01:21:37] course, we have the tools, which we've talked about a lot in this video
[01:21:38] talked about a lot in this video already. We can connect multiple
[01:21:39] already. We can connect multiple different tools here, as we're going to
[01:21:40] different tools here, as we're going to do in a second. And then we also have
[01:21:41] do in a second. And then we also have memory set up here, which is a little
[01:21:43] memory set up here, which is a little bit outside of the scope of this video.
[01:21:44] bit outside of the scope of this video. As I said, in most platforms, it comes
[01:21:46] As I said, in most platforms, it comes builtin, but NAT is a bit more of a
[01:21:47] builtin, but NAT is a bit more of a developercentric platform. So, if you
[01:21:49] developercentric platform. So, if you wanted to play around with memory, um
[01:21:50] wanted to play around with memory, um different forms of of managing memory,
[01:21:52] different forms of of managing memory, you can do that here. In our case, we're
[01:21:53] you can do that here. In our case, we're not going to be touching it. And in
[01:21:55] not going to be touching it. And in order to connect a knowledge base, if we
[01:21:57] order to connect a knowledge base, if we wanted to set up a knowledge base for
[01:21:58] wanted to set up a knowledge base for our agent, we would connect it as a
[01:22:00] our agent, we would connect it as a tool. So you can see here we've got
[01:22:01] tool. So you can see here we've got in-memory vector store, pine cone vector
[01:22:03] in-memory vector store, pine cone vector stores, etc. These are vector databases
[01:22:05] stores, etc. These are vector databases that we can connect just like in the
[01:22:07] that we can connect just like in the other tutorials we're going to do in
[01:22:08] other tutorials we're going to do in this video. When you upload some
[01:22:09] this video. When you upload some documents to make a knowledge base,
[01:22:10] documents to make a knowledge base, they're essentially being put in a
[01:22:12] they're essentially being put in a vector store like these, but the
[01:22:13] vector store like these, but the platforms manage it for you and make it
[01:22:15] platforms manage it for you and make it a lot easier to do. So in this case,
[01:22:16] a lot easier to do. So in this case, we're just going to be doing two
[01:22:18] we're just going to be doing two different tools. Firstly, we're going to
[01:22:19] different tools. Firstly, we're going to be calling an NATM workflow. So I'm just
[01:22:21] be calling an NATM workflow. So I'm just going to finish off the the basic setup
[01:22:23] going to finish off the the basic setup of this. Um, and then we're going to add
[01:22:24] of this. Um, and then we're going to add another tool on. It's going to be the
[01:22:26] another tool on. It's going to be the Gmail
[01:22:28] Gmail tool. And then before you know it, we
[01:22:30] tool. And then before you know it, we have our AI agent structure built out.
[01:22:32] have our AI agent structure built out. So, we're using the Open AI models.
[01:22:34] So, we're using the Open AI models. We're going to pick the model shortly.
[01:22:36] We're going to pick the model shortly. We're going to be using the tool to call
[01:22:37] We're going to be using the tool to call the second NATM workflow, which is going
[01:22:39] the second NATM workflow, which is going to be uh triggering the the email
[01:22:41] to be uh triggering the the email notifications for our sales reps and the
[01:22:43] notifications for our sales reps and the classification of the uh of the lead.
[01:22:45] classification of the uh of the lead. That's going to make a bit more sense
[01:22:46] That's going to make a bit more sense when we actually do it. So, just stick
[01:22:48] when we actually do it. So, just stick with me on this. And then this Gmail is
[01:22:49] with me on this. And then this Gmail is going to be sending back a hey sorry you
[01:22:52] going to be sending back a hey sorry you didn't qualify for what we do um sorry
[01:22:55] didn't qualify for what we do um sorry we can't help you let us know if we can
[01:22:56] we can't help you let us know if we can do anything else for so to start setting
[01:22:58] do anything else for so to start setting things up we can start from left to
[01:22:59] things up we can start from left to right here with the chat model um the
[01:23:00] right here with the chat model um the openai model that we want to use and you
[01:23:02] openai model that we want to use and you need to set up your openai account so
[01:23:04] need to set up your openai account so you can click create new credential and
[01:23:05] you can click create new credential and you need to go and add in your API key
[01:23:07] you need to go and add in your API key here I'd suggest you go and make a new
[01:23:08] here I'd suggest you go and make a new one on platform openai.com and you can
[01:23:11] one on platform openai.com and you can add a new one in here and you can name
[01:23:12] add a new one in here and you can name the key nat so you start to know which
[01:23:14] the key nat so you start to know which keys are used for which different
[01:23:16] keys are used for which different platforms um and once you put that in
[01:23:18] platforms um and once you put that in there you can Just click save and then
[01:23:19] there you can Just click save and then it will run a little test and then
[01:23:20] it will run a little test and then you're ready to go. You should have this
[01:23:21] you're ready to go. You should have this set up here. Then we get to select the
[01:23:23] set up here. Then we get to select the model that we want to use for our agent
[01:23:24] model that we want to use for our agent here. And in this case, I want to go for
[01:23:26] here. And in this case, I want to go for something quite smart. So, I'm going to
[01:23:27] something quite smart. So, I'm going to go for
[01:23:28] go for 03. We have 03 mini here. This one
[01:23:31] 03. We have 03 mini here. This one appears to be a little bit more recent.
[01:23:32] appears to be a little bit more recent. So, they'll sometimes put the dates on
[01:23:34] So, they'll sometimes put the dates on the end of it. And if you just look at
[01:23:35] the end of it. And if you just look at the current date, you can kind of see
[01:23:36] the current date, you can kind of see how how close to the current date it is.
[01:23:38] how how close to the current date it is. Um, but I'd say this one's a bit more
[01:23:39] Um, but I'd say this one's a bit more recent, so it's going to be hopefully a
[01:23:40] recent, so it's going to be hopefully a bit better. And next, we're going to
[01:23:42] bit better. And next, we're going to skip this cuz we need to set up a whole
[01:23:43] skip this cuz we need to set up a whole different workflow to connect it to. Um,
[01:23:45] different workflow to connect it to. Um, we're going to jump straight into this
[01:23:46] we're going to jump straight into this Gmail one. You need to set up again
[01:23:47] Gmail one. You need to set up again another connection as you go through all
[01:23:49] another connection as you go through all of these different automation platforms.
[01:23:50] of these different automation platforms. You do need to do these these
[01:23:52] You do need to do these these connections between uh your own account,
[01:23:54] connections between uh your own account, say your Gmail or your calendar or all
[01:23:56] say your Gmail or your calendar or all these different apps. You need to go and
[01:23:57] these different apps. You need to go and create a new credential. Um and you can
[01:23:59] create a new credential. Um and you can just do the sign in with Google here.
[01:24:01] just do the sign in with Google here. Super easy to do. I'm sure you don't
[01:24:02] Super easy to do. I'm sure you don't need my help with that. Once you've set
[01:24:04] need my help with that. Once you've set up that connection, you can close this
[01:24:05] up that connection, you can close this and you will see the connection that you
[01:24:07] and you will see the connection that you set up here. Basically, that's what
[01:24:08] set up here. Basically, that's what we're going to be sending emails
[01:24:09] we're going to be sending emails through. And then we can get into
[01:24:10] through. And then we can get into setting this up. So, because this Gmail
[01:24:12] setting this up. So, because this Gmail tool is going to be used to send a a
[01:24:14] tool is going to be used to send a a reply back to the person who submitted
[01:24:15] reply back to the person who submitted the form and say, "Hey, sorry, you're
[01:24:17] the form and say, "Hey, sorry, you're not a good fit for us." You want to send
[01:24:18] not a good fit for us." You want to send it back to the person who submitted the
[01:24:19] it back to the person who submitted the form. Now, if you scroll down here, uh,
[01:24:21] form. Now, if you scroll down here, uh, yep, you see that I've I've forgotten to
[01:24:24] yep, you see that I've I've forgotten to add the email form in. So, this is a
[01:24:25] add the email form in. So, this is a good example of needing to go back a
[01:24:27] good example of needing to go back a little bit. So, we can go back to the
[01:24:28] little bit. So, we can go back to the form submission here. Um, scroll down,
[01:24:31] form submission here. Um, scroll down, say, what is your
[01:24:35] say, what is your email? And we can set it as an email.
[01:24:37] email? And we can set it as an email. So, it's going to automatically force
[01:24:39] So, it's going to automatically force them to provide a valid email for us.
[01:24:41] them to provide a valid email for us. And I want to maybe shimmy this up a
[01:24:42] And I want to maybe shimmy this up a bit.
[01:24:45] Um, so it's name, email, then company,
[01:24:49] Um, so it's name, email, then company, website. Um, we can do another test here
[01:24:52] website. Um, we can do another test here just to give it some proper
[01:24:55] just to give it some proper data. Oh, it's not going to let us do
[01:24:57] data. Oh, it's not going to let us do that because this isn't set up properly.
[01:24:58] that because this isn't set up properly. So, we can just delete that for
[01:25:01] So, we can just delete that for now. And we're actually going to delete
[01:25:03] now. And we're actually going to delete that. Otherwise, it's going to be a bit
[01:25:04] that. Otherwise, it's going to be a bit of a pain.
[01:25:06] of a pain. So, we want to test it
[01:25:13] again. So, we can submit another form
[01:25:15] again. So, we can submit another form here and go back to NA10. And there we
[01:25:19] here and go back to NA10. And there we go. We have the information. We have the
[01:25:20] go. We have the information. We have the email now. That's great. And so, now we
[01:25:22] email now. That's great. And so, now we can come and set up our tools again.
[01:25:23] can come and set up our tools again. We've got the workflow there and we've
[01:25:25] We've got the workflow there and we've got the
[01:25:28] got the Gmail. Um, and now we have our
[01:25:30] Gmail. Um, and now we have our connection set up. Yep.
[01:25:36] Oh, and we haven't got the data here
[01:25:38] Oh, and we haven't got the data here because we need to run this
[01:25:41] because we need to run this again and get the research. So, now the
[01:25:43] again and get the research. So, now the research is done in there for us to set
[01:25:44] research is done in there for us to set up the Gmail tool here. We can go to two
[01:25:47] up the Gmail tool here. We can go to two and we'll be able to pull in the email.
[01:25:49] and we'll be able to pull in the email. So, again, they submit this form. We
[01:25:51] So, again, they submit this form. We realize that they're not a qualified uh
[01:25:52] realize that they're not a qualified uh person for our offer. And then we're
[01:25:54] person for our offer. And then we're going to send an email back and say,
[01:25:55] going to send an email back and say, "Hey, sorry, you're not a good fit." So,
[01:25:56] "Hey, sorry, you're not a good fit." So, we can say the subject here is um thanks
[01:25:59] we can say the subject here is um thanks for your interest. I'm going to change
[01:26:02] for your interest. I'm going to change the email type to text here and I'm
[01:26:04] the email type to text here and I'm going to write a basic message in. I'm
[01:26:05] going to write a basic message in. I'm just going to snag it from the one that
[01:26:07] just going to snag it from the one that I've done previously. So, we need to
[01:26:08] I've done previously. So, we need to change this from fix to an expression
[01:26:10] change this from fix to an expression because we want to be pulling in their
[01:26:11] because we want to be pulling in their name here. So, I'm going to paste in
[01:26:13] name here. So, I'm going to paste in what I have here. Again, this would be
[01:26:14] what I have here. Again, this would be included um in the resources. It's just
[01:26:16] included um in the resources. It's just going to save us time if I don't have to
[01:26:17] going to save us time if I don't have to type this all out manually. Um but you
[01:26:19] type this all out manually. Um but you can see here, I'll just delete this so
[01:26:20] can see here, I'll just delete this so you guys know what we're doing. If I go
[01:26:23] you guys know what we're doing. If I go hi, or hi, and then we can add in what
[01:26:26] hi, or hi, and then we can add in what is your first name? Hi, name. In this
[01:26:29] is your first name? Hi, name. In this case, it's going to be filling in my
[01:26:30] case, it's going to be filling in my name here as an example. So, highly mly,
[01:26:32] name here as an example. So, highly mly, thank you for your interest in big boy
[01:26:33] thank you for your interest in big boy recruitment services as you specialize
[01:26:35] recruitment services as you specialize in recruitment for software and
[01:26:36] in recruitment for software and development agencies. We're not a good
[01:26:38] development agencies. We're not a good fit based on your company's industry.
[01:26:39] fit based on your company's industry. Please let us know if you'd like to
[01:26:40] Please let us know if you'd like to connect us with one of your partners who
[01:26:41] connect us with one of your partners who specializes in dealing with your needs.
[01:26:43] specializes in dealing with your needs. Cheers. Huge Jackman here to sales, big
[01:26:46] Cheers. Huge Jackman here to sales, big boy recruits, BBR, uh, Dallas, Texas.
[01:26:48] boy recruits, BBR, uh, Dallas, Texas. So, if you guys remember huge Jackman,
[01:26:50] So, if you guys remember huge Jackman, comment down below um for the OG fans.
[01:26:52] comment down below um for the OG fans. And then that is our Gmail all set up.
[01:26:54] And then that is our Gmail all set up. And just quickly so that you've got a
[01:26:56] And just quickly so that you've got a bit more knowledge around how this Gmail
[01:26:57] bit more knowledge around how this Gmail uh tool works, we have all these
[01:26:59] uh tool works, we have all these different steps that we can use. We're
[01:27:00] different steps that we can use. We're using the send one. So it's sending an
[01:27:02] using the send one. So it's sending an email. You can use reply, you can use
[01:27:04] email. You can use reply, you can use get, delete, all these other functions,
[01:27:05] get, delete, all these other functions, but the easiest one and the most common
[01:27:07] but the easiest one and the most common one you're going to use is going to be
[01:27:08] one you're going to use is going to be that send one, of course. Now, we need
[01:27:09] that send one, of course. Now, we need to set up this NATM workflow which the
[01:27:11] to set up this NATM workflow which the agent is going to call as a tool um when
[01:27:13] agent is going to call as a tool um when they are a qualified prospect. So I'm
[01:27:15] they are a qualified prospect. So I'm going to delete this one and just save
[01:27:16] going to delete this one and just save this for now. Then we're going to go
[01:27:18] this for now. Then we're going to go back
[01:27:20] back to home. We're going to create a new
[01:27:23] to home. We're going to create a new workflow.
[01:27:25] workflow. And this is a really cool skill that I
[01:27:26] And this is a really cool skill that I want to teach you. The fact that you can
[01:27:27] want to teach you. The fact that you can build all these workflows and then
[01:27:28] build all these workflows and then connect them to agents and it can just
[01:27:30] connect them to agents and it can just be taking data in and kind of shooting
[01:27:32] be taking data in and kind of shooting it off in all directions and triggering
[01:27:33] it off in all directions and triggering all these complex multi-step processes
[01:27:36] all these complex multi-step processes because it's a super valuable way of
[01:27:37] because it's a super valuable way of using agents. Um, so I really want to
[01:27:39] using agents. Um, so I really want to teach you that. And obviously this one's
[01:27:40] teach you that. And obviously this one's going to be starting off a bit different
[01:27:42] going to be starting off a bit different to the other one. We actually want this
[01:27:43] to the other one. We actually want this to be set up as when executed by another
[01:27:45] to be set up as when executed by another workflow. So that's going to be what the
[01:27:46] workflow. So that's going to be what the trigger is here. And we are going to be
[01:27:49] trigger is here. And we are going to be able to define using fields below. Let's
[01:27:51] able to define using fields below. Let's just add in one here that is a lead lead
[01:27:54] just add in one here that is a lead lead name. Um, for now we can just leave that
[01:27:57] name. Um, for now we can just leave that there. But that's all that we need to
[01:27:58] there. But that's all that we need to set up. We need to go back over to the
[01:28:00] set up. We need to go back over to the other one. Just needed to set this part
[01:28:01] other one. Just needed to set this part up. Let's rename this qualified lead
[01:28:04] up. Let's rename this qualified lead lead classifier and
[01:28:07] lead classifier and notifier. So we can save that there. And
[01:28:09] notifier. So we can save that there. And we have a bit more work to do on this
[01:28:10] we have a bit more work to do on this other one. If we go back to this, we can
[01:28:13] other one. If we go back to this, we can rename this here. So let's call this our
[01:28:16] rename this here. So let's call this our lead
[01:28:18] lead qualification agent.
[01:28:21] qualification agent. And so now we have our other workflow
[01:28:23] And so now we have our other workflow set up. We can come here. We can call
[01:28:24] set up. We can come here. We can call another workflow with the tool and we
[01:28:27] another workflow with the tool and we can call it lead is qualified. And so
[01:28:30] can call it lead is qualified. And so now is when we get to tie back into what
[01:28:31] now is when we get to tie back into what we learned in the foundation section
[01:28:32] we learned in the foundation section because we are now writing descriptions
[01:28:34] because we are now writing descriptions for our tools. Remember how we had
[01:28:35] for our tools. Remember how we had schemas and scheas are basically
[01:28:38] schemas and scheas are basically written instructions or instruction
[01:28:40] written instructions or instruction manuals on how to use tools and how to
[01:28:42] manuals on how to use tools and how to use the APIs that wrap around them. Um
[01:28:44] use the APIs that wrap around them. Um this description is going to be
[01:28:45] this description is going to be basically those descriptions that you
[01:28:46] basically those descriptions that you put in the schema. But NAT is going to
[01:28:48] put in the schema. But NAT is going to be basically constructing it for us in
[01:28:50] be basically constructing it for us in the back end. And we just get to put in
[01:28:52] the back end. And we just get to put in here, okay, what's the name of this
[01:28:53] here, okay, what's the name of this tool? It's going to be called lead is
[01:28:55] tool? It's going to be called lead is qualified. It's giving us a nice example
[01:28:56] qualified. It's giving us a nice example of how we can write a description for
[01:28:58] of how we can write a description for the tool. So call this tool to get a
[01:28:59] the tool. So call this tool to get a random color. The input should be a
[01:29:00] random color. The input should be a string with a comma separated names of
[01:29:02] string with a comma separated names of colors to execute. So in our case, we
[01:29:03] colors to execute. So in our case, we can say call this tool when the lead is
[01:29:05] can say call this tool when the lead is qualified according to our criteria. The
[01:29:07] qualified according to our criteria. The inputs should be lead name, lead email,
[01:29:13] inputs should be lead name, lead email, company, company summary, and request in
[01:29:18] company, company summary, and request in info. We're basically telling that AI
[01:29:20] info. We're basically telling that AI model or the brain what this tool can
[01:29:22] model or the brain what this tool can do. So when we send it some kind of
[01:29:23] do. So when we send it some kind of input, it then it looks over our tools.
[01:29:25] input, it then it looks over our tools. It looks at the Gmail description and it
[01:29:27] It looks at the Gmail description and it looks at this uh workflow tool
[01:29:29] looks at this uh workflow tool description and goes, "Oh, well, I have
[01:29:30] description and goes, "Oh, well, I have a tool that does this and a tool that
[01:29:31] a tool that does this and a tool that does this. What have they just sent me?
[01:29:33] does this. What have they just sent me? Okay, now I think I know what I need to
[01:29:34] Okay, now I think I know what I need to do from here." So this is the rough gist
[01:29:36] do from here." So this is the rough gist of what we want to do as a description
[01:29:37] of what we want to do as a description for this tool. I'm actually going to
[01:29:38] for this tool. I'm actually going to beef it up with a bit of a a bigger one
[01:29:40] beef it up with a bit of a a bigger one here. Um if the lead is qualified to
[01:29:42] here. Um if the lead is qualified to work with big boy recruits, eg they are
[01:29:44] work with big boy recruits, eg they are software based business like SAS or
[01:29:45] software based business like SAS or development agencies and trigger this
[01:29:47] development agencies and trigger this tool and send the lead data in the
[01:29:48] tool and send the lead data in the following format. It's just dummy data.
[01:29:50] following format. It's just dummy data. So name a name email um an email message
[01:29:54] So name a name email um an email message I want new div qualified true company
[01:29:57] I want new div qualified true company information and company information
[01:29:59] information and company information which is a summary of the relevance tool
[01:30:01] which is a summary of the relevance tool to do the company research that we have.
[01:30:03] to do the company research that we have. So, might seem a bit crazy at the
[01:30:04] So, might seem a bit crazy at the moment, but stick with me because it
[01:30:06] moment, but stick with me because it will make sense in a second. We're
[01:30:07] will make sense in a second. We're basically just told it when it's going
[01:30:08] basically just told it when it's going to trigger this tool and the format to
[01:30:09] to trigger this tool and the format to send the data in. And then for the
[01:30:11] send the data in. And then for the workflow, we get to choose here the one
[01:30:13] workflow, we get to choose here the one that we just set up, which is our
[01:30:15] that we just set up, which is our qualified lead classifier and notifier,
[01:30:17] qualified lead classifier and notifier, at least in my case. And then we see the
[01:30:18] at least in my case. And then we see the workflow inputs that we've just set up.
[01:30:20] workflow inputs that we've just set up. So, if we go back over to our other
[01:30:22] So, if we go back over to our other automation, so when we open this up and
[01:30:24] automation, so when we open this up and define our inputs here, you can see over
[01:30:26] define our inputs here, you can see over here we are getting just one of them
[01:30:28] here we are getting just one of them that we've put in as an example so far.
[01:30:30] that we've put in as an example so far. So now we need to set up all these
[01:30:32] So now we need to set up all these inputs correctly. And we have the name
[01:30:34] inputs correctly. And we have the name that we want. So we've got the name and
[01:30:35] that we want. So we've got the name and we want the email. So we can add another
[01:30:40] email. What else do we need? We need the
[01:30:47] message.
[01:30:49] message. Um, honestly don't think we need this
[01:30:51] Um, honestly don't think we need this qualified one here. And then we have the
[01:30:54] qualified one here. And then we have the company information.
[01:31:02] So, if we just test this, head back over
[01:31:05] So, if we just test this, head back over here, and
[01:31:09] we refresh this
[01:31:13] we refresh this list. Oh, back out. Save
[01:31:16] list. Oh, back out. Save it. And this pops up. It says that these
[01:31:19] it. And this pops up. It says that these inputs are outdated. So, there we go. We
[01:31:21] inputs are outdated. So, there we go. We have lead name, email, message, etc. And
[01:31:23] have lead name, email, message, etc. And then we can actually automatically fill
[01:31:24] then we can actually automatically fill out a lot of these inputs. Maybe I will
[01:31:26] out a lot of these inputs. Maybe I will put this back in here just to show you
[01:31:27] put this back in here just to show you guys how these work. So if we go um
[01:31:35] qualified. Um and then we just call it
[01:31:37] qualified. Um and then we just call it uh true
[01:31:39] uh true here. I just put it as a string.
[01:31:46] And we go back here and we add in one
[01:31:49] And we go back here and we add in one more which is a
[01:31:52] more which is a qual
[01:31:55] qualified which is also a string. And so
[01:31:58] qualified which is also a string. And so we have this qualified field here as
[01:31:59] we have this qualified field here as well. If we go back um I'll just test
[01:32:02] well. If we go back um I'll just test this. Save it
[01:32:05] this. Save it again. Come back over and update
[01:32:07] again. Come back over and update this. I think we can actually make it
[01:32:09] this. I think we can actually make it even cooler. So let's go. Um it changes
[01:32:12] even cooler. So let's go. Um it changes from a string to a boolean. So that's
[01:32:13] from a string to a boolean. So that's either true or false. Um, and if we test
[01:32:16] either true or false. Um, and if we test this, save it again, and we change this
[01:32:20] this, save it again, and we change this to take away these little things. Sorry,
[01:32:22] to take away these little things. Sorry, pisses me off if I don't have this set
[01:32:24] pisses me off if I don't have this set up right. Um, and then we update this,
[01:32:27] up right. Um, and then we update this, you'll see this turns into a switch. So,
[01:32:28] you'll see this turns into a switch. So, that's a true or false, right? In order
[01:32:29] that's a true or false, right? In order to trigger this tool, it should be
[01:32:30] to trigger this tool, it should be qualified by default. So, it's a little
[01:32:32] qualified by default. So, it's a little bit redundant, but it's still cool to
[01:32:34] bit redundant, but it's still cool to show you how we can get AI to fill out
[01:32:35] show you how we can get AI to fill out these fields. Um, in a lot of cases, we
[01:32:37] these fields. Um, in a lot of cases, we don't, but for this qualified run, we
[01:32:39] don't, but for this qualified run, we can. So, we can set this as an AI
[01:32:41] can. So, we can set this as an AI generated field. We can say if the elite
[01:32:43] generated field. We can say if the elite is qualified based on our
[01:32:47] is qualified based on our criteria this set to
[01:32:50] criteria this set to true. And then for the rest of
[01:32:53] true. And then for the rest of them we can just fill this out
[01:33:04] quickly. Give this a
[01:33:07] quickly. Give this a second. Open this back
[01:33:10] second. Open this back up. And we can fill out some of these
[01:33:12] up. And we can fill out some of these fields. So we can go lead name that we
[01:33:14] fields. So we can go lead name that we want to pass through to the other
[01:33:15] want to pass through to the other automation is going to be that. So we
[01:33:17] automation is going to be that. So we can fill a lot of these in email
[01:33:21] can fill a lot of these in email um message and the company information
[01:33:26] um message and the company information um we can get from um this technically
[01:33:28] um we can get from um this technically but um maybe we could do a cool AI
[01:33:30] but um maybe we could do a cool AI generated one here which is um a short
[01:33:34] generated one here which is um a short summary of the
[01:33:37] summary of the company and the industry that they are
[01:33:40] company and the industry that they are in.
[01:33:42] in. company's details. So, this is basically
[01:33:43] company's details. So, this is basically telling the AI model of our agent how to
[01:33:46] telling the AI model of our agent how to fill this field out, which is one of the
[01:33:47] fill this field out, which is one of the reasons that AI agents are so powerful.
[01:33:49] reasons that AI agents are so powerful. So, that's all set up. Now, we've got
[01:33:51] So, that's all set up. Now, we've got all of our tools set up. The last step
[01:33:52] all of our tools set up. The last step is just to set up a prompt for our
[01:33:54] is just to set up a prompt for our agent. And I am going to cheat a little
[01:33:56] agent. And I am going to cheat a little bit here and just throw one in that I've
[01:33:57] bit here and just throw one in that I've done before to save us a bit of time
[01:33:59] done before to save us a bit of time here. So, we want to set the prompt
[01:34:03] here. So, we want to set the prompt here. We can paste in this information
[01:34:05] here. We can paste in this information here. And this is basically just telling
[01:34:07] here. And this is basically just telling the agent who it is and what it's
[01:34:08] the agent who it is and what it's supposed to do. You're a lead
[01:34:09] supposed to do. You're a lead qualification agent. Your job is to
[01:34:11] qualification agent. Your job is to analyze the form submission and company
[01:34:12] analyze the form submission and company research provided and then decide
[01:34:14] research provided and then decide whether they are qualified to work with
[01:34:15] whether they are qualified to work with big boy recruits. Ra we specialize in
[01:34:18] big boy recruits. Ra we specialize in XYZ. Um we are specialist in capturing
[01:34:20] XYZ. Um we are specialist in capturing talent for ra. We only work with
[01:34:22] talent for ra. We only work with softwarebased businesses, EG SAS
[01:34:24] softwarebased businesses, EG SAS companies or development agencies. These
[01:34:25] companies or development agencies. These companies are willing to pay much more
[01:34:27] companies are willing to pay much more developers than your average marketing
[01:34:28] developers than your average marketing company or local business. Therefore, we
[01:34:30] company or local business. Therefore, we only work with them. Your job is to
[01:34:31] only work with them. Your job is to determine if the lead you are provided
[01:34:33] determine if the lead you are provided with is a good fit for big boy recruits.
[01:34:34] with is a good fit for big boy recruits. And if so, call the lead is qualified
[01:34:36] And if so, call the lead is qualified tool and send the elite information to
[01:34:38] tool and send the elite information to it. If lead is not qualified, then you
[01:34:39] it. If lead is not qualified, then you must trigger the Gmail send email tool
[01:34:41] must trigger the Gmail send email tool for us to respond to them letting know
[01:34:43] for us to respond to them letting know letting them know we are unable to work
[01:34:44] letting them know we are unable to work with them. And then we have a response
[01:34:45] with them. And then we have a response format here which we can probably just
[01:34:47] format here which we can probably just delete. And then we can add in here is
[01:34:49] delete. And then we can add in here is the lead
[01:34:50] the lead to information for you to
[01:34:54] to information for you to analyze. Let's pop this out to make it a
[01:34:56] analyze. Let's pop this out to make it a bit easier.
[01:35:00] We can add in um just go name um company
[01:35:07] We can add in um just go name um company URL
[01:35:09] URL in go message
[01:35:13] request and of course we go a
[01:35:17] company and we take it. So that's from
[01:35:20] company and we take it. So that's from the relevant step for the research that
[01:35:22] the relevant step for the research that we did to scrape using our firecrawl
[01:35:24] we did to scrape using our firecrawl tool. And then we provided all the
[01:35:25] tool. And then we provided all the information to this agent and it's going
[01:35:27] information to this agent and it's going to be injected with all of these values
[01:35:29] to be injected with all of these values on each form submission and then it's
[01:35:31] on each form submission and then it's going to make a call on what tool it
[01:35:32] going to make a call on what tool it needs to use. So we're pretty much
[01:35:35] needs to use. So we're pretty much there. We can even give it a run here
[01:35:37] there. We can even give it a run here and try to test the step and see which
[01:35:39] and try to test the step and see which tool it's going to try to
[01:35:44] choose. If we go back we can see okay
[01:35:46] choose. If we go back we can see okay look it's used the chat model as the
[01:35:48] look it's used the chat model as the brain and it's triggered the NA10
[01:35:51] brain and it's triggered the NA10 workflow as expected. You can see here
[01:35:52] workflow as expected. You can see here that it's sent off information to our
[01:35:54] that it's sent off information to our other workflow. It sent the lead name,
[01:35:56] other workflow. It sent the lead name, the email, the message, and the company
[01:35:59] the email, the message, and the company information, and it set it as qualified
[01:36:00] information, and it set it as qualified as well. So, all of these fields have
[01:36:02] as well. So, all of these fields have been filled out. We've got a nice AI
[01:36:03] been filled out. We've got a nice AI generated summary here from the model
[01:36:05] generated summary here from the model and brain. And we have the qualified set
[01:36:07] and brain. And we have the qualified set to true. And so, the final step now for
[01:36:09] to true. And so, the final step now for us is to head back over to our other
[01:36:12] us is to head back over to our other automation and just finish it
[01:36:14] automation and just finish it off. Oh, we need to save that. I will
[01:36:17] off. Oh, we need to save that. I will just run that again for you so you can
[01:36:19] just run that again for you so you can see it in slow motion. It's using the
[01:36:20] see it in slow motion. It's using the LLM as the brain and the tools agent and
[01:36:22] LLM as the brain and the tools agent and it's deciding whether it's qualified or
[01:36:24] it's deciding whether it's qualified or not. And if it is qualified, then it
[01:36:26] not. And if it is qualified, then it will send it to this workflow. Bam,
[01:36:28] will send it to this workflow. Bam, we've sent it. And there you go. If we
[01:36:31] we've sent it. And there you go. If we head back over to um let's save
[01:36:35] this. Head back over to our qualified
[01:36:37] this. Head back over to our qualified lead classifier notifier. Now, we can
[01:36:40] lead classifier notifier. Now, we can add on a quick few steps here. I'm just
[01:36:41] add on a quick few steps here. I'm just sort of going to rip through this. Um
[01:36:43] sort of going to rip through this. Um it's not super important. Um but it just
[01:36:45] it's not super important. Um but it just shows you a little bit more
[01:36:46] shows you a little bit more functionality of what you can build in
[01:36:47] functionality of what you can build in on N10. So, we're going to add in a
[01:36:49] on N10. So, we're going to add in a messenger model step here, and we're
[01:36:51] messenger model step here, and we're going to choose uh 40
[01:36:55] mini. And what I want this to do is to
[01:36:57] mini. And what I want this to do is to take in that information that we sent to
[01:36:58] take in that information that we sent to the workflow about the company research,
[01:37:00] the workflow about the company research, etc. So, we know this is a qualified
[01:37:02] etc. So, we know this is a qualified lead now, but we just want to split it
[01:37:03] lead now, but we just want to split it between either our SAS team or our
[01:37:05] between either our SAS team or our development agency sales team. So,
[01:37:07] development agency sales team. So, they're specialized in dealing with
[01:37:08] they're specialized in dealing with different cases. So, I'm going to cheat
[01:37:09] different cases. So, I'm going to cheat and just throw in a prompt here, which
[01:37:10] and just throw in a prompt here, which you guys will be able to get access to.
[01:37:13] you guys will be able to get access to. Um, which is basically saying we have a
[01:37:15] Um, which is basically saying we have a new inbound lead. Um, change this to an
[01:37:16] new inbound lead. Um, change this to an expression. Sorry. Um, we have a new
[01:37:19] expression. Sorry. Um, we have a new inbound lead that we need you to
[01:37:20] inbound lead that we need you to classify into either SAS or development
[01:37:22] classify into either SAS or development agency. Here's the lead information. Um,
[01:37:24] agency. Here's the lead information. Um, we need to go back step and test
[01:37:27] we need to go back step and test this. There we go. We should have some
[01:37:30] this. There we go. We should have some information. Um, and now we can put
[01:37:33] information. Um, and now we can put these in. So, you see how there was
[01:37:34] these in. So, you see how there was nothing here before I went back and
[01:37:35] nothing here before I went back and tested the trigger so that it gives us
[01:37:36] tested the trigger so that it gives us some null values here that we can fill
[01:37:38] some null values here that we can fill out. Here's lead information. Um lead
[01:37:41] out. Here's lead information. Um lead name uh message
[01:37:45] name uh message um
[01:37:46] um name
[01:37:47] name request company
[01:37:51] request company information if the company is a SAS
[01:37:53] information if the company is a SAS output SAS if the lead has development
[01:37:56] output SAS if the lead has development agency upput agency. So we're looking
[01:37:57] agency upput agency. So we're looking for just agency or SAS as the outputs
[01:38:00] for just agency or SAS as the outputs here. Um simplify the output. Yep,
[01:38:04] here. Um simplify the output. Yep, that's all good. So we can no point in
[01:38:06] that's all good. So we can no point in us testing that step there because all
[01:38:07] us testing that step there because all the values are null. Um but the next
[01:38:10] the values are null. Um but the next step is a basic
[01:38:12] step is a basic router flow
[01:38:15] router flow if so this is a basic conditional
[01:38:17] if so this is a basic conditional routing. So we have the conditions we
[01:38:19] routing. So we have the conditions we can go expression here. So we can go
[01:38:23] can go expression here. So we can go um the content here. So this is the
[01:38:24] um the content here. So this is the output from the open AI step. If the
[01:38:27] output from the open AI step. If the content which is the response from the
[01:38:29] content which is the response from the LLM step the classifier it's either
[01:38:30] LLM step the classifier it's either going to be agency or it's going to be
[01:38:32] going to be agency or it's going to be SAS. So if it let's just to to make it a
[01:38:34] SAS. So if it let's just to to make it a bit more flexible. If we go string, if
[01:38:36] bit more flexible. If we go string, if it contains
[01:38:40] agency, great. So, if it contains agency
[01:38:42] agency, great. So, if it contains agency on the true side, we want to go
[01:38:45] on the true side, we want to go Gmail and we want to send a message. Um,
[01:38:50] Gmail and we want to send a message. Um, and then if it is false, we want to do
[01:38:54] and then if it is false, we want to do basically the same thing. Now, I've got
[01:38:55] basically the same thing. Now, I've got a preset email just to help us out here.
[01:39:09] Um, okay. So, here we're not getting
[01:39:11] Um, okay. So, here we're not getting much data on the input side here and we
[01:39:13] much data on the input side here and we can't seem to simulate it because it's
[01:39:14] can't seem to simulate it because it's of course triggered by another workflow.
[01:39:16] of course triggered by another workflow. What we can do is just save it here. go
[01:39:18] What we can do is just save it here. go into
[01:39:19] into executions. And if we go back to our
[01:39:21] executions. And if we go back to our other workflow, the
[01:39:27] agent, and we can go to the form
[01:39:29] agent, and we can go to the form submissions
[01:39:31] submissions one. If we go to executions, and we just
[01:39:34] one. If we go to executions, and we just run one of these that we just did
[01:39:36] run one of these that we just did before, copy to
[01:39:38] before, copy to editor. And we just run this
[01:39:44] again. This is basically just going to
[01:39:46] again. This is basically just going to trigger this again. and so that we get a
[01:39:48] trigger this again. and so that we get a fresh execution and we can sort of pull
[01:39:49] fresh execution and we can sort of pull that data back into the workflow. Oh,
[01:39:52] that data back into the workflow. Oh, we're having issues
[01:40:02] now. It's cuz I need to delete this.
[01:40:10] So if
[01:40:15] we stop that and we just run it
[01:40:23] again. Boom. Triggered it. And that's
[01:40:26] again. Boom. Triggered it. And that's all done. Now if we go back to this and
[01:40:28] all done. Now if we go back to this and we go to executions, go to the most
[01:40:30] we go to executions, go to the most recent one that succeeded. It's going to
[01:40:32] recent one that succeeded. It's going to load in. Oh, hang on. This one's
[01:40:35] load in. Oh, hang on. This one's probably it.
[01:40:41] Oh no, that's not
[01:40:47] it. Okay, so this one here, if we click
[01:40:51] it. Okay, so this one here, if we click this, yep, we've got all the data in
[01:40:53] this, yep, we've got all the data in here. So, what we can do is copy this
[01:40:55] here. So, what we can do is copy this into the editor and then we've got the
[01:40:57] into the editor and then we've got the data that we need that's already loaded
[01:40:58] data that we need that's already loaded in so that we have some values to put
[01:41:00] in so that we have some values to put into our Gmail steps Gmail. So, that's a
[01:41:02] into our Gmail steps Gmail. So, that's a handy little trick to to know how to do.
[01:41:05] handy little trick to to know how to do. And now we have all of this information.
[01:41:07] And now we have all of this information. So, that's what that's what I was trying
[01:41:08] So, that's what that's what I was trying to get. Um, the same setup and we're
[01:41:10] to get. Um, the same setup and we're going to send this to I'm just going to
[01:41:12] going to send this to I'm just going to use an example here and call this um
[01:41:15] use an example here and call this um it's the same email. You wouldn't pull
[01:41:17] it's the same email. You wouldn't pull this in necessarily. I'm just using this
[01:41:18] this in necessarily. I'm just using this as something that I can show you
[01:41:20] as something that I can show you at show. Say new agency lead. Let's do a
[01:41:24] at show. Say new agency lead. Let's do a text. We say um new agency lead man. Go
[01:41:29] text. We say um new agency lead man. Go get
[01:41:29] get him. Um turn into an
[01:41:32] him. Um turn into an expression. And then we say we can just
[01:41:35] expression. And then we say we can just throw this company data in there. It's
[01:41:37] throw this company data in there. It's going to be messy. You can play around
[01:41:39] going to be messy. You can play around with this more when it comes to
[01:41:40] with this more when it comes to formatting, but just to show you the
[01:41:41] formatting, but just to show you the functionality. If we go uh test a step
[01:41:44] functionality. If we go uh test a step here, that's going to sent an email to
[01:41:46] here, that's going to sent an email to this. This is like my agency sales reps
[01:41:49] this. This is like my agency sales reps uh email. Of
[01:41:51] uh email. Of course, um let's rename
[01:42:00] this. Can duplicate this. Right click,
[01:42:04] this. Can duplicate this. Right click, duplicate, bring it
[01:42:06] duplicate, bring it here.
[01:42:08] here. Oh, connect this up. And we change this.
[01:42:12] Oh, connect this up. And we change this. You change this to your like SAS guy.
[01:42:14] You change this to your like SAS guy. You change it to a different different
[01:42:15] You change it to a different different email. Um, of course, and then you can
[01:42:18] email. Um, of course, and then you can say new SAS
[01:42:22] say new SAS lead. Right. So now we have done all of
[01:42:24] lead. Right. So now we have done all of that basically all built out. The data
[01:42:27] that basically all built out. The data is going to come in from the agent. It's
[01:42:28] is going to come in from the agent. It's going to send in the company summary.
[01:42:30] going to send in the company summary. This is going to classify it into being
[01:42:32] This is going to classify it into being a uh agency lead or a SAS lead because
[01:42:34] a uh agency lead or a SAS lead because those are the only two types of
[01:42:35] those are the only two types of businesses that we work with. So all of
[01:42:37] businesses that we work with. So all of them will be qualified when they come
[01:42:38] them will be qualified when they come through here. And then it just sends an
[01:42:40] through here. And then it just sends an email to our uh agency sales rep or our
[01:42:43] email to our uh agency sales rep or our uh SAS oh rename this to our SAS sales
[01:42:46] uh SAS oh rename this to our SAS sales rep, new SAS lead for them to continue
[01:42:50] rep, new SAS lead for them to continue and do the next steps and follow up
[01:42:54] with. Right. So to test this we can turn
[01:42:56] with. Right. So to test this we can turn this on to active and you can see that
[01:42:58] this on to active and you can see that you can now make calls from your
[01:42:59] you can now make calls from your production form URL. Um we can go okay.
[01:43:03] production form URL. Um we can go okay. If we double click on this we can open
[01:43:05] If we double click on this we can open this up. We can click on production URL.
[01:43:07] this up. We can click on production URL. Copy this and open this up in a new tab.
[01:43:11] Copy this and open this up in a new tab. And now we can give it a
[01:43:16] spin. So of course my agency Morning
[01:43:18] spin. So of course my agency Morning Side AI does development services. So
[01:43:20] Side AI does development services. So this should be qualified and it should
[01:43:21] this should be qualified and it should also route it to the agency email. So if
[01:43:24] also route it to the agency email. So if I now go
[01:43:26] I now go submit, we go back into NADN, we go into
[01:43:29] submit, we go back into NADN, we go into executions, we can see this one is
[01:43:32] executions, we can see this one is running. If we go to
[01:43:35] running. If we go to Gmail and I pull up my spare
[01:43:41] inbox and there we go. We see it has
[01:43:43] inbox and there we go. We see it has succeeded. And then if we go
[01:43:47] succeeded. And then if we go to and then if we go to our lead
[01:43:49] to and then if we go to our lead qualifier and notifier and we go to
[01:43:51] qualifier and notifier and we go to executions, we will also see that we
[01:43:53] executions, we will also see that we have a new one that has succeeded here
[01:43:55] have a new one that has succeeded here which was just uh a few seconds ago and
[01:43:58] which was just uh a few seconds ago and that's gone through. It is um outputed
[01:44:01] that's gone through. It is um outputed it as agency which is the the
[01:44:03] it as agency which is the the classification that we wanted. It has
[01:44:05] classification that we wanted. It has gone through and has sent a new email.
[01:44:06] gone through and has sent a new email. And if we go to here we have new agency
[01:44:08] And if we go to here we have new agency lead there. There we go. All the
[01:44:10] lead there. There we go. All the information. So that's working number
[01:44:11] information. So that's working number one. Now we can go back to our form and
[01:44:13] one. Now we can go back to our form and we can try it again but this time with
[01:44:14] we can try it again but this time with let's say an unqualified business. Let's
[01:44:16] let's say an unqualified business. Let's go. What is your name? Ray Croc Ray
[01:44:21] go. What is your name? Ray Croc Ray McDonald.com. Um
[01:44:26] McTum I need more guys more people
[01:44:30] McTum I need more guys more people flipping damn
[01:44:33] flipping damn burgers. So essentially Ray here has
[01:44:35] burgers. So essentially Ray here has come to our recruitment agency and
[01:44:37] come to our recruitment agency and they're asking, "Hey, I need people to
[01:44:39] they're asking, "Hey, I need people to do flip patties for me in my fast food
[01:44:41] do flip patties for me in my fast food restaurant." Um, and because Big Boy
[01:44:43] restaurant." Um, and because Big Boy Recruits in Dallas, which is a
[01:44:44] Recruits in Dallas, which is a hypothetical company, of course, um,
[01:44:47] hypothetical company, of course, um, doesn't do that. It's going to qualify
[01:44:49] doesn't do that. It's going to qualify them or it's going to disqualify them
[01:44:50] them or it's going to disqualify them and then send an email to our good
[01:44:52] and then send an email to our good buddy. Oh
[01:44:54] buddy. Oh no, some poor dude at McDonald's is
[01:44:56] no, some poor dude at McDonald's is going to get an email now. Um, because
[01:44:58] going to get an email now. Um, because send an email. Um, but it's going to be
[01:45:00] send an email. Um, but it's going to be running and of course it's going to be
[01:45:02] running and of course it's going to be sending. if they're unqualified, it will
[01:45:04] sending. if they're unqualified, it will send an email to them and say, "Hey,
[01:45:05] send an email to them and say, "Hey, sorry you're not a good fit for us. Let
[01:45:07] sorry you're not a good fit for us. Let us know if we can help or we can connect
[01:45:08] us know if we can help or we can connect you to our
[01:45:11] partners." And while that is running, I
[01:45:13] partners." And while that is running, I would just put together the final one
[01:45:14] would just put together the final one here to test the functionality, which is
[01:45:16] here to test the functionality, which is if we go Liam
[01:45:18] if we go Liam admin.com, and we set up my SAS
[01:45:21] admin.com, and we set up my SAS https, my SAS agent, if you haven't
[01:45:24] https, my SAS agent, if you haven't already used it, we're going to show you
[01:45:25] already used it, we're going to show you how to use it in the last tutorial of
[01:45:26] how to use it in the last tutorial of this video. So, you guys will get to see
[01:45:27] this video. So, you guys will get to see that. Um, which is my own no code AI
[01:45:30] that. Um, which is my own no code AI agent building platform. And what can we
[01:45:32] agent building platform. And what can we help you with agents? Um, so this should
[01:45:34] help you with agents? Um, so this should be a SAS one and it's going to qualify
[01:45:36] be a SAS one and it's going to qualify as SAS. Um, we
[01:45:41] have the McDonald's one has succeeded
[01:45:45] have the McDonald's one has succeeded here. And you see, yep, as expected, we
[01:45:47] here. And you see, yep, as expected, we were not qualified. The McDonald's
[01:45:49] were not qualified. The McDonald's person was not qualified for our offer.
[01:45:51] person was not qualified for our offer. So, it looked at the qualification
[01:45:52] So, it looked at the qualification criteria we provided in here, said,
[01:45:54] criteria we provided in here, said, "Hey, no, that's not a good fit." So,
[01:45:55] "Hey, no, that's not a good fit." So, I'm going to use this tool. And you can
[01:45:57] I'm going to use this tool. And you can see that it sent the email and it said,
[01:46:00] see that it sent the email and it said, "Hey, thanks for your interest. Um, but
[01:46:03] "Hey, thanks for your interest. Um, but we're not a good fit for you." So,
[01:46:04] we're not a good fit for you." So, someone at McDonald's just got an email.
[01:46:06] someone at McDonald's just got an email. Apologize for that, but we didn't
[01:46:07] Apologize for that, but we didn't trigger the other workflow, which is a
[01:46:09] trigger the other workflow, which is a key part. And we're not going to send
[01:46:10] key part. And we're not going to send emails to our sales team saying, "Hey,
[01:46:12] emails to our sales team saying, "Hey, look, new leads." Now, I have sent
[01:46:14] look, new leads." Now, I have sent another one through here which just
[01:46:15] another one through here which just finished
[01:46:17] finished executing. And we can see this. It's
[01:46:19] executing. And we can see this. It's gone through. It's researched um
[01:46:21] gone through. It's researched um agentive. you'll see um Agent is a
[01:46:24] agentive. you'll see um Agent is a leading service delivery platform for AI
[01:46:25] leading service delivery platform for AI agent AI automation agency owners um etc
[01:46:29] agent AI automation agency owners um etc and it's called the tool because we were
[01:46:30] and it's called the tool because we were qualified because we're a SAS business
[01:46:32] qualified because we're a SAS business right and again if we go back to
[01:46:35] right and again if we go back to here and we look at the most recent one
[01:46:38] here and we look at the most recent one which is this oh we have another one
[01:46:43] here then you'll see new SAS lead has
[01:46:46] here then you'll see new SAS lead has been triggered because we are a SAS of
[01:46:48] been triggered because we are a SAS of course um the LLM step here has outputed
[01:46:51] course um the LLM step here has outputed just SAS So that means that it should
[01:46:53] just SAS So that means that it should send an email to the SAS team, which if
[01:46:55] send an email to the SAS team, which if we go to my
[01:46:58] inbox, tada, new SAS lead, right?
[01:47:02] inbox, tada, new SAS lead, right? So I know that may have taken a while,
[01:47:04] So I know that may have taken a while, but uh we got there eventually. And you
[01:47:06] but uh we got there eventually. And you can see that we've built out all of this
[01:47:07] can see that we've built out all of this functionality. We have our AI agent
[01:47:09] functionality. We have our AI agent calling our tools if they are qualified
[01:47:10] calling our tools if they are qualified and triggering this other workflow.
[01:47:12] and triggering this other workflow. Again, you can build so much cool stuff
[01:47:13] Again, you can build so much cool stuff by connecting an agent to multiple
[01:47:15] by connecting an agent to multiple different workflows. We have a little
[01:47:17] different workflows. We have a little relevance AI researcher tool that we're
[01:47:18] relevance AI researcher tool that we're reusing here and we have people getting
[01:47:20] reusing here and we have people getting denied um with an instant email sending
[01:47:22] denied um with an instant email sending them back. So, hope this been a cool one
[01:47:24] them back. So, hope this been a cool one to show you how NATM works. I really,
[01:47:26] to show you how NATM works. I really, really like this agent functionality
[01:47:27] really like this agent functionality that they have. I think you guys are
[01:47:28] that they have. I think you guys are going to be able to build some awesome
[01:47:30] going to be able to build some awesome stuff if you keep going down this rabbit
[01:47:31] stuff if you keep going down this rabbit hole. So, that has been agent build
[01:47:33] hole. So, that has been agent build number two. Stick with me as we jump
[01:47:35] number two. Stick with me as we jump into agent build number three, which is
[01:47:37] into agent build number three, which is a pretty damn cool one, focusing on both
[01:47:39] a pretty damn cool one, focusing on both chat and voice-based agents all in the
[01:47:41] chat and voice-based agents all in the same build. So, let's get the ball
[01:47:43] same build. So, let's get the ball rolling.
[01:47:49] All right, so that is two builds out of
[01:47:50] All right, so that is two builds out of the way. Well done if you made it this
[01:47:51] the way. Well done if you made it this far. We have another big one here. Um,
[01:47:53] far. We have another big one here. Um, this is going to be breaking down how to
[01:47:55] this is going to be breaking down how to use voice flow. Let's take this off
[01:47:57] use voice flow. Let's take this off here. Um, to build an agent that is
[01:47:59] here. Um, to build an agent that is going to be both accessible through a
[01:48:00] going to be both accessible through a website chat, so you can chat to it on a
[01:48:02] website chat, so you can chat to it on a website as a as a chat widget, which
[01:48:04] website as a as a chat widget, which you're probably familiar with, but we're
[01:48:05] you're probably familiar with, but we're going to connect the exact same agent
[01:48:07] going to connect the exact same agent and exact same functionality that you
[01:48:08] and exact same functionality that you get through that chat widget also to a
[01:48:10] get through that chat widget also to a phone number on the website that will be
[01:48:12] phone number on the website that will be able to call and have the same
[01:48:13] able to call and have the same experience. So, this is going to show
[01:48:14] experience. So, this is going to show you how on voice you can build both chat
[01:48:16] you how on voice you can build both chat and voice experiences. Um, and this is a
[01:48:19] and voice experiences. Um, and this is a new feature for them as of the time of
[01:48:20] new feature for them as of the time of filming. And this agent is what we can
[01:48:21] filming. And this agent is what we can classify as an AI customer support and
[01:48:23] classify as an AI customer support and lead generation agent for both website
[01:48:25] lead generation agent for both website and phone. And we're going to build it
[01:48:26] and phone. And we're going to build it on voice flow, of course. And the
[01:48:28] on voice flow, of course. And the purpose of this agent is that it's
[01:48:29] purpose of this agent is that it's designed to be able to answer common
[01:48:30] designed to be able to answer common questions from potential customers via a
[01:48:32] questions from potential customers via a website chatbot and also via a phone
[01:48:33] website chatbot and also via a phone number that can be called. Not only can
[01:48:35] number that can be called. Not only can it answer questions to help them sort of
[01:48:37] it answer questions to help them sort of move them towards a uh a purchase, but
[01:48:39] move them towards a uh a purchase, but it can also generate instant quotes for
[01:48:41] it can also generate instant quotes for interested parties. This is intended to
[01:48:43] interested parties. This is intended to increase the number of leads that they
[01:48:44] increase the number of leads that they get because people who see a contact
[01:48:46] get because people who see a contact form may be like, "Hey, I want to get
[01:48:47] form may be like, "Hey, I want to get instant response. I want to know
[01:48:49] instant response. I want to know instantly how much this is cuz I'm
[01:48:50] instantly how much this is cuz I'm shopping around." Um, and rather than
[01:48:51] shopping around." Um, and rather than just filling in a contact form and
[01:48:53] just filling in a contact form and waiting. Um, having this instant
[01:48:54] waiting. Um, having this instant quotation can give people confirmation
[01:48:56] quotation can give people confirmation on the price. Um, so they're ready to
[01:48:58] on the price. Um, so they're ready to take a step forward and end up getting
[01:48:59] take a step forward and end up getting the sale ultimately. So that instant
[01:49:01] the sale ultimately. So that instant quotation feature is a cool one. Um,
[01:49:02] quotation feature is a cool one. Um, very easy to do with the custom tool on
[01:49:04] very easy to do with the custom tool on relevance that we're going to build. And
[01:49:05] relevance that we're going to build. And finally, this agent is going to be able
[01:49:07] finally, this agent is going to be able to actually capture lead information
[01:49:08] to actually capture lead information from those who have been given a quote.
[01:49:10] from those who have been given a quote. So after they've been given a quote,
[01:49:11] So after they've been given a quote, then we'll move to say, "Hey, give us
[01:49:13] then we'll move to say, "Hey, give us your details and we will follow up. Our
[01:49:15] your details and we will follow up. Our team will follow you up and set an
[01:49:16] team will follow you up and set an appointment for the service." And the
[01:49:17] appointment for the service." And the value here of the system is that
[01:49:18] value here of the system is that customers are going to often want
[01:49:20] customers are going to often want instant answers so that they can make a
[01:49:21] instant answers so that they can make a purchase. So by offering easy ways for
[01:49:23] purchase. So by offering easy ways for them to get this information, we can
[01:49:24] them to get this information, we can increase the chance that they're going
[01:49:25] increase the chance that they're going to purchase from the business. Um,
[01:49:27] to purchase from the business. Um, companies typically have to spend money
[01:49:28] companies typically have to spend money on some kind of customer support or
[01:49:30] on some kind of customer support or sales team in order to get these kind of
[01:49:32] sales team in order to get these kind of answers given to customers when they
[01:49:33] answers given to customers when they need them. But this agent can
[01:49:35] need them. But this agent can essentially be a oneanddone solution um
[01:49:37] essentially be a oneanddone solution um to both help increase the sales of the
[01:49:39] to both help increase the sales of the business by increasing that likelihood
[01:49:40] business by increasing that likelihood of purchasing because they now have more
[01:49:42] of purchasing because they now have more information um while also saving the
[01:49:44] information um while also saving the business money that they would typically
[01:49:45] business money that they would typically spend on some kind of support staff um
[01:49:47] spend on some kind of support staff um say if this chatbot can handle a dozens
[01:49:50] say if this chatbot can handle a dozens and dozens of responses a a week that
[01:49:52] and dozens of responses a a week that would typically have to have gone
[01:49:53] would typically have to have gone through a support person then we're
[01:49:54] through a support person then we're saving the company money and also
[01:49:56] saving the company money and also helping them increase their chance of
[01:49:57] helping them increase their chance of generating more revenue. So um here's a
[01:49:59] generating more revenue. So um here's a rough layout of the design here. We are
[01:50:01] rough layout of the design here. We are going to have a website. I'll give you a
[01:50:02] going to have a website. I'll give you a template for this. It's very easy to set
[01:50:04] template for this. It's very easy to set up and we're just going to throw in a
[01:50:05] up and we're just going to throw in a number um that's going to be connected
[01:50:06] number um that's going to be connected to the voice agent that we build and
[01:50:08] to the voice agent that we build and we're going to be setting up voice flows
[01:50:09] we're going to be setting up voice flows web chat widget as well. And this agent
[01:50:11] web chat widget as well. And this agent is going to have access to a knowledge
[01:50:13] is going to have access to a knowledge base to answer questions um that
[01:50:15] base to answer questions um that prospects may have about the business
[01:50:16] prospects may have about the business and their services etc. Um it's going to
[01:50:18] and their services etc. Um it's going to have a tool that is allowing them to
[01:50:20] have a tool that is allowing them to generate an instant quotation. So it's
[01:50:21] generate an instant quotation. So it's going to take in some information. This
[01:50:23] going to take in some information. This is going to be for a cleaning business
[01:50:24] is going to be for a cleaning business or a hypothetical cleaning business. And
[01:50:25] or a hypothetical cleaning business. And then we're going to be able to generate
[01:50:26] then we're going to be able to generate an instant quote for them based on the
[01:50:28] an instant quote for them based on the property type and the size of the
[01:50:29] property type and the size of the property they need cleaned. and we're
[01:50:31] property they need cleaned. and we're going to be able to capture the lead
[01:50:32] going to be able to capture the lead information afterwards and log it into a
[01:50:34] information afterwards and log it into a CRM. In this case, we'll just use Google
[01:50:35] CRM. In this case, we'll just use Google Sheets, but it's fairly easy to swap
[01:50:37] Sheets, but it's fairly easy to swap that out to whatever CRM you want. So,
[01:50:38] that out to whatever CRM you want. So, it's going to look a bit like this. I've
[01:50:40] it's going to look a bit like this. I've actually added a little bit more. And we
[01:50:41] actually added a little bit more. And we are using another relevance tool in
[01:50:42] are using another relevance tool in here. This is from a different project
[01:50:44] here. This is from a different project from my accelerator, but I'm going to be
[01:50:45] from my accelerator, but I'm going to be pinching that and putting it in here for
[01:50:46] pinching that and putting it in here for you all. And this is the uh tool number
[01:50:49] you all. And this is the uh tool number two here, the generate instant quote.
[01:50:51] two here, the generate instant quote. So, we're going to be slotting that in
[01:50:52] So, we're going to be slotting that in there, taking in some information,
[01:50:53] there, taking in some information, answering questions, etc. The process of
[01:50:55] answering questions, etc. The process of building on Voice Flow is one of my kind
[01:50:56] building on Voice Flow is one of my kind of favorite experiences um in the
[01:50:58] of favorite experiences um in the automation space. I really like the the
[01:50:59] automation space. I really like the the way they've built out their uh their
[01:51:00] way they've built out their uh their flow builder. Um so I'm sure you guys
[01:51:02] flow builder. Um so I'm sure you guys will enjoy building this uh step by step
[01:51:04] will enjoy building this uh step by step with me. And then the general usage
[01:51:05] with me. And then the general usage pattern of the system is that the
[01:51:06] pattern of the system is that the person's going to arrive on the website.
[01:51:08] person's going to arrive on the website. They'll either click to chat with the
[01:51:09] They'll either click to chat with the chatbot and engage with this
[01:51:11] chatbot and engage with this functionality or they'll enter the phone
[01:51:12] functionality or they'll enter the phone number into their phone. And then the
[01:51:13] number into their phone. And then the agent will jump in and respond either
[01:51:15] agent will jump in and respond either through text or through uh voice and
[01:51:17] through text or through uh voice and determine what they're needing help
[01:51:18] determine what they're needing help with, which is this section here. And
[01:51:19] with, which is this section here. And then it's going to be routing using this
[01:51:21] then it's going to be routing using this router section here to the correct tool
[01:51:23] router section here to the correct tool whether they want a question answered or
[01:51:25] whether they want a question answered or they want to get a quote. Um, and then
[01:51:27] they want to get a quote. Um, and then each of these branches will execute on
[01:51:28] each of these branches will execute on that uh, functionality depending on
[01:51:30] that uh, functionality depending on their intent. So, it's going to look a
[01:51:32] their intent. So, it's going to look a bit like this. We'll have a phone number
[01:51:33] bit like this. We'll have a phone number and we'll have a chatbot like this. This
[01:51:34] and we'll have a chatbot like this. This is actually an agenda chatbot from my
[01:51:36] is actually an agenda chatbot from my own software, but we'll be swapping this
[01:51:37] own software, but we'll be swapping this out to a voice flow one in this build.
[01:51:39] out to a voice flow one in this build. So, without further ado, let's jump into
[01:51:40] So, without further ado, let's jump into voice
[01:51:42] voice flow. So, when you click that link on
[01:51:44] flow. So, when you click that link on the Figma, it's going to take you to the
[01:51:45] the Figma, it's going to take you to the signup page. You can sign up there and
[01:51:47] signup page. You can sign up there and then once you're in, you're going to get
[01:51:48] then once you're in, you're going to get a page that looks a bit like this. The
[01:51:49] a page that looks a bit like this. The first thing that we want to do, of
[01:51:50] first thing that we want to do, of course, is to create a new agent up here
[01:51:52] course, is to create a new agent up here on the top right. Let's call this
[01:51:54] on the top right. Let's call this Bonor's cleaning um, website. and phone
[01:51:56] Bonor's cleaning um, website. and phone agent. Um, let's just start with a basic
[01:51:58] agent. Um, let's just start with a basic template here. Import knowledge for this
[01:52:00] template here. Import knowledge for this import knowledge. We can actually just
[01:52:02] import knowledge. We can actually just skip that for now. And then we get into
[01:52:03] skip that for now. And then we get into the flow builder on voice flow. So just
[01:52:06] the flow builder on voice flow. So just a quick orientation if you are new to
[01:52:07] a quick orientation if you are new to the voice flow platform. This is where
[01:52:08] the voice flow platform. This is where we can add in our knowledge which we
[01:52:10] we can add in our knowledge which we will do shortly. The workflows are where
[01:52:12] will do shortly. The workflows are where we access the flow builder. In most
[01:52:13] we access the flow builder. In most simple builds like this, you just going
[01:52:14] simple builds like this, you just going to have one workflow. So you don't need
[01:52:16] to have one workflow. So you don't need to worry too much about that. Now we
[01:52:17] to worry too much about that. Now we have integrations like uh the widget
[01:52:20] have integrations like uh the widget which we're going to be using to deploy
[01:52:21] which we're going to be using to deploy this on a website. We have the phone
[01:52:23] this on a website. We have the phone number integration which we're going to
[01:52:24] number integration which we're going to be doing later as well. Then we have API
[01:52:26] be doing later as well. Then we have API keys etc which you don't need to worry
[01:52:28] keys etc which you don't need to worry too much about right now. We have some
[01:52:29] too much about right now. We have some publishing features here which we'll
[01:52:30] publishing features here which we'll double later. We have access to
[01:52:32] double later. We have access to transcripts. So once we deploy this you
[01:52:34] transcripts. So once we deploy this you can access all of the transcripts either
[01:52:35] can access all of the transcripts either by voice or through chat here and and
[01:52:37] by voice or through chat here and and sort of dig through the answers and and
[01:52:38] sort of dig through the answers and and see how the uh people are interacting
[01:52:40] see how the uh people are interacting with the agent that you've built. Um
[01:52:42] with the agent that you've built. Um something that a lot of people neglect
[01:52:43] something that a lot of people neglect after they've put one of these into
[01:52:44] after they've put one of these into production. And then we have things like
[01:52:46] production. And then we have things like analytics um etc. But obviously we need
[01:52:48] analytics um etc. But obviously we need some data before we see anything useful
[01:52:49] some data before we see anything useful there. And then the settings page is not
[01:52:50] there. And then the settings page is not too much you need to worry about right
[01:52:51] too much you need to worry about right now. Just sort of on a need to know
[01:52:52] now. Just sort of on a need to know basis. The more important stuff, of
[01:52:54] basis. The more important stuff, of course, is up in this first tab here,
[01:52:55] course, is up in this first tab here, which is content. So, we have messages,
[01:52:57] which is content. So, we have messages, we have prompts, we have components.
[01:52:59] we have prompts, we have components. We're going to be working a lot with
[01:53:01] We're going to be working a lot with prompts shortly. So, that's the main one
[01:53:02] prompts shortly. So, that's the main one we need to be worried about. But for
[01:53:04] we need to be worried about. But for now, we can just go into workflows, and
[01:53:05] now, we can just go into workflows, and we open up this first workflow and edit
[01:53:07] we open up this first workflow and edit it. And here we have the template that
[01:53:09] it. And here we have the template that VoiceFlow gives for us. Um, which I'm
[01:53:11] VoiceFlow gives for us. Um, which I'm actually just going to nuke this, and
[01:53:12] actually just going to nuke this, and we'll start fresh. And if you see on the
[01:53:13] we'll start fresh. And if you see on the Figma, we have a design here that we're
[01:53:15] Figma, we have a design here that we're roughly working towards. I'm going to be
[01:53:16] roughly working towards. I'm going to be showing you the sort of step by step.
[01:53:18] showing you the sort of step by step. So, we need a welcome step.
[01:53:21] So, we need a welcome step. So, we're going to start off by going
[01:53:22] So, we're going to start off by going here and dropping. I'll try to zoom in a
[01:53:24] here and dropping. I'll try to zoom in a bit for you guys here. Talk message. So,
[01:53:27] bit for you guys here. Talk message. So, message is how you send a message um via
[01:53:29] message is how you send a message um via the chat. So, start is when maybe you
[01:53:31] the chat. So, start is when maybe you click on the widget, it pops up. And
[01:53:32] click on the widget, it pops up. And this message that we're about to put in
[01:53:34] this message that we're about to put in is the first message the bot is going to
[01:53:35] is the first message the bot is going to send. So, we say um up here, hey, hey,
[01:53:39] send. So, we say um up here, hey, hey, welcome to
[01:53:41] welcome to corners. I'm going to zoom this up for a
[01:53:43] corners. I'm going to zoom this up for a bit for you guys. And right away, we
[01:53:44] bit for you guys. And right away, we have a little tip and trick that I want
[01:53:45] have a little tip and trick that I want to give to you because we are building
[01:53:47] to give to you because we are building this as a chat and voice assistant. We
[01:53:49] this as a chat and voice assistant. We want to over voice. You don't want to
[01:53:51] want to over voice. You don't want to overuse punctuation because it leaves
[01:53:52] overuse punctuation because it leaves these big long pauses when the the voice
[01:53:54] these big long pauses when the the voice agent is going, "Hey, welcome to
[01:53:56] agent is going, "Hey, welcome to Connor's cleaning." So, we wanted to
[01:53:58] Connor's cleaning." So, we wanted to just say, "Hey, welcome to Connor's
[01:54:00] just say, "Hey, welcome to Connor's cleaning." A bit more natural. There's
[01:54:01] cleaning." A bit more natural. There's times where you'll see me on the side of
[01:54:02] times where you'll see me on the side of sloppier punctuation, but that's just to
[01:54:04] sloppier punctuation, but that's just to ensure that when we get to testing it on
[01:54:06] ensure that when we get to testing it on voice, it sounds as natural as possible.
[01:54:08] voice, it sounds as natural as possible. So, hey, welcome to Connor's cleaning.
[01:54:09] So, hey, welcome to Connor's cleaning. And then, of course, we're going to wait
[01:54:10] And then, of course, we're going to wait for them to reply and say something back
[01:54:12] for them to reply and say something back to us. We go to listen and then capture.
[01:54:14] to us. We go to listen and then capture. And this is going to capture the
[01:54:15] And this is going to capture the information. We want to change this from
[01:54:17] information. We want to change this from capturing entities which is like say I'm
[01:54:19] capturing entities which is like say I'm looking for a price or an address. Um
[01:54:21] looking for a price or an address. Um we're just going to go the entire user
[01:54:22] we're just going to go the entire user reply and the reply is going to be saved
[01:54:24] reply and the reply is going to be saved into this variable here. So we actually
[01:54:25] into this variable here. So we actually want to change this to um first user
[01:54:30] want to change this to um first user reply because we're going to need it a
[01:54:32] reply because we're going to need it a little bit later. Um the users first
[01:54:37] little bit later. Um the users first reply. And I like to name these as we
[01:54:39] reply. And I like to name these as we go. So we can call this
[01:54:41] go. So we can call this welcome. Drag this out here. Get a new
[01:54:43] welcome. Drag this out here. Get a new one. And we're going to be doing a uh a
[01:54:45] one. And we're going to be doing a uh a set step here. So, we're going to be
[01:54:47] set step here. So, we're going to be setting some variables. And I'm going to
[01:54:48] setting some variables. And I'm going to add a new variable to set. And we're
[01:54:51] add a new variable to set. And we're going to do it based off a prompt here,
[01:54:52] going to do it based off a prompt here, which is a cool feature in voice they've
[01:54:54] which is a cool feature in voice they've added recently. And we're going to be
[01:54:55] added recently. And we're going to be able to select a prompt that's going to
[01:54:56] able to select a prompt that's going to take this information from this first
[01:54:58] take this information from this first reply and then generate some kind of
[01:54:59] reply and then generate some kind of output from it and set a variable. And
[01:55:01] output from it and set a variable. And the variable we're going to set here is
[01:55:02] the variable we're going to set here is called last response. So, this is
[01:55:04] called last response. So, this is typically what you're going to put as
[01:55:05] typically what you're going to put as the last response from the AI or from
[01:55:06] the last response from the AI or from the agent. Um, last response here. And
[01:55:08] the agent. Um, last response here. And last utterance is typically the most
[01:55:10] last utterance is typically the most recent uh message from the user. So
[01:55:12] recent uh message from the user. So utterance is coming from the user the
[01:55:13] utterance is coming from the user the most recent last utterance and the last
[01:55:15] most recent last utterance and the last response is what the the AI or the agent
[01:55:18] response is what the the AI or the agent or the system has last responded to. So
[01:55:19] or the system has last responded to. So we want to set the last response to
[01:55:22] we want to set the last response to something that is generated through this
[01:55:24] something that is generated through this prompt here. So we can create a new
[01:55:25] prompt here. So we can create a new prompt here and this is basically going
[01:55:27] prompt here and this is basically going to take in the data from the chat and
[01:55:28] to take in the data from the chat and the conversation so far and we'll be
[01:55:30] the conversation so far and we'll be able to generate things off of it. So
[01:55:31] able to generate things off of it. So say we add in here the conversation
[01:55:33] say we add in here the conversation history. That's a good thing to have in
[01:55:35] history. That's a good thing to have in in most cases. And I'm going to be
[01:55:36] in most cases. And I'm going to be dumping in some of the prompts here just
[01:55:37] dumping in some of the prompts here just to save us a bit of time. But basically,
[01:55:39] to save us a bit of time. But basically, we're saying summarize the customer's
[01:55:40] we're saying summarize the customer's question below and ask them to confirm
[01:55:42] question below and ask them to confirm that that's what they meant. And so,
[01:55:43] that that's what they meant. And so, we're not actually going to be
[01:55:44] we're not actually going to be generating the last utterance here.
[01:55:45] generating the last utterance here. We're going to be adding in the last the
[01:55:48] We're going to be adding in the last the first user reply that we got. I mean,
[01:55:50] first user reply that we got. I mean, it's going to be included here in the
[01:55:51] it's going to be included here in the conversation history, but there's no
[01:55:53] conversation history, but there's no harm really in hard coding it or at
[01:55:54] harm really in hard coding it or at least putting the variable in here to
[01:55:56] least putting the variable in here to make sure that it's in there. Um, we're
[01:55:57] make sure that it's in there. Um, we're just saying summarize the customer's
[01:55:59] just saying summarize the customer's question and basically say a
[01:56:00] question and basically say a confirmation statement. So, just to
[01:56:01] confirmation statement. So, just to confirm this is what you're looking to
[01:56:02] confirm this is what you're looking to do. So, you imagine this over the phone.
[01:56:04] do. So, you imagine this over the phone. Hey, um um yeah, I'm not really sure
[01:56:07] Hey, um um yeah, I'm not really sure what I'm supposed to be doing here, but
[01:56:08] what I'm supposed to be doing here, but I was thinking if if you guys were
[01:56:10] I was thinking if if you guys were possibly so all of that information is
[01:56:12] possibly so all of that information is taken in, we can flick back to them and
[01:56:14] taken in, we can flick back to them and say, just to confirm this, this sounds
[01:56:15] say, just to confirm this, this sounds like you're looking for this, yes or no.
[01:56:17] like you're looking for this, yes or no. Um so, ensure your tone is empathetic.
[01:56:18] Um so, ensure your tone is empathetic. Speak directly to the end customer. Keep
[01:56:19] Speak directly to the end customer. Keep your answer brief and two sentences max.
[01:56:22] your answer brief and two sentences max. So, if we go back here and actually we
[01:56:25] So, if we go back here and actually we can name that prompt. So it's um
[01:56:28] can name that prompt. So it's um summarize
[01:56:30] summarize problem and then we need to send the
[01:56:33] problem and then we need to send the response. So this prompt is going to
[01:56:35] response. So this prompt is going to take in the information we provided
[01:56:37] take in the information we provided here. It's going to use this prompt to
[01:56:38] here. It's going to use this prompt to take in um the conversation history so
[01:56:41] take in um the conversation history so far and this information from the user
[01:56:43] far and this information from the user in the first question. It's going to
[01:56:44] in the first question. It's going to generate a a question to ask back and
[01:56:47] generate a a question to ask back and it's going to save it to this variable
[01:56:49] it's going to save it to this variable that we have here. So apply output to
[01:56:51] that we have here. So apply output to variable last response. There is
[01:56:52] variable last response. There is actually an easier way to do AI
[01:56:54] actually an easier way to do AI responses like this, but in our case, we
[01:56:55] responses like this, but in our case, we need to be saving this variable. So,
[01:56:57] need to be saving this variable. So, it'll make sense in a second. But, we
[01:56:58] it'll make sense in a second. But, we can go into here and we can go last
[01:57:01] can go into here and we can go last response. And then it's going to send
[01:57:04] response. And then it's going to send that information back to them. So, let's
[01:57:05] that information back to them. So, let's just do a quick test here. Click start.
[01:57:08] just do a quick test here. Click start. Hey, welcome to Connor's Cleaning. Oh,
[01:57:10] Hey, welcome to Connor's Cleaning. Oh, actually, we need to ask a question.
[01:57:12] actually, we need to ask a question. Hey, welcome to Connor's Cleaning. Um,
[01:57:15] Hey, welcome to Connor's Cleaning. Um, how can I help?
[01:57:23] We'll
[01:57:24] We'll say I need cleaning services for my
[01:57:28] say I need cleaning services for my house. Sounds like you're looking for
[01:57:30] house. Sounds like you're looking for cleaning services for your greenhouse.
[01:57:31] cleaning services for your greenhouse. Is that correct? Want to make sure I
[01:57:33] Is that correct? Want to make sure I understand your specific needs before we
[01:57:34] understand your specific needs before we proceed. So, I obviously spelled house
[01:57:36] proceed. So, I obviously spelled house with G house. So, we thought it was a
[01:57:37] with G house. So, we thought it was a greenhouse, but that's what we want.
[01:57:39] greenhouse, but that's what we want. Some kind of confirmation message just
[01:57:40] Some kind of confirmation message just saying like, hey, look, is this what
[01:57:41] saying like, hey, look, is this what you're actually looking to do before we
[01:57:42] you're actually looking to do before we then go and trigger the different tools
[01:57:44] then go and trigger the different tools that we are equipping our agent with? By
[01:57:45] that we are equipping our agent with? By the way, there is a way of changing
[01:57:47] the way, there is a way of changing between trackpad and mouse. So I am
[01:57:48] between trackpad and mouse. So I am panning around with my mouse here. You
[01:57:50] panning around with my mouse here. You can also do a trackpad method which is a
[01:57:52] can also do a trackpad method which is a lot easier to use if you're if you're
[01:57:53] lot easier to use if you're if you're having trouble using it. Okay. So after
[01:57:54] having trouble using it. Okay. So after that they're obviously going to say yes
[01:57:56] that they're obviously going to say yes or no whether like have I got the
[01:57:57] or no whether like have I got the question or have I summarized what
[01:57:59] question or have I summarized what you're looking for correctly and we can
[01:58:00] you're looking for correctly and we can go to a choice step here and we can set
[01:58:03] go to a choice step here and we can set up some triggers. We can set the intent
[01:58:05] up some triggers. We can set the intent to yes and then we can add another
[01:58:07] to yes and then we can add another trigger and we can set it as no. So this
[01:58:09] trigger and we can set it as no. So this is basically using AI to analyze what
[01:58:12] is basically using AI to analyze what they've said and grouping it around
[01:58:14] they've said and grouping it around these certain things which are called
[01:58:15] these certain things which are called intents. So, what is the intent of them
[01:58:16] intents. So, what is the intent of them of this uh of the response? And in this
[01:58:18] of this uh of the response? And in this case, they have some pre-built ones, but
[01:58:20] case, they have some pre-built ones, but we are going to be building our own
[01:58:21] we are going to be building our own custom intents later. But for now, just
[01:58:23] custom intents later. But for now, just know that if you're looking to sort of
[01:58:25] know that if you're looking to sort of split traffic or split people coming
[01:58:26] split traffic or split people coming through the system, these choice blocks
[01:58:28] through the system, these choice blocks with the default uh intents from voice
[01:58:30] with the default uh intents from voice flow, yes and no, are ready to use out
[01:58:32] flow, yes and no, are ready to use out of the box. And if they don't say yes or
[01:58:33] of the box. And if they don't say yes or no clearly or we can't pick it up, we
[01:58:35] no clearly or we can't pick it up, we can add a no match here. We can say
[01:58:37] can add a no match here. We can say sorry, I didn't get that. Can you say
[01:58:39] sorry, I didn't get that. Can you say yes again? A yes or a no is enough. And
[01:58:43] yes again? A yes or a no is enough. And then we can say to follow a path after
[01:58:45] then we can say to follow a path after these reprompts which we'll call no
[01:58:46] these reprompts which we'll call no match. And then we have this uh no match
[01:58:49] match. And then we have this uh no match path which we'll set up in a second
[01:58:51] path which we'll set up in a second here. I'll just put it as a a filler for
[01:58:53] here. I'll just put it as a a filler for now. Basically if if they don't say yes
[01:58:55] now. Basically if if they don't say yes or no um this is setting up error
[01:58:56] or no um this is setting up error handling. Um, and basically if people
[01:58:59] handling. Um, and basically if people particularly over the phone, um, there's
[01:59:01] particularly over the phone, um, there's so many different ways that the
[01:59:02] so many different ways that the conversation can go and end up and
[01:59:03] conversation can go and end up and you'll want to, while I don't focus on
[01:59:05] you'll want to, while I don't focus on it too much in this build, um, as you're
[01:59:07] it too much in this build, um, as you're building production grade assistants,
[01:59:08] building production grade assistants, you'll need to build a lot more of these
[01:59:10] you'll need to build a lot more of these fallbacks and these reprompt and these
[01:59:12] fallbacks and these reprompt and these no match things to handle edge cases
[01:59:14] no match things to handle edge cases where people use it in a weird way that
[01:59:15] where people use it in a weird way that you don't expect. So, I want to give you
[01:59:17] you don't expect. So, I want to give you a little taste of that in this tutorial,
[01:59:18] a little taste of that in this tutorial, but it is nowhere near representative of
[01:59:20] but it is nowhere near representative of what it takes to actually get something
[01:59:21] what it takes to actually get something into production that you can trust on a
[01:59:23] into production that you can trust on a on a customer's website. Okay, so we've
[01:59:25] on a customer's website. Okay, so we've got this choice block set up to
[01:59:26] got this choice block set up to determine if we have got their
[01:59:27] determine if we have got their summarization of the problem correct.
[01:59:29] summarization of the problem correct. And we can take this up to here and we
[01:59:31] And we can take this up to here and we can set another uh variable. And so this
[01:59:33] can set another uh variable. And so this is really the core part of the
[01:59:35] is really the core part of the application which is determining what
[01:59:36] application which is determining what their intent is, what are they looking
[01:59:37] their intent is, what are they looking to do and which tool are we going to
[01:59:39] to do and which tool are we going to route them to it. So this is a very
[01:59:40] route them to it. So this is a very handy skill to have which I'm going to
[01:59:41] handy skill to have which I'm going to teach you which is how to set up some
[01:59:43] teach you which is how to set up some kind of intent classification system. Um
[01:59:46] kind of intent classification system. Um which is really really essential to
[01:59:47] which is really really essential to building agents on on voice flow and any
[01:59:49] building agents on on voice flow and any kind of agent where the platform itself
[01:59:50] kind of agent where the platform itself isn't automatically handling that for
[01:59:52] isn't automatically handling that for you. So if we go set a new variable and
[01:59:54] you. So if we go set a new variable and we're going to do it through a prompt.
[01:59:56] we're going to do it through a prompt. We're going to set a new variable here
[01:59:58] We're going to set a new variable here called
[02:00:00] called desired action. So basically people
[02:00:02] desired action. So basically people coming through and asking questions can
[02:00:04] coming through and asking questions can be saying hey look I I just have a quick
[02:00:07] be saying hey look I I just have a quick question about where you guys are based
[02:00:08] question about where you guys are based and then we're going to route them to
[02:00:08] and then we're going to route them to the knowledge base. And then someone may
[02:00:10] the knowledge base. And then someone may be saying hey how much does it cost for
[02:00:11] be saying hey how much does it cost for this? And then we're going to route them
[02:00:12] this? And then we're going to route them to the pricing uh the instant quotation
[02:00:15] to the pricing uh the instant quotation um system that we're setting up. So
[02:00:16] um system that we're setting up. So needs to be able to determine what
[02:00:17] needs to be able to determine what they're looking for and we're going to
[02:00:18] they're looking for and we're going to route them depending on that. And that's
[02:00:20] route them depending on that. And that's what this router is going to do. So the
[02:00:22] what this router is going to do. So the action that the prospect wants to take,
[02:00:25] action that the prospect wants to take, the most likely action that the prospect
[02:00:26] the most likely action that the prospect wants to take. Then we need to make a
[02:00:29] wants to take. Then we need to make a new prompt here. We're going to call
[02:00:31] new prompt here. We're going to call this intent
[02:00:33] this intent classifier. Classifies the intent of the
[02:00:37] classifier. Classifies the intent of the uh prospect into asking the knowledge
[02:00:40] uh prospect into asking the knowledge base or generating an instant
[02:00:44] base or generating an instant quote. Add in the conversation history.
[02:00:46] quote. Add in the conversation history. It's always good to have that in there.
[02:00:47] It's always good to have that in there. And I'm going to put in the prompt that
[02:00:48] And I'm going to put in the prompt that I've written previously. And this is a
[02:00:49] I've written previously. And this is a pretty basic one as well, which is just
[02:00:51] pretty basic one as well, which is just saying what does the customer want to
[02:00:52] saying what does the customer want to do, ask a question, get a real-time
[02:00:53] do, ask a question, get a real-time quote, or something else entirely. You
[02:00:55] quote, or something else entirely. You must output a label for this only. Your
[02:00:57] must output a label for this only. Your options are ask a question, get a quote,
[02:01:00] options are ask a question, get a quote, or other. And you guys can just pause it
[02:01:01] or other. And you guys can just pause it and see what I've got in there. But
[02:01:02] and see what I've got in there. But basically, anything asking a question is
[02:01:04] basically, anything asking a question is going to be about the business and the
[02:01:05] going to be about the business and the services. And if there's anything about
[02:01:07] services. And if there's anything about pricing or directly related to getting a
[02:01:09] pricing or directly related to getting a quote and like they're ready to move on
[02:01:10] quote and like they're ready to move on this, then we're going to route them to
[02:01:12] this, then we're going to route them to get a quote. And anything else is going
[02:01:13] get a quote. And anything else is going to go to other. And because in the next
[02:01:14] to go to other. And because in the next step, we are going to be looking out for
[02:01:16] step, we are going to be looking out for either this is the output or this or
[02:01:18] either this is the output or this or this. a really clear statement saying
[02:01:20] this. a really clear statement saying this is all you need to output just this
[02:01:21] this is all you need to output just this and not hey I took a look at the the
[02:01:23] and not hey I took a look at the the conversation history and it seems like
[02:01:25] conversation history and it seems like the user wants to do get a quote we just
[02:01:27] the user wants to do get a quote we just want just get a quote and we can
[02:01:28] want just get a quote and we can explicitly state that with this big caps
[02:01:30] explicitly state that with this big caps lock block here and as with the other
[02:01:31] lock block here and as with the other builds all of these prompts are going to
[02:01:32] builds all of these prompts are going to be available in the resources for you to
[02:01:34] be available in the resources for you to follow along with okay so now we get to
[02:01:37] follow along with okay so now we get to the cool bit which is routing this. So
[02:01:39] the cool bit which is routing this. So if we go condition add this in here and
[02:01:43] if we go condition add this in here and we go add path condition builder and we
[02:01:46] we go add path condition builder and we say if desired action
[02:01:49] say if desired action is
[02:01:51] is ask
[02:01:52] ask a
[02:01:57] question. Oh that's that's all we need
[02:01:59] question. Oh that's that's all we need there. So as you can see that's added
[02:02:01] there. So as you can see that's added one in here. And if we want to add
[02:02:02] one in here. And if we want to add another one in, we go if desired action
[02:02:05] another one in, we go if desired action is um what do we have the label as
[02:02:11] is um what do we have the label as output? What did we what's the exact
[02:02:14] output? What did we what's the exact label that we had in here? So this
[02:02:16] label that we had in here? So this prompt is going to be outputting these
[02:02:18] prompt is going to be outputting these labels. So we need to make sure they
[02:02:19] labels. So we need to make sure they match up. So ask a question. Get a
[02:02:21] match up. So ask a question. Get a quote.
[02:02:25] Yep. Get a quote.
[02:02:29] Yep. Get a quote. and other one is
[02:02:33] other and it's already got an else path
[02:02:36] other and it's already got an else path in there for any error handling as well.
[02:02:37] in there for any error handling as well. So what this now allows us to do is to
[02:02:39] So what this now allows us to do is to build out our different tools. So we can
[02:02:41] build out our different tools. So we can go up to here to ask a question. Just
[02:02:43] go up to here to ask a question. Just throw this in for now so we can get an
[02:02:45] throw this in for now so we can get an idea of what it's going to look
[02:02:47] idea of what it's going to look like.
[02:02:50] Um other this is going to be sort of
[02:02:52] Um other this is going to be sort of error
[02:02:54] error handling. And if it's else, that means
[02:02:56] handling. And if it's else, that means that the LLM step here hasn't outputed
[02:02:59] that the LLM step here hasn't outputed any of the labels that we told it to,
[02:03:00] any of the labels that we told it to, and it's likely thrown in a bunch of
[02:03:02] and it's likely thrown in a bunch of rubbish. Um, so this is sort of an error
[02:03:04] rubbish. Um, so this is sort of an error handling step. Um, should say, "Sorry,
[02:03:07] handling step. Um, should say, "Sorry, something went wrong, at least during
[02:03:09] something went wrong, at least during this prototyping phase. So now what I'd
[02:03:10] this prototyping phase. So now what I'd like to do is make this look a little
[02:03:11] like to do is make this look a little bit prettier. Um, we can go through and
[02:03:13] bit prettier. Um, we can go through and add things in here like this is the uh
[02:03:16] add things in here like this is the uh confirm problem um intent classifier
[02:03:20] confirm problem um intent classifier router." And then we can go here add a
[02:03:23] router." And then we can go here add a note can say tool number number one
[02:03:26] note can say tool number number one answer from knowledge
[02:03:35] base two you guys don't have this so be
[02:03:37] base two you guys don't have this so be easy for you guys to see understand I
[02:03:38] easy for you guys to see understand I know this might look pretty
[02:03:42] confusing and then this other one we
[02:03:44] confusing and then this other one we don't need to worry about too much so to
[02:03:45] don't need to worry about too much so to keep things quick I'm not going to test
[02:03:46] keep things quick I'm not going to test this just yet I'm going to test it once
[02:03:47] this just yet I'm going to test it once we've got that functionality set up on
[02:03:49] we've got that functionality set up on either side at least for this top one
[02:03:51] either side at least for this top one first so now We need to go and set up
[02:03:52] first so now We need to go and set up our knowledge base. And to do this, we
[02:03:53] our knowledge base. And to do this, we can click on the back button here. Go to
[02:03:55] can click on the back button here. Go to our
[02:03:57] our knowledge. And here we have a data
[02:03:59] knowledge. And here we have a data source which we can upload. I'm going to
[02:04:00] source which we can upload. I'm going to upload a file, but you can put in URLs
[02:04:02] upload a file, but you can put in URLs to different websites, etc. I'm going to
[02:04:04] to different websites, etc. I'm going to be uploading a file
[02:04:06] be uploading a file here. And I'm going to upload this
[02:04:08] here. And I'm going to upload this Connor's cleaning FAQ kind of document,
[02:04:10] Connor's cleaning FAQ kind of document, which you guys are going to have access
[02:04:11] which you guys are going to have access to in the resources. Basically, it's
[02:04:13] to in the resources. Basically, it's just about us, location, our services,
[02:04:15] just about us, location, our services, ra um some frequently asked questions,
[02:04:18] ra um some frequently asked questions, etc. So, I've just AI generated this.
[02:04:20] etc. So, I've just AI generated this. Um, and if you're doing any kind of
[02:04:21] Um, and if you're doing any kind of prototype builds, I recommend you do the
[02:04:22] prototype builds, I recommend you do the same just to throw it in there and see
[02:04:24] same just to throw it in there and see if the knowledge base is working as
[02:04:25] if the knowledge base is working as expected. Obviously, you'd swap this out
[02:04:27] expected. Obviously, you'd swap this out with actual customer data or or your
[02:04:28] with actual customer data or or your client's FAQ. I'm just going to throw
[02:04:30] client's FAQ. I'm just going to throw that in there for now. And you guys can
[02:04:32] that in there for now. And you guys can do the
[02:04:34] do the same. And when you're setting up your
[02:04:36] same. And when you're setting up your knowledge base, you can also set up the
[02:04:38] knowledge base, you can also set up the settings for it. So, in this case, it's
[02:04:40] settings for it. So, in this case, it's using by default Claude 3.5 Haiku. And
[02:04:42] using by default Claude 3.5 Haiku. And you can see how many tokens this is
[02:04:43] you can see how many tokens this is going to cost you for Voice Flow's
[02:04:44] going to cost you for Voice Flow's usage. Um, what is Haiku? Haiku seems to
[02:04:47] usage. Um, what is Haiku? Haiku seems to be the cheapest. Oh, you've got GBT40
[02:04:49] be the cheapest. Oh, you've got GBT40 mini. Let me just chuck on GBT40 mini
[02:04:51] mini. Let me just chuck on GBT40 mini here. We want this thing to be pretty
[02:04:53] here. We want this thing to be pretty deterministic. So, I'd say 0.1 is fine.
[02:04:55] deterministic. So, I'd say 0.1 is fine. Max tokens. Um, we can increase that
[02:04:57] Max tokens. Um, we can increase that just in case it needs to give a longer
[02:04:59] just in case it needs to give a longer answer. And chunk limit of of three
[02:05:02] answer. And chunk limit of of three should be enough. So, that's just so
[02:05:03] should be enough. So, that's just so this stuff is a little bit more
[02:05:04] this stuff is a little bit more advanced. That's that vector database as
[02:05:06] advanced. That's that vector database as I was talking about. Basically,
[02:05:07] I was talking about. Basically, knowledge base is going to be sending
[02:05:08] knowledge base is going to be sending the message that we ask it and querying
[02:05:11] the message that we ask it and querying it and getting back chunks of
[02:05:12] it and getting back chunks of information. Because our knowledge base
[02:05:14] information. Because our knowledge base is quite small, we don't really need to
[02:05:15] is quite small, we don't really need to have too many chunks. If you put this
[02:05:16] have too many chunks. If you put this up, you just be getting the whole
[02:05:17] up, you just be getting the whole document back. Anyway, so max tokens,
[02:05:19] document back. Anyway, so max tokens, the number of tokens that it's going to
[02:05:21] the number of tokens that it's going to include in the response. So, we want to
[02:05:22] include in the response. So, we want to increase that to 480 um so that it can
[02:05:24] increase that to 480 um so that it can give a longer response if they need.
[02:05:25] give a longer response if they need. Maybe just tone that down a bit. And
[02:05:27] Maybe just tone that down a bit. And these are of course kind of controls
[02:05:28] these are of course kind of controls that you have on how much you want to
[02:05:30] that you have on how much you want to allow the app to spend. And those
[02:05:31] allow the app to spend. And those settings obviously the main ways that
[02:05:32] settings obviously the main ways that you can control how much um your
[02:05:34] you can control how much um your knowledge base is using and how much
[02:05:35] knowledge base is using and how much your you or your client are ultimately
[02:05:37] your you or your client are ultimately spending on the AI features for the
[02:05:39] spending on the AI features for the knowledge base. So once we've got that
[02:05:40] knowledge base. So once we've got that set up, we can go back to workflows
[02:05:41] set up, we can go back to workflows here, open this up
[02:05:43] here, open this up again, and then to plug in our knowledge
[02:05:45] again, and then to plug in our knowledge base, we can go to the dev section here.
[02:05:47] base, we can go to the dev section here. We can go to KB search, pop this in
[02:05:49] We can go to KB search, pop this in here. I will
[02:05:51] here. I will uh we need to delete that and reconnect
[02:05:55] uh we need to delete that and reconnect this up to the top. And we're going to
[02:05:57] this up to the top. And we're going to delete this as well. And so we can go
[02:06:00] delete this as well. And so we can go into this knowledgebased step here, and
[02:06:02] into this knowledgebased step here, and we can enter the query. So what we're
[02:06:03] we can enter the query. So what we're going to say is we basically want to
[02:06:05] going to say is we basically want to throw the information that we've got
[02:06:06] throw the information that we've got from the user already about what they
[02:06:08] from the user already about what they want which is we have here as the first
[02:06:10] want which is we have here as the first message they gave us which might be a
[02:06:12] message they gave us which might be a bit longwinded. Then we have the summary
[02:06:13] bit longwinded. Then we have the summary that they have confirmed and then we can
[02:06:15] that they have confirmed and then we can put these into the query that's going to
[02:06:17] put these into the query that's going to be asking the knowledge base hey this is
[02:06:19] be asking the knowledge base hey this is what we want information on can you give
[02:06:20] what we want information on can you give us some information back. So we can go
[02:06:24] us some information back. So we can go user first message put a curable in
[02:06:27] user first message put a curable in there. We can go first use reply and
[02:06:29] there. We can go first use reply and then we can also go summarized problem.
[02:06:31] then we can also go summarized problem. Now you can see why if we put last
[02:06:33] Now you can see why if we put last response here, why we have this variable
[02:06:35] response here, why we have this variable saved instead of just sending it
[02:06:36] saved instead of just sending it automatically. So I actually don't like
[02:06:38] automatically. So I actually don't like using last response because that's
[02:06:39] using last response because that's something that you like to update quite
[02:06:40] something that you like to update quite a lot. So I'm actually just going to
[02:06:41] a lot. So I'm actually just going to switch this to um changing it to
[02:06:46] switch this to um changing it to summarized problem just so we don't get
[02:06:49] summarized problem just so we don't get any kind of overlaps that cause problems
[02:06:50] any kind of overlaps that cause problems down the line. A summary of the user's
[02:06:55] down the line. A summary of the user's problem.
[02:07:02] Then we put this in here. Get to spit it
[02:07:04] Then we put this in here. Get to spit it out. So when you put a variable in a
[02:07:07] out. So when you put a variable in a message, it's just going to print out
[02:07:08] message, it's just going to print out and and spit out the the value that's
[02:07:10] and and spit out the the value that's inside that variable. So we've set the
[02:07:12] inside that variable. So we've set the summarized problem variable and then
[02:07:13] summarized problem variable and then we're just going to spit it out and send
[02:07:15] we're just going to spit it out and send it into the chat or over the over the
[02:07:16] it into the chat or over the over the phone. So now we can come back out to
[02:07:17] phone. So now we can come back out to our knowledge base and we can take out
[02:07:19] our knowledge base and we can take out the SL response and replace it with
[02:07:21] the SL response and replace it with summarized summarized problem. Then we
[02:07:23] summarized summarized problem. Then we can save the chunks that come back from
[02:07:24] can save the chunks that come back from the knowledge base. I don't want to get
[02:07:26] the knowledge base. I don't want to get too in depth on what chunks are
[02:07:28] too in depth on what chunks are specifically. It's a little bit more
[02:07:29] specifically. It's a little bit more advanced, but for now, we can just know
[02:07:30] advanced, but for now, we can just know that it's going to return some
[02:07:31] that it's going to return some information from that knowledge base.
[02:07:32] information from that knowledge base. It's going to chop up that document we
[02:07:34] It's going to chop up that document we put in. And when we put in this
[02:07:36] put in. And when we put in this question, it's going to basically ask
[02:07:38] question, it's going to basically ask that knowledge base, can we get three
[02:07:39] that knowledge base, can we get three chunks that most closely match the
[02:07:41] chunks that most closely match the information that is in this query that
[02:07:42] information that is in this query that we sent to it. So, we can save these
[02:07:44] we sent to it. So, we can save these chunks, which is going to be three
[02:07:45] chunks, which is going to be three because we set that up in the knowledge
[02:07:46] because we set that up in the knowledge base settings into this chunks variable.
[02:07:48] base settings into this chunks variable. And the chunk limit is three still. If
[02:07:50] And the chunk limit is three still. If we click this, we can add in a chunks
[02:07:52] we click this, we can add in a chunks not found path. But for this tutorial,
[02:07:53] not found path. But for this tutorial, we don't need to worry about that
[02:07:54] we don't need to worry about that necessarily. And then we're going to use
[02:07:56] necessarily. And then we're going to use those chunks that came back from the
[02:07:57] those chunks that came back from the knowledge base to generate an answer
[02:07:58] knowledge base to generate an answer based on the original question. So if we
[02:08:00] based on the original question. So if we put this here, we go talk, we go prompt.
[02:08:02] put this here, we go talk, we go prompt. And for this prompt, if we go here, we
[02:08:04] And for this prompt, if we go here, we can create a new prompt. We can add in
[02:08:06] can create a new prompt. We can add in the conversation history just for good
[02:08:08] the conversation history just for good measure here to give it the full context
[02:08:09] measure here to give it the full context of what's going on. And then I have a
[02:08:10] of what's going on. And then I have a prompt here. You are an AI customer
[02:08:12] prompt here. You are an AI customer support rep from Connor's Cleaning
[02:08:13] support rep from Connor's Cleaning helping customer with the question. Use
[02:08:15] helping customer with the question. Use the provider details below to answer the
[02:08:17] the provider details below to answer the customer's question. Ensure you keep
[02:08:18] customer's question. Ensure you keep your answer brief and speak directly to
[02:08:20] your answer brief and speak directly to your end customer. You are speaking to
[02:08:21] your end customer. You are speaking to them over the phone. It's the input data
[02:08:24] them over the phone. It's the input data provider details which is the chunks
[02:08:25] provider details which is the chunks variable. I'll just put that in
[02:08:27] variable. I'll just put that in again. Chunks to make sure it's set up
[02:08:30] again. Chunks to make sure it's set up properly to the user's original uh
[02:08:34] properly to the user's original uh question. We can put all this
[02:08:36] question. We can put all this information back in. So, first reply,
[02:08:38] information back in. So, first reply, this is what they asked us as soon as
[02:08:39] this is what they asked us as soon as they picked up the phone or the first
[02:08:40] they picked up the phone or the first message they sent when we asked them
[02:08:42] message they sent when we asked them what can we help you with. And then we
[02:08:44] what can we help you with. And then we also just put in for good measure our
[02:08:46] also just put in for good measure our summary of the problem that they
[02:08:48] summary of the problem that they confirmed. And we can go to our
[02:08:51] confirmed. And we can go to our summarize problem
[02:08:53] summarize problem variable and throw that in. That should
[02:08:55] variable and throw that in. That should be good to
[02:08:56] be good to go. And I like to make these look purple
[02:08:59] go. And I like to make these look purple or some kind of cool color. Um, call
[02:09:02] or some kind of cool color. Um, call this a KB
[02:09:04] this a KB query. And we can change this to
[02:09:07] query. And we can change this to generate answer from chunks. Let's say
[02:09:11] generate answer from chunks. Let's say from Kh. And if you want to make this a
[02:09:13] from Kh. And if you want to make this a bit easier for you to kind of understand
[02:09:15] bit easier for you to kind of understand at a glance, you can add in your
[02:09:17] at a glance, you can add in your descriptions on these. So if we go to
[02:09:18] descriptions on these. So if we go to edit again and we go here, this takes in
[02:09:22] edit again and we go here, this takes in chunks from the from the KB and their
[02:09:25] chunks from the from the KB and their original question and writes a short and
[02:09:28] original question and writes a short and sweet answer. And we have this in here
[02:09:30] sweet answer. And we have this in here that you are speaking to them over the
[02:09:31] that you are speaking to them over the phone because we want to make sure that
[02:09:32] phone because we want to make sure that we're building this with the phone in
[02:09:33] we're building this with the phone in mind, which is more tricky than just
[02:09:35] mind, which is more tricky than just chat. So long text outputs don't really
[02:09:37] chat. So long text outputs don't really work that well over the phone. So that's
[02:09:38] work that well over the phone. So that's kind of why we're putting that in there
[02:09:39] kind of why we're putting that in there as well. And we can call this um
[02:09:42] as well. And we can call this um generate
[02:09:44] generate answer. All right. So now we can
[02:09:46] answer. All right. So now we can actually give this a spin. We can start
[02:09:48] actually give this a spin. We can start it right from the beginning
[02:09:52] again. Oh, we may need to if we just
[02:09:54] again. Oh, we may need to if we just click run. Okay, there's no training
[02:09:56] click run. Okay, there's no training needed yet. We can run
[02:09:59] needed yet. We can run test. Where are you
[02:10:01] test. Where are you located? Sounds like you're asking about
[02:10:03] located? Sounds like you're asking about a business location. Could you confirm
[02:10:04] a business location. Could you confirm if you'd like to know the specific
[02:10:06] if you'd like to know the specific address or where Connor's Cleaning
[02:10:08] address or where Connor's Cleaning operates? Okay, it's good this popped up
[02:10:09] operates? Okay, it's good this popped up because as you can see, it's asking for
[02:10:10] because as you can see, it's asking for a non- yes or no answer. We're just
[02:10:12] a non- yes or no answer. We're just looking for a confirmation in yes or no.
[02:10:15] looking for a confirmation in yes or no. And so this would technically break the
[02:10:16] And so this would technically break the system and that'd be saying, "Oh, I'd
[02:10:18] system and that'd be saying, "Oh, I'd like a specific address." And this is
[02:10:19] like a specific address." And this is looking for yes or no. And so it would
[02:10:20] looking for yes or no. And so it would send it to this no match. So what we can
[02:10:23] send it to this no match. So what we can do to fix this is to go into the
[02:10:24] do to fix this is to go into the summarize problem prompt, modify the
[02:10:26] summarize problem prompt, modify the prompt, and then say they should be able
[02:10:29] prompt, and then say they should be able to answer only with yes or no. This is a
[02:10:32] to answer only with yes or no. This is a confirmation step, not asking for more
[02:10:35] confirmation step, not asking for more information.
[02:10:38] So now if we run that
[02:10:48] again, whereabouts are you
[02:10:53] located? Sounds like you want to know
[02:10:54] located? Sounds like you want to know the specific location of our cleaning
[02:10:56] the specific location of our cleaning business. Is that correct?
[02:10:58] business. Is that correct? Yep. Now it goes to the router here.
[02:11:02] Yep. Now it goes to the router here. It's going to determine that I said yes.
[02:11:04] It's going to determine that I said yes. Bam, bam, bam. And there we go. So that
[02:11:06] Bam, bam, bam. And there we go. So that that all happened pretty quickly, but
[02:11:08] that all happened pretty quickly, but you can see it's sort of broken down
[02:11:09] you can see it's sort of broken down through here. Um, if I click over here,
[02:11:11] through here. Um, if I click over here, it's going to remove all of this. Okay,
[02:11:13] it's going to remove all of this. Okay, so let's break down how this happened
[02:11:14] so let's break down how this happened step by step. Um, so you can see this
[02:11:16] step by step. Um, so you can see this through here. It's still using 3.5 haiku
[02:11:18] through here. It's still using 3.5 haiku for some reason. I'll need to double
[02:11:20] for some reason. I'll need to double check why that's still using the model
[02:11:22] check why that's still using the model we didn't select. But basically, it
[02:11:24] we didn't select. But basically, it comes through this step here is the
[02:11:25] comes through this step here is the intent classifier. So you can see that
[02:11:26] intent classifier. So you can see that it set it as yes. That is the correct
[02:11:29] it set it as yes. That is the correct intent and predicted intent yes. And
[02:11:31] intent and predicted intent yes. And that routed it to
[02:11:33] that routed it to this. And then using the model again, it
[02:11:37] this. And then using the model again, it analyzed the information that it was
[02:11:38] analyzed the information that it was given. And then it set the desired
[02:11:40] given. And then it set the desired action variable to ask a question which
[02:11:42] action variable to ask a question which is one of the labels that we wanted and
[02:11:43] is one of the labels that we wanted and that is correct. And then it said
[02:11:45] that is correct. And then it said condition matched taken path one. So it
[02:11:47] condition matched taken path one. So it set the desired action variable to ask a
[02:11:49] set the desired action variable to ask a question. We were checking for it here.
[02:11:51] question. We were checking for it here. Then it said okay great. Now I'm sending
[02:11:52] Then it said okay great. Now I'm sending it up here to the knowledgebased query.
[02:11:55] it up here to the knowledgebased query. It says it's query received. We passed
[02:11:56] It says it's query received. We passed in all the information whereabouts you
[02:11:58] in all the information whereabouts you located and then the summary that we
[02:12:00] located and then the summary that we gave it. And then we got two chunks back
[02:12:02] gave it. And then we got two chunks back from the KB and the AI response here
[02:12:04] from the KB and the AI response here finally took in all of this information
[02:12:06] finally took in all of this information and it gave us the final output and
[02:12:08] and it gave us the final output and generated this response. We are located
[02:12:10] generated this response. We are located at 247 ra and at the end here it's
[02:12:12] at 247 ra and at the end here it's saying is there a specific area you're
[02:12:14] saying is there a specific area you're interested in. For a basic build like
[02:12:16] interested in. For a basic build like this I'd probably change the prompt to
[02:12:17] this I'd probably change the prompt to say don't ask another question because
[02:12:19] say don't ask another question because in this case you then need to set up a
[02:12:20] in this case you then need to set up a looping mechanism where it can keep
[02:12:22] looping mechanism where it can keep answering questions for them and then
[02:12:24] answering questions for them and then break out into any of these other
[02:12:25] break out into any of these other intents um as needed. But for now that
[02:12:28] intents um as needed. But for now that is a knowledge base and that's how you
[02:12:29] is a knowledge base and that's how you can ask questions. And so that is tool
[02:12:30] can ask questions. And so that is tool number one knocked out which was easy
[02:12:32] number one knocked out which was easy enough. So great we can go on to tool
[02:12:34] enough. So great we can go on to tool number two now. So for this second quote
[02:12:35] number two now. So for this second quote I'll be able to give you a relevance
[02:12:36] I'll be able to give you a relevance tool that we're using for it. But let's
[02:12:38] tool that we're using for it. But let's just jump into answering this question.
[02:12:39] just jump into answering this question. So they've said here that they wanted
[02:12:41] So they've said here that they wanted something related to pricing or quoting.
[02:12:43] something related to pricing or quoting. Remember in here in the router we have
[02:12:45] Remember in here in the router we have set the intent classifier to say it's
[02:12:47] set the intent classifier to say it's going to go to the get a quote if
[02:12:48] going to go to the get a quote if they're asking about pricing or have
[02:12:50] they're asking about pricing or have directly requests a quote. And this will
[02:12:52] directly requests a quote. And this will take them to a real-time quotation tool
[02:12:53] take them to a real-time quotation tool that takes the property type and size
[02:12:55] that takes the property type and size and then returns an estimate. So that's
[02:12:56] and then returns an estimate. So that's the people that are going to be getting
[02:12:58] the people that are going to be getting to this next branch of the agent. So
[02:13:00] to this next branch of the agent. So desired action is get a quote. We can
[02:13:04] desired action is get a quote. We can say, "Okay, sure." To give you an
[02:13:06] say, "Okay, sure." To give you an instant quote, I
[02:13:11] just Okay, sure. To give you an instant
[02:13:14] just Okay, sure. To give you an instant quote, I just need the properties type
[02:13:15] quote, I just need the properties type and size and square feet. Then I'm going
[02:13:18] and size and square feet. Then I'm going to add another chat step or message,
[02:13:20] to add another chat step or message, sorry. And we can ask a
[02:13:24] question. Is the property a house or an
[02:13:29] apartment? The next we can do one of
[02:13:32] apartment? The next we can do one of these choice steps again and this time
[02:13:34] these choice steps again and this time we get to create some custom intents. So
[02:13:36] we get to create some custom intents. So we can go to triggers here and we want
[02:13:38] we can go to triggers here and we want to select an intent. See it doesn't have
[02:13:39] to select an intent. See it doesn't have a house. So we can go create an intent
[02:13:41] a house. So we can go create an intent and we say house. The
[02:13:46] users property type is a house. And then
[02:13:50] users property type is a house. And then we can add in some examples here. So
[02:13:52] we can add in some examples here. So obviously house this is just giving
[02:13:54] obviously house this is just giving examples to voice flows AI engine to
[02:13:56] examples to voice flows AI engine to help us better to classify the different
[02:13:58] help us better to classify the different intents as they come into this step. So
[02:14:00] intents as they come into this step. So we can say home and then you can add in
[02:14:02] we can say home and then you can add in some AI generated ones here which
[02:14:04] some AI generated ones here which usually pretty easy and uh which usually
[02:14:06] usually pretty easy and uh which usually pretty good. Okay, residence, dwelling,
[02:14:07] pretty good. Okay, residence, dwelling, property, abode, living place. Uh this
[02:14:10] property, abode, living place. Uh this this gets tricky um because some of
[02:14:12] this gets tricky um because some of these could overlap with apartment. So
[02:14:14] these could overlap with apartment. So property is probably abodess too broad
[02:14:17] property is probably abodess too broad living place.
[02:14:18] living place. uh dwelling uh
[02:14:21] uh dwelling uh residence potentially we could get away
[02:14:23] residence potentially we could get away with. We could say like
[02:14:26] with. We could say like manor mansion family
[02:14:31] home single family
[02:14:35] home single family home and by now we've given enough
[02:14:37] home and by now we've given enough examples where we can just go to create
[02:14:39] examples where we can just go to create and now we need to do the same for
[02:14:41] and now we need to do the same for apartment. So, we'll go to create an
[02:14:43] apartment. So, we'll go to create an intent apartment. The user's property
[02:14:47] intent apartment. The user's property type. The user's property type is an
[02:14:49] type. The user's property type is an apartment. And then we can put an
[02:14:55] apartment. Um, see what else it's got
[02:14:58] apartment. Um, see what else it's got for us. Um, townhouse,
[02:15:02] for us. Um, townhouse, penthouse, duplex, flat, probably not
[02:15:06] penthouse, duplex, flat, probably not right. Loft probably not right.
[02:15:08] right. Loft probably not right. Townhouse penthouse. Think that's a good
[02:15:10] Townhouse penthouse. Think that's a good bunch.
[02:15:12] bunch. And then we can add in a no match here
[02:15:13] And then we can add in a no match here as well.
[02:15:16] as well. Um, and we can add in a reprompt. Sorry,
[02:15:19] Um, and we can add in a reprompt. Sorry, I didn't get that. Is it a house or
[02:15:26] an If it is a house, we can come up here
[02:15:28] an If it is a house, we can come up here and set it as logic here and go
[02:15:34] set. We can
[02:15:37] set. We can go value or expression. Select the
[02:15:40] go value or expression. Select the variable to set. We're going to go
[02:15:42] variable to set. We're going to go property
[02:15:45] property type the
[02:15:48] the save that variable or create that
[02:15:51] the save that variable or create that variable, sorry. And then we can enter
[02:15:53] variable, sorry. And then we can enter this
[02:15:54] this in and set this as
[02:15:58] in and set this as house. So we're setting the property
[02:16:00] house. So we're setting the property type variable to house when it's been
[02:16:02] type variable to house when it's been triggered um by this particular
[02:16:05] triggered um by this particular route. And then we need to add another
[02:16:07] route. And then we need to add another one. So, I'll probably just duplicate
[02:16:11] one. So, I'll probably just duplicate this. That's by right clicking on one of
[02:16:13] this. That's by right clicking on one of these blocks. Um, and then we can
[02:16:15] these blocks. Um, and then we can connect up apartment to
[02:16:17] connect up apartment to it. Property type. Instead of being
[02:16:19] it. Property type. Instead of being house, we can make it
[02:16:23] apartment. And from here, now that we
[02:16:25] apartment. And from here, now that we know the property type, we can set the
[02:16:27] know the property type, we can set the size of the apartment or the house. So,
[02:16:29] size of the apartment or the house. So, we go and how many
[02:16:32] we go and how many square and how many square feet is it?
[02:16:37] square and how many square feet is it? We can connect both of these up here.
[02:16:39] We can connect both of these up here. And then we're going to save the entire
[02:16:40] And then we're going to save the entire user reply or on a capture step. So
[02:16:43] user reply or on a capture step. So anything that they respond to after
[02:16:44] anything that they respond to after this, we want to capture the entire
[02:16:48] thing. And we want to go here, set up a
[02:16:52] thing. And we want to go here, set up a set
[02:16:54] set step. Sorry, that's not right.
[02:17:05] using a prompt. And what we're going to
[02:17:07] using a prompt. And what we're going to do is use AI to analyze the response and
[02:17:10] do is use AI to analyze the response and then extract the number of square feet
[02:17:12] then extract the number of square feet from it. We could have used a step here
[02:17:14] from it. We could have used a step here where we change this to instead of the
[02:17:15] where we change this to instead of the entire user reply, we change it to an
[02:17:17] entire user reply, we change it to an entity. Um, but it's not as reliable as
[02:17:20] entity. Um, but it's not as reliable as doing it this way. So, I'd prefer to
[02:17:21] doing it this way. So, I'd prefer to just get it right the first time. Um,
[02:17:23] just get it right the first time. Um, cuz a entity of the number of uh number
[02:17:26] cuz a entity of the number of uh number of feet may be a bit harder to pick up
[02:17:28] of feet may be a bit harder to pick up than a clear word like an entity of
[02:17:30] than a clear word like an entity of house or apartment or a name, etc. So
[02:17:33] house or apartment or a name, etc. So just to make sure that it works every
[02:17:35] just to make sure that it works every time for us, we want to create a new
[02:17:37] time for us, we want to create a new prompt. And I'm going to put this in
[02:17:39] prompt. And I'm going to put this in here. Extract the number of square feet
[02:17:40] here. Extract the number of square feet from what the user said in numerical
[02:17:42] from what the user said in numerical format only. Each 500 include nothing
[02:17:44] format only. Each 500 include nothing else in your response. This will be
[02:17:45] else in your response. This will be saved as a variable and passed to an API
[02:17:47] saved as a variable and passed to an API to a quote generator function. So giving
[02:17:49] to a quote generator function. So giving it a bit of context about what's been
[02:17:50] it a bit of context about what's been going on. And also put in the memory
[02:17:52] going on. And also put in the memory there just for good
[02:17:54] there just for good measure. Oh, we didn't name the prompt.
[02:17:57] measure. Oh, we didn't name the prompt. Call this extract square.
[02:18:04] And then we need to set the variable
[02:18:05] And then we need to set the variable that we want to save this to, which is
[02:18:06] that we want to save this to, which is going to be proper
[02:18:08] going to be proper property size. So now we're saving that
[02:18:12] property size. So now we're saving that response, the size of the
[02:18:16] user's, the size of the user's property
[02:18:18] user's, the size of the user's property in square
[02:18:19] in square feet. And then we need to do one kind of
[02:18:22] feet. And then we need to do one kind of tricky step, but it's just something
[02:18:23] tricky step, but it's just something that you guys will pick up as you go and
[02:18:25] that you guys will pick up as you go and uh as you build more of these. But the
[02:18:27] uh as you build more of these. But the next step after this is going to be
[02:18:28] next step after this is going to be sending that information to a relevance
[02:18:30] sending that information to a relevance tool. And the relevance tool is
[02:18:31] tool. And the relevance tool is expecting not what's called a string,
[02:18:33] expecting not what's called a string, which is just a number of letters or
[02:18:36] which is just a number of letters or just text. Um, you can have a number as
[02:18:38] just text. Um, you can have a number as a text, which is confusing, but
[02:18:39] a text, which is confusing, but basically it's just the format uh in
[02:18:41] basically it's just the format uh in which it's being received in. So,
[02:18:42] which it's being received in. So, because we're sending it over an API, we
[02:18:44] because we're sending it over an API, we need to be specific about the format. So
[02:18:46] need to be specific about the format. So I can't take this is essentially going
[02:18:48] I can't take this is essentially going to be saving that 500 or say if we say
[02:18:50] to be saving that 500 or say if we say it's a 500 foot property. This is going
[02:18:52] it's a 500 foot property. This is going to be plucking that out and giving us
[02:18:55] to be plucking that out and giving us 500 as a string. In order to get the
[02:18:57] 500 as a string. In order to get the response we want from relevance we need
[02:18:58] response we want from relevance we need to convert it to a number and then send
[02:19:00] to convert it to a number and then send it. So a little block of uh custom code
[02:19:03] it. So a little block of uh custom code here. Um know this was a no code
[02:19:06] here. Um know this was a no code tutorial but I hope you can forgive me
[02:19:07] tutorial but I hope you can forgive me for
[02:19:10] this. And all we need to do is put this
[02:19:12] this. And all we need to do is put this in here. So property size this is the
[02:19:13] in here. So property size this is the variable. We're going to go property
[02:19:15] variable. We're going to go property size and we're just casting this
[02:19:19] size and we're just casting this variable as a number and then
[02:19:21] variable as a number and then reassigning it to the variable that it
[02:19:23] reassigning it to the variable that it was before. So we're taking whatever
[02:19:24] was before. So we're taking whatever came out of this, we're saying, okay,
[02:19:25] came out of this, we're saying, okay, can you just make it a number um and
[02:19:27] can you just make it a number um and we'll save it and sort of overwrite the
[02:19:29] we'll save it and sort of overwrite the existing
[02:19:30] existing variable. So now we have the number 500
[02:19:32] variable. So now we have the number 500 in that case that we're ready to send to
[02:19:34] in that case that we're ready to send to the next step. And then if that's gone
[02:19:35] the next step. And then if that's gone correctly, we can talk to them and
[02:19:40] say one sec while I get
[02:19:47] And then we have this JavaScript fail
[02:19:49] And then we have this JavaScript fail route here which you can just sort of
[02:19:50] route here which you can just sort of throw down there for now. Um there is a
[02:19:53] throw down there for now. Um there is a chance that this prompt outputs not just
[02:19:56] chance that this prompt outputs not just a number. As you can see we're asking it
[02:19:57] a number. As you can see we're asking it for just this and therefore the property
[02:20:00] for just this and therefore the property size variable if it just is 500. Um but
[02:20:04] size variable if it just is 500. Um but sometimes it can say hey your size is
[02:20:09] sometimes it can say hey your size is 500. and then we end up with a variable
[02:20:10] 500. and then we end up with a variable that's not actually convertible into a
[02:20:12] that's not actually convertible into a number. Um, so we do need to add a
[02:20:15] number. Um, so we do need to add a little bit there as a as a potential
[02:20:17] little bit there as a as a potential fallback. Um, probably won't be doing it
[02:20:19] fallback. Um, probably won't be doing it in this video if I'm honest. It's fairly
[02:20:21] in this video if I'm honest. It's fairly basic. Um, but you would add this in
[02:20:22] basic. Um, but you would add this in here some sort of looping back in to
[02:20:24] here some sort of looping back in to make sure that it is actually in the
[02:20:25] make sure that it is actually in the right format or just make sure that your
[02:20:26] right format or just make sure that your prompt is actually only you put like a
[02:20:28] prompt is actually only you put like a strict instruction only output just the
[02:20:30] strict instruction only output just the number um so that you get less errors
[02:20:32] number um so that you get less errors there. So the next major step after this
[02:20:34] there. So the next major step after this is to get our relevant AI research. If
[02:20:36] is to get our relevant AI research. If we go back to the Figma here, you'll see
[02:20:37] we go back to the Figma here, you'll see that we have this relevant AI tool which
[02:20:40] that we have this relevant AI tool which is going to allow us to uh generate the
[02:20:42] is going to allow us to uh generate the instant quote. So, I've pre-made this
[02:20:44] instant quote. So, I've pre-made this and I've actually sniped it from some of
[02:20:45] and I've actually sniped it from some of my accelerator resources. So, if you
[02:20:47] my accelerator resources. So, if you open this link, it's going to allow you
[02:20:50] open this link, it's going to allow you to clone this into your relevance
[02:20:51] to clone this into your relevance account. So, up here you can click clone
[02:20:54] account. So, up here you can click clone and we'll just clone it into Morningside
[02:20:58] AI. And now this thing is going to be
[02:21:01] AI. And now this thing is going to be taking in a property type and a size and
[02:21:02] taking in a property type and a size and square feet. And then we have a basic
[02:21:04] square feet. And then we have a basic LLM step here. This is a really really
[02:21:06] LLM step here. This is a really really simple one. Again, like I said earlier
[02:21:07] simple one. Again, like I said earlier in this video. The building really
[02:21:10] in this video. The building really powerful and advanced functionality does
[02:21:12] powerful and advanced functionality does take a lot longer. And if I was to do
[02:21:14] take a lot longer. And if I was to do things that weren't just a very basic
[02:21:15] things that weren't just a very basic LLM step like this, then it would take a
[02:21:17] LLM step like this, then it would take a lot longer with different platforms you
[02:21:18] lot longer with different platforms you have to sign up for. The idea is to
[02:21:20] have to sign up for. The idea is to teach you how these things can connect.
[02:21:22] teach you how these things can connect. And then you can come into relevance
[02:21:23] And then you can come into relevance here. Once you know how to connect voice
[02:21:24] here. Once you know how to connect voice flow to relevance through an API call,
[02:21:26] flow to relevance through an API call, you can come in here and throw whatever
[02:21:27] you can come in here and throw whatever the hell you want in and make it as
[02:21:28] the hell you want in and make it as advanced as you want. But in this case,
[02:21:30] advanced as you want. But in this case, we literally could have done this in
[02:21:32] we literally could have done this in voice flow if I'm being fully honest.
[02:21:34] voice flow if I'm being fully honest. But the idea of being able to access an
[02:21:35] But the idea of being able to access an external tool via an API is really the
[02:21:38] external tool via an API is really the skill that I'm trying to teach you here.
[02:21:39] skill that I'm trying to teach you here. So, what this is doing is taking in the
[02:21:41] So, what this is doing is taking in the property type. We've got two options
[02:21:42] property type. We've got two options here and the square footage in a number.
[02:21:46] here and the square footage in a number. See here, it's it's a number. I can't
[02:21:47] See here, it's it's a number. I can't just type in here. It has to be a
[02:21:49] just type in here. It has to be a number. So, that's what the API is going
[02:21:50] number. So, that's what the API is going to be expecting. You can see here that
[02:21:51] to be expecting. You can see here that it says it's expecting a number. And
[02:21:54] it says it's expecting a number. And then we pass this into a basic prompt
[02:21:55] then we pass this into a basic prompt here that's saying the customer is
[02:21:56] here that's saying the customer is requesting this um and these are the
[02:21:58] requesting this um and these are the rough prices for the different square
[02:22:00] rough prices for the different square footage and different types. and the LLM
[02:22:02] footage and different types. and the LLM in this case GPT4 mini just going to
[02:22:04] in this case GPT4 mini just going to look over that take in their inputs and
[02:22:05] look over that take in their inputs and then give an output. So if I just go up
[02:22:07] then give an output. So if I just go up here and I set it's an apartment and I
[02:22:10] here and I set it's an apartment and I mean I don't know what five how big is
[02:22:12] mean I don't know what five how big is an apartment in square feet I don't know
[02:22:15] an apartment in square feet I don't know um but we can run
[02:22:19] that it's going to give us some kind of
[02:22:22] that it's going to give us some kind of output and then it gives us the
[02:22:24] output and then it gives us the estimate. So it's saying regular
[02:22:25] estimate. So it's saying regular maintenance cleaning for 60 deep
[02:22:26] maintenance cleaning for 60 deep cleaning for 120 move and move out etc.
[02:22:29] cleaning for 120 move and move out etc. So that's the output that we're going to
[02:22:30] So that's the output that we're going to be sending back to voice flow and we're
[02:22:32] be sending back to voice flow and we're going to be turning that into a nice
[02:22:33] going to be turning that into a nice message to send through chat or through
[02:22:35] message to send through chat or through the phone. So in order to set this tool
[02:22:36] the phone. So in order to set this tool up in voice flow and be able to interact
[02:22:38] up in voice flow and be able to interact with it, we need to we can hide this
[02:22:40] with it, we need to we can hide this make sure the tool's been saved and you
[02:22:41] make sure the tool's been saved and you have it in your account and then you can
[02:22:43] have it in your account and then you can go to use here and just like we learned
[02:22:45] go to use here and just like we learned in theuh NA10 tutorial we can go to API
[02:22:48] in theuh NA10 tutorial we can go to API here and then we get an API for us to
[02:22:50] here and then we get an API for us to use and again is a post request and it
[02:22:53] use and again is a post request and it tells us how to use it. So we have
[02:22:54] tells us how to use it. So we have params basically the inputs it's
[02:22:56] params basically the inputs it's expecting of the property type and a
[02:22:58] expecting of the property type and a string. You see how it's got two uh
[02:22:59] string. You see how it's got two uh quotations? That means anything inside
[02:23:01] quotations? That means anything inside it is a string. And the square footage
[02:23:02] it is a string. And the square footage here, you can see it isn't in quotation.
[02:23:04] here, you can see it isn't in quotation. So, it's not a string. It's in this
[02:23:05] So, it's not a string. It's in this case, it's a number. And of course, we
[02:23:07] case, it's a number. And of course, we have the project ID here, letting
[02:23:08] have the project ID here, letting relevance know which tool that we've
[02:23:10] relevance know which tool that we've created that we're actually trying to
[02:23:11] created that we're actually trying to interact with. And so, all we need to do
[02:23:12] interact with. And so, all we need to do now to interact with this and set up our
[02:23:14] now to interact with this and set up our quote generator is to copy this link.
[02:23:16] quote generator is to copy this link. So, this is the endpoint URL that we're
[02:23:17] So, this is the endpoint URL that we're going to be calling over the internet.
[02:23:19] going to be calling over the internet. And this is what it's expecting in the
[02:23:20] And this is what it's expecting in the in the body of that post request. If you
[02:23:22] in the body of that post request. If you go back to voice flow here and we need
[02:23:25] go back to voice flow here and we need to go to dev
[02:23:27] to go to dev API, we're going to change this to post.
[02:23:30] API, we're going to change this to post. Put in that
[02:23:31] Put in that URL. And in this case, seems that we've
[02:23:33] URL. And in this case, seems that we've got a little bit of a different page on
[02:23:34] got a little bit of a different page on relevant for some reason. So we can
[02:23:36] relevant for some reason. So we can actually do the authentication step,
[02:23:37] actually do the authentication step, which is helpful. So you can click
[02:23:38] which is helpful. So you can click generate API key here. May have changed
[02:23:40] generate API key here. May have changed by the time you're watching this video,
[02:23:41] by the time you're watching this video, but should roughly be the same. And we
[02:23:44] but should roughly be the same. And we can click deploy here. Make sure that
[02:23:46] can click deploy here. Make sure that the API is up and running for us to
[02:23:47] the API is up and running for us to interact
[02:23:48] interact with. Actually, now that we've deployed
[02:23:50] with. Actually, now that we've deployed it, we don't need the authentication
[02:23:52] it, we don't need the authentication anymore. That was a bit strange. Uh,
[02:23:55] anymore. That was a bit strange. Uh, actually, I will do the API key just so
[02:23:57] actually, I will do the API key just so you guys see how this works. We can make
[02:23:58] you guys see how this works. We can make it private here. So, now that we have
[02:24:00] it private here. So, now that we have our API key, we need to see how it's
[02:24:02] our API key, we need to see how it's expecting to receive that API key via
[02:24:04] expecting to receive that API key via the HTTP request, which we're going to
[02:24:05] the HTTP request, which we're going to be sending from voice flow. Um, so if we
[02:24:07] be sending from voice flow. Um, so if we scroll down here, curl is usually the
[02:24:09] scroll down here, curl is usually the one I like to go to. And there is a
[02:24:10] one I like to go to. And there is a little bit I haven't really explained in
[02:24:12] little bit I haven't really explained in terms of headers and bodies when it
[02:24:13] terms of headers and bodies when it comes to API calls. But for now, just
[02:24:15] comes to API calls. But for now, just know that when you have a curl request
[02:24:17] know that when you have a curl request like this, maybe it's even easier on the
[02:24:18] like this, maybe it's even easier on the uh JavaScript. Here we have what's
[02:24:20] uh JavaScript. Here we have what's called headers. And this is basically
[02:24:22] called headers. And this is basically like the the the envelope that you put
[02:24:25] like the the the envelope that you put the information in. So this up here is
[02:24:27] the information in. So this up here is the information that we're putting in
[02:24:28] the information that we're putting in the request. It's going inside the
[02:24:29] the request. It's going inside the envelope. And the headers and the method
[02:24:32] envelope. And the headers and the method and the endpoint URL are like the stamp
[02:24:34] and the endpoint URL are like the stamp and the information that you put on the
[02:24:35] and the information that you put on the outside of the envelope to make sure it
[02:24:36] outside of the envelope to make sure it gets where it wants to go. So you can
[02:24:38] gets where it wants to go. So you can say that this endpoint here, that's what
[02:24:40] say that this endpoint here, that's what we call the endpoint. Same as up here.
[02:24:41] we call the endpoint. Same as up here. That's the the same as we have just
[02:24:43] That's the the same as we have just here. Endpoint is like the address where
[02:24:45] here. Endpoint is like the address where the envelope is being sent to. We have
[02:24:47] the envelope is being sent to. We have the post, the method. Maybe this is like
[02:24:50] the post, the method. Maybe this is like super fast mail or like overnight
[02:24:52] super fast mail or like overnight delivery or maybe like a parcel versus
[02:24:54] delivery or maybe like a parcel versus an envelope. Basically, the type of
[02:24:56] an envelope. Basically, the type of delivery that you're doing or type of
[02:24:57] delivery that you're doing or type of request. And the headers include
[02:24:58] request. And the headers include important stuff like the type of content
[02:25:00] important stuff like the type of content that's inside it. So you might say this
[02:25:02] that's inside it. So you might say this like this is there's written text or
[02:25:03] like this is there's written text or there's a letter in here. So it might
[02:25:05] there's a letter in here. So it might seem a little bit complicated, but we'll
[02:25:06] seem a little bit complicated, but we'll fill this all in. Now, anytime you are
[02:25:08] fill this all in. Now, anytime you are making an API call, you'll see these
[02:25:09] making an API call, you'll see these headers around and you'll see the
[02:25:11] headers around and you'll see the endpoint and the method and then the
[02:25:12] endpoint and the method and then the body which we're going to be setting up.
[02:25:14] body which we're going to be setting up. So, this will all make sense in 2
[02:25:15] So, this will all make sense in 2 seconds, but let's just say for now we
[02:25:17] seconds, but let's just say for now we have content type and it's going to be
[02:25:18] have content type and it's going to be application JSON. That's one of our
[02:25:20] application JSON. That's one of our headers. So, if we go back to Connor's
[02:25:22] headers. So, if we go back to Connor's cleaning, we open up the headers. We can
[02:25:25] cleaning, we open up the headers. We can go content type here as we saw here,
[02:25:28] go content type here as we saw here, right? So content type, we need to set
[02:25:29] right? So content type, we need to set it to
[02:25:30] it to application/json. Very common one that
[02:25:32] application/json. Very common one that you're going to be
[02:25:33] you're going to be using. And we have another one which is
[02:25:36] using. And we have another one which is authorization. So this is basically the
[02:25:38] authorization. So this is basically the majority of the endpoints you're going
[02:25:39] majority of the endpoints you're going to be seeing which is authorization and
[02:25:41] to be seeing which is authorization and content type. And a lot of the time it's
[02:25:42] content type. And a lot of the time it's going to be an API key and application
[02:25:45] going to be an API key and application JSON. So then we can go back to
[02:25:47] JSON. So then we can go back to relevance. We can get our API
[02:25:50] relevance. We can get our API key. And now to set up the body of the
[02:25:54] key. And now to set up the body of the request which is this. We can copy this
[02:25:58] request which is this. We can copy this and change this to raw. And we'll paste
[02:26:01] and change this to raw. And we'll paste this in. we have the params or the
[02:26:03] this in. we have the params or the inputs in this case, the property type
[02:26:05] inputs in this case, the property type and square footage for the tool. And
[02:26:06] and square footage for the tool. And what we want to do is insert the
[02:26:08] what we want to do is insert the variables that we've got over here into
[02:26:11] variables that we've got over here into these. So we can go inside these
[02:26:12] these. So we can go inside these quotations here and we can go property
[02:26:16] quotations here and we can go property uh type in this case and then for square
[02:26:20] uh type in this case and then for square footage we can go
[02:26:22] footage we can go property
[02:26:25] property size. And so because the property type
[02:26:27] size. And so because the property type is expecting a string as we can see if
[02:26:29] is expecting a string as we can see if we go back here um to build
[02:26:32] we go back here um to build It's expecting a string and this is
[02:26:34] It's expecting a string and this is expecting a number. The string must be
[02:26:37] expecting a number. The string must be wrapped around in uh these quotations
[02:26:40] wrapped around in uh these quotations and the square footage is a number and
[02:26:42] and the square footage is a number and so we can just put the number because
[02:26:44] so we can just put the number because we've already converted it into a number
[02:26:45] we've already converted it into a number here. Right? So that's probably the
[02:26:47] here. Right? So that's probably the trickiest part of all the stuff I'm
[02:26:48] trickiest part of all the stuff I'm going to teach you today. And now that
[02:26:49] going to teach you today. And now that we have this set up, we can actually
[02:26:50] we have this set up, we can actually send a test request and we can say uh
[02:26:53] send a test request and we can say uh house. We can say 500 and test this API
[02:26:58] house. We can say 500 and test this API call. And there we go. It's complete. We
[02:27:00] call. And there we go. It's complete. We have got back our answer the estimate
[02:27:02] have got back our answer the estimate etc. and all of the information is
[02:27:04] etc. and all of the information is coming back from relevant AI as expected
[02:27:06] coming back from relevant AI as expected and now what we need to do is extract
[02:27:07] and now what we need to do is extract the information which we want which is
[02:27:09] the information which we want which is this answer from this API call and from
[02:27:11] this answer from this API call and from the response. So we sent a request and
[02:27:13] the response. So we sent a request and we got a response. Remember how we were
[02:27:15] we got a response. Remember how we were using those terms before. We can click
[02:27:16] using those terms before. We can click on answer and we can save it to and we
[02:27:20] on answer and we can save it to and we can call it uh
[02:27:22] can call it uh raw quote
[02:27:24] raw quote data because it is quite raw
[02:27:28] data because it is quite raw um raw quote data
[02:27:33] from. And now we have the information
[02:27:35] from. And now we have the information back from relevance AI. All we need to
[02:27:37] back from relevance AI. All we need to do is make it pretty and use AI to
[02:27:39] do is make it pretty and use AI to generate a message that summarizes the
[02:27:41] generate a message that summarizes the quote to the customer. So we can go a uh
[02:27:45] quote to the customer. So we can go a uh prompt step here. We can create a new
[02:27:48] prompt step here. We can create a new prompt. Let's add in the conversation
[02:27:50] prompt. Let's add in the conversation history for context. And I've got this
[02:27:53] history for context. And I've got this prompt
[02:27:55] prompt here. Write a short and clear
[02:27:57] here. Write a short and clear explanation of this quote for the
[02:27:58] explanation of this quote for the customers. uh we can go
[02:28:01] customers. uh we can go property property
[02:28:03] property property type for the customer's property type
[02:28:06] type for the customer's property type and we can put in the raw quote data
[02:28:08] and we can put in the raw quote data here. So that's going to insert this
[02:28:10] here. So that's going to insert this with the customer's apartment or the
[02:28:12] with the customer's apartment or the customer's house and then we're just
[02:28:13] customer's house and then we're just going to dump in the raw data that came
[02:28:15] going to dump in the raw data that came back from relevance AI. Your response
[02:28:16] back from relevance AI. Your response will be read over the phone. So it must
[02:28:18] will be read over the phone. So it must be all in one paragraph and no longer
[02:28:19] be all in one paragraph and no longer than three to four short sentences. It
[02:28:21] than three to four short sentences. It should read like and I've given an
[02:28:22] should read like and I've given an example here of how I wanted to give the
[02:28:24] example here of how I wanted to give the outputs.
[02:28:28] And so we can change this to
[02:28:31] And so we can change this to quote quote response. And now we are
[02:28:35] quote quote response. And now we are ready to give this a spin. So if we run
[02:28:38] ready to give this a spin. So if we run this whole thing from the top
[02:28:40] this whole thing from the top um
[02:28:46] run, how much for a weekly clean? So I'm
[02:28:50] run, how much for a weekly clean? So I'm going straight to the asking a question
[02:28:51] going straight to the asking a question about price. You're asking about a
[02:28:53] about price. You're asking about a pricing for our weekly cleaning service.
[02:28:55] pricing for our weekly cleaning service. Is that correct? Yes.
[02:28:57] Is that correct? Yes. Bam. Bam. Okay, sure. To give you an
[02:29:00] Bam. Bam. Okay, sure. To give you an instant quote, I just need the property
[02:29:01] instant quote, I just need the property type and size and square feet. Is the
[02:29:03] type and size and square feet. Is the property a house or an apartment? It's a
[02:29:10] house. How many square feet is it? 500.
[02:29:13] house. How many square feet is it? 500. I don't know. Is that a big That sounds
[02:29:14] I don't know. Is that a big That sounds very small to
[02:29:16] very small to me. I don't know if 500 I have I have no
[02:29:19] me. I don't know if 500 I have I have no I have no clue about the sizes of houses
[02:29:20] I have no clue about the sizes of houses if 500 is normal or
[02:29:23] if 500 is normal or not. And there we go. Based on your 500
[02:29:26] not. And there we go. Based on your 500 foot house, we have four cleaning
[02:29:27] foot house, we have four cleaning packages. Regular maintenance cleaning
[02:29:29] packages. Regular maintenance cleaning at $90 for standard weekly cleaning,
[02:29:31] at $90 for standard weekly cleaning, deep cleaning, ra. So, we're giving them
[02:29:33] deep cleaning, ra. So, we're giving them a quick summary based on their 500 ft
[02:29:35] a quick summary based on their 500 ft house or x number of square ft x
[02:29:38] house or x number of square ft x property type and giving them a quick
[02:29:40] property type and giving them a quick summary. So, that's pretty cool. We're
[02:29:42] summary. So, that's pretty cool. We're using relevance tool and we're getting
[02:29:43] using relevance tool and we're getting this information back. Now, there is one
[02:29:44] this information back. Now, there is one more step that I have added onto this
[02:29:46] more step that I have added onto this this I get this thing where if I've gone
[02:29:48] this I get this thing where if I've gone this far with you guys, I may as well
[02:29:49] this far with you guys, I may as well add in like the rest of it to make it
[02:29:51] add in like the rest of it to make it actually a bit more useful. um which is
[02:29:53] actually a bit more useful. um which is a quick lead capture using Google Sheets
[02:29:55] a quick lead capture using Google Sheets and Make.com. So, I couldn't leave you
[02:29:57] and Make.com. So, I couldn't leave you guys hanging on this. I thought I may as
[02:29:59] guys hanging on this. I thought I may as well throw it in there. So, stick with
[02:30:00] well throw it in there. So, stick with me because this is really where you're
[02:30:01] me because this is really where you're going to be like, "Oh, this is this is
[02:30:03] going to be like, "Oh, this is this is uh opening my eyes to to what you can do
[02:30:04] uh opening my eyes to to what you can do with these kind of platforms." So, the
[02:30:06] with these kind of platforms." So, the reason we're adding this on is because
[02:30:07] reason we're adding this on is because the person has asked about pricing or
[02:30:09] the person has asked about pricing or they're directly interested in some kind
[02:30:10] they're directly interested in some kind of services and we've given them an
[02:30:12] of services and we've given them an instant quote and now we're trying to
[02:30:13] instant quote and now we're trying to immediately follow that up with, hey,
[02:30:14] immediately follow that up with, hey, look, give us your details and we'll be
[02:30:16] look, give us your details and we'll be in touch and we'll get that service
[02:30:17] in touch and we'll get that service booked in right away. So, we can jump
[02:30:20] booked in right away. So, we can jump into a uh message block here. This is
[02:30:22] into a uh message block here. This is I'll just paste this in to keep things
[02:30:24] I'll just paste this in to keep things nice and quick here. Please provide your
[02:30:25] nice and quick here. Please provide your name and phone number and I'll get one
[02:30:27] name and phone number and I'll get one of the team to call you to find a time
[02:30:28] of the team to call you to find a time that works. Now, one thing I will change
[02:30:29] that works. Now, one thing I will change is as you saw on that last run, it had a
[02:30:32] is as you saw on that last run, it had a question at the bottom. It's like, which
[02:30:33] question at the bottom. It's like, which one are you interested in? I would
[02:30:35] one are you interested in? I would probably try to remove that.
[02:30:38] probably try to remove that. Um, do not ask a question at the end.
[02:30:43] Um, do not ask a question at the end. Just give them this description.
[02:30:52] So that's just going to end the message
[02:30:53] So that's just going to end the message and saying, "Look, this is a quote."
[02:30:54] and saying, "Look, this is a quote." Bam. And then the next message I get is
[02:30:56] Bam. And then the next message I get is this. Please provide your name and phone
[02:30:58] this. Please provide your name and phone number and I'll get one of the team to
[02:30:59] number and I'll get one of the team to call you to find a time that works. And
[02:31:01] call you to find a time that works. And so we want to save this entire user
[02:31:02] so we want to save this entire user reply with a capture step. Capture step.
[02:31:05] reply with a capture step. Capture step. There we go. Change this to entire user
[02:31:08] There we go. Change this to entire user reply. So we want to capture all of the
[02:31:09] reply. So we want to capture all of the information that they send or over the
[02:31:11] information that they send or over the phone or either through chat. So in this
[02:31:12] phone or either through chat. So in this response, they're going to say their
[02:31:13] response, they're going to say their name and their phone number, right? and
[02:31:14] name and their phone number, right? and we need to extract those
[02:31:17] we need to extract those out. I'm going to put this here and do a
[02:31:20] out. I'm going to put this here and do a set step. We're going to use a prompt.
[02:31:23] set step. We're going to use a prompt. So, we're setting this with
[02:31:26] So, we're setting this with AI. And we're going to create a new
[02:31:28] AI. And we're going to create a new prompt. Um, let's just set the variable
[02:31:30] prompt. Um, let's just set the variable first. Let's say this is going to be put
[02:31:32] first. Let's say this is going to be put into last
[02:31:35] response. Make a new prompt
[02:31:39] here. And this is the prompt that we're
[02:31:41] here. And this is the prompt that we're going to be using. So, we have just
[02:31:42] going to be using. So, we have just asked the user to provide their name and
[02:31:43] asked the user to provide their name and phone number. We need to attempt to
[02:31:44] phone number. We need to attempt to extract the information and then confirm
[02:31:46] extract the information and then confirm it with them. Here is their reply last
[02:31:48] it with them. Here is their reply last utterance which they've just provided
[02:31:49] utterance which they've just provided and we've captured. If there is a valid
[02:31:51] and we've captured. If there is a valid name and phone number present, then you
[02:31:52] name and phone number present, then you must do a confirmation eg okay quickly
[02:31:54] must do a confirmation eg okay quickly to confirm your name is this and number
[02:31:55] to confirm your name is this and number is this. Is that correct? However, if
[02:31:57] is this. Is that correct? However, if one or both are missing or appear to be
[02:31:59] one or both are missing or appear to be invalid, you must output only retry as
[02:32:01] invalid, you must output only retry as your response and nothing else. This
[02:32:03] your response and nothing else. This retry variable will be checked and if it
[02:32:05] retry variable will be checked and if it matches exactly, then it will trigger
[02:32:07] matches exactly, then it will trigger another attempt to capture. So either a
[02:32:09] another attempt to capture. So either a write a short and sweet confirmation
[02:32:10] write a short and sweet confirmation message or b output retry for another
[02:32:13] message or b output retry for another attempt at capturing. So what we're
[02:32:15] attempt at capturing. So what we're doing here is using AI to analyze the
[02:32:17] doing here is using AI to analyze the response and say look we're looking to
[02:32:18] response and say look we're looking to pluck out a name and phone number and we
[02:32:20] pluck out a name and phone number and we want to also confirm that cuz this is
[02:32:21] want to also confirm that cuz this is likely going to be over the phone. And
[02:32:22] likely going to be over the phone. And if the AI doesn't see a clear valid
[02:32:25] if the AI doesn't see a clear valid phone number and a valid name then it's
[02:32:26] phone number and a valid name then it's going to output only the word retry. So
[02:32:29] going to output only the word retry. So give us a response. If it's good to go
[02:32:31] give us a response. If it's good to go and we can move on to the next step. If
[02:32:33] and we can move on to the next step. If it says retry then we're going to try to
[02:32:35] it says retry then we're going to try to retry. Um, now of course this retry
[02:32:37] retry. Um, now of course this retry doesn't actually do anything unless we
[02:32:38] doesn't actually do anything unless we build the functionality in to look for
[02:32:40] build the functionality in to look for that retry keyword, which we'll do in a
[02:32:43] that retry keyword, which we'll do in a second untitled prompt. We can change
[02:32:45] second untitled prompt. We can change this to um extract what attempt extract
[02:32:51] name. And then we can go to um
[02:32:54] name. And then we can go to um conditions here and
[02:32:58] go if last response which is the
[02:33:01] go if last response which is the variable that we're saving the output of
[02:33:03] variable that we're saving the output of that prompt into here. Um whether it's
[02:33:05] that prompt into here. Um whether it's going to be retry or the say just to
[02:33:06] going to be retry or the say just to confirm is this your phone name and
[02:33:08] confirm is this your phone name and phone number. Um if last response is
[02:33:12] phone number. Um if last response is retry or even just to make it a bit more
[02:33:14] retry or even just to make it a bit more flexible contains retry unless unless
[02:33:17] flexible contains retry unless unless the person's name is like Bill Retry
[02:33:20] the person's name is like Bill Retry Smith then uh this should be fine. And
[02:33:21] Smith then uh this should be fine. And actually, just to make this look a bit
[02:33:23] actually, just to make this look a bit cleaner, I might change this to um if
[02:33:24] cleaner, I might change this to um if last response um does not contain retry.
[02:33:30] last response um does not contain retry. Then we're going to go up
[02:33:35] here and we are going to send the last
[02:33:39] here and we are going to send the last response because as we said, it's going
[02:33:41] response because as we said, it's going to either generate the confirmation
[02:33:42] to either generate the confirmation message or it'll output retry. So if
[02:33:44] message or it'll output retry. So if it's valid, it'll and we put up last
[02:33:46] it's valid, it'll and we put up last response here. They'll say their name
[02:33:48] response here. They'll say their name and phone number. We'll analyze it and
[02:33:50] and phone number. We'll analyze it and then we'll go great. It doesn't contain
[02:33:51] then we'll go great. It doesn't contain the word retry in it. And bang. Hey,
[02:33:53] the word retry in it. And bang. Hey, just to confirm this is your name and
[02:33:55] just to confirm this is your name and this is your phone number. And then for
[02:33:56] this is your phone number. And then for the choices here, we can go and use our
[02:33:58] the choices here, we can go and use our handy dandy. They're going to be giving
[02:34:00] handy dandy. They're going to be giving us a yes or no answer to this. So, we
[02:34:01] us a yes or no answer to this. So, we can put in these two triggers, yes and
[02:34:05] no. And so, if they say no to the
[02:34:07] no. And so, if they say no to the confirmation, say no, that's not my
[02:34:09] confirmation, say no, that's not my correct phone number or name, then we
[02:34:11] correct phone number or name, then we need to have some kind of retry um logic
[02:34:13] need to have some kind of retry um logic here. I usually like to make my retries
[02:34:16] here. I usually like to make my retries um a orange color. And then my failure
[02:34:19] um a orange color. And then my failure is a red. Um, so we
[02:34:25] say, "Okay, let's try that again. Can
[02:34:27] say, "Okay, let's try that again. Can you please give me a full name and phone
[02:34:28] you please give me a full name and phone number, please?" And then we're going to
[02:34:30] number, please?" And then we're going to send them all the way back to this step
[02:34:31] send them all the way back to this step here. So they're basically going to
[02:34:33] here. So they're basically going to recapture their information and then put
[02:34:35] recapture their information and then put them through this process. And this is a
[02:34:36] them through this process. And this is a loop that can be done over and over and
[02:34:37] loop that can be done over and over and over again. So, and then we also need to
[02:34:39] over again. So, and then we also need to deal with this else step. So if the word
[02:34:42] deal with this else step. So if the word does contain retry and it has said,
[02:34:43] does contain retry and it has said, "Hey, look, this isn't a valid phone
[02:34:45] "Hey, look, this isn't a valid phone number or a name," then we need to deal
[02:34:47] number or a name," then we need to deal with that as well. So, we can come down
[02:34:48] with that as well. So, we can come down here and go to message. Pop it under
[02:34:52] here and go to message. Pop it under here. And I've got a message for this.
[02:34:54] here. And I've got a message for this. Sorry, I didn't quite get that. Can you
[02:34:55] Sorry, I didn't quite get that. Can you please give me a full name and phone
[02:34:56] please give me a full name and phone number so a member of our team can get
[02:34:58] number so a member of our team can get in
[02:35:00] touch. Um, right click on this and you
[02:35:03] touch. Um, right click on this and you can go block color. Change it to an
[02:35:04] can go block color. Change it to an orange. And then we're going to be going
[02:35:05] orange. And then we're going to be going back to here as well. So, it's helpful.
[02:35:08] back to here as well. So, it's helpful. You can click on these arrows. So, the
[02:35:10] You can click on these arrows. So, the lines here, and you can change them to
[02:35:12] lines here, and you can change them to the same color. So, we want to make them
[02:35:14] the same color. So, we want to make them a bit more obvious that they're coming
[02:35:16] a bit more obvious that they're coming in from places we
[02:35:19] expected. We can make this an orange one
[02:35:22] expected. We can make this an orange one as
[02:35:24] as well. And this one,
[02:35:27] well. And this one, too. So, if they come in and they say,
[02:35:29] too. So, if they come in and they say, "Hey, my name's Bill and my phone number
[02:35:30] "Hey, my name's Bill and my phone number is
[02:35:31] is 02111." And it comes in here and it
[02:35:33] 02111." And it comes in here and it goes, "Hey, that doesn't look like it's
[02:35:34] goes, "Hey, that doesn't look like it's proper." It's going to send a retry as
[02:35:37] proper." It's going to send a retry as the output. We're going to pick it up
[02:35:38] the output. We're going to pick it up here and it's going to say, "Sorry, I
[02:35:39] here and it's going to say, "Sorry, I didn't quite get that." and it's going
[02:35:40] didn't quite get that." and it's going to come back up and they're going to be
[02:35:42] to come back up and they're going to be expected to give it again and it will go
[02:35:43] expected to give it again and it will go through and then once we got a valid
[02:35:45] through and then once we got a valid name and phone number and it's not
[02:35:46] name and phone number and it's not outputting retry, then it's going to go
[02:35:48] outputting retry, then it's going to go through here. It's going to spit that
[02:35:50] through here. It's going to spit that out and say, "Hey, just to double check,
[02:35:51] out and say, "Hey, just to double check, this is your phone number and email
[02:35:53] this is your phone number and email before we proceed." Yes and no. No is
[02:35:55] before we proceed." Yes and no. No is going to be handled there and it's going
[02:35:56] going to be handled there and it's going to take them back to the first step
[02:35:57] to take them back to the first step again. So, that's some nice um error
[02:36:00] again. So, that's some nice um error handling and sort of looping that you're
[02:36:01] handling and sort of looping that you're going to need to be building into a lot
[02:36:02] going to need to be building into a lot of your conversational AI agents,
[02:36:04] of your conversational AI agents, especially on voice flow, right? And so,
[02:36:05] especially on voice flow, right? And so, the last steps here are some quick
[02:36:06] the last steps here are some quick variable extractions. So we can go to
[02:36:08] variable extractions. So we can go to div logic here and go to set and we're
[02:36:11] div logic here and go to set and we're going to extract the name and the phone
[02:36:13] going to extract the name and the phone number. So we'll go prompt. Holy moly,
[02:36:16] number. So we'll go prompt. Holy moly, it is it's bloody hot here. The variable
[02:36:19] it is it's bloody hot here. The variable that we want to save this, we were going
[02:36:21] that we want to save this, we were going to be extracting the name. So we'll add
[02:36:23] to be extracting the name. So we'll add a new variable called name. The user's
[02:36:28] name. Um, and this is going to be called
[02:36:31] name. Um, and this is going to be called uh extract
[02:36:35] name. Here's a quick and easy prompt.
[02:36:37] name. Here's a quick and easy prompt. You can pause it to take a look at that.
[02:36:38] You can pause it to take a look at that. It's just going to extract their
[02:36:39] It's just going to extract their name. We need to add another variable.
[02:36:42] name. We need to add another variable. This is going to be their phone
[02:36:46] number. And then we need another
[02:36:51] prompt. Just paste this one in here.
[02:36:53] prompt. Just paste this one in here. Pretty basic. Again, pause it if you
[02:36:55] Pretty basic. Again, pause it if you want to take a
[02:36:56] want to take a look. And I haven't named that prompt.
[02:36:58] look. And I haven't named that prompt. It's going to annoy
[02:37:00] It's going to annoy me. Extract phone
[02:37:05] me. Extract phone number. And now we're going to have
[02:37:06] number. And now we're going to have their name and their phone number
[02:37:07] their name and their phone number extracted out of this response.
[02:37:11] extracted out of this response. And oh, and actually we need to add in
[02:37:15] And oh, and actually we need to add in the conversation history there so that
[02:37:18] the conversation history there so that it actually has the this information in
[02:37:22] it. And then we
[02:37:30] go great. Let me get that added into our
[02:37:32] go great. Let me get that added into our system. This buys us a bit of time as we
[02:37:35] system. This buys us a bit of time as we use our um make web hook which we're
[02:37:37] use our um make web hook which we're going to set up now. So the next step is
[02:37:39] going to set up now. So the next step is to get a Google sheet set up and to use
[02:37:41] to get a Google sheet set up and to use make.com to uh take this data and shoot
[02:37:44] make.com to uh take this data and shoot it into a Google sheet. So to do that um
[02:37:46] it into a Google sheet. So to do that um I will leave a link on I mean you can
[02:37:48] I will leave a link on I mean you can just search it up. It's make it's
[02:37:50] just search it up. It's make it's make.com. All right. I'll save you the
[02:37:52] make.com. All right. I'll save you the hassle. So you sign into make.com create
[02:37:54] hassle. So you sign into make.com create an account whatever you want to do or
[02:37:57] an account whatever you want to do or need to do.
[02:38:04] Go to scenarios and then we're going to
[02:38:06] Go to scenarios and then we're going to create a new
[02:38:08] create a new scenario. I'm going to build from
[02:38:10] scenario. I'm going to build from scratch here. I'm going to get all that
[02:38:12] scratch here. I'm going to get all that rubbish out of the way. I don't know why
[02:38:13] rubbish out of the way. I don't know why it's acting like I'm some rookie here.
[02:38:16] it's acting like I'm some rookie here. Um, and then we need to go to web hooks,
[02:38:20] Um, and then we need to go to web hooks, custom web hook. We're going to
[02:38:23] custom web hook. We're going to um we're going to add in a new web hook.
[02:38:26] um we're going to add in a new web hook. This is going to be conors cleaning lead
[02:38:29] This is going to be conors cleaning lead capture. going to save that. It's going
[02:38:32] capture. going to save that. It's going to create this web hook here. I'm going
[02:38:34] to create this web hook here. I'm going to copy this edges to clipboard. We're
[02:38:37] to copy this edges to clipboard. We're going to come back to our build and then
[02:38:39] going to come back to our build and then we're going to go to
[02:38:41] we're going to go to the API step. So, what this is doing if
[02:38:44] the API step. So, what this is doing if you're a bit new to to web hooks and and
[02:38:45] you're a bit new to to web hooks and and API calls and stuff. What we can do here
[02:38:48] API calls and stuff. What we can do here on make is set this up to basically
[02:38:50] on make is set this up to basically listen. It's a URL. You know how we had
[02:38:52] listen. It's a URL. You know how we had the endpoint? The end point, this thing
[02:38:54] the endpoint? The end point, this thing here that it's given us that I've just
[02:38:56] here that it's given us that I've just copied to our clipboard. That's like the
[02:38:58] copied to our clipboard. That's like the address, remember? So if you put it
[02:38:59] address, remember? So if you put it write it on the on the letter, that's
[02:39:01] write it on the on the letter, that's where it's going to go. This allows us
[02:39:02] where it's going to go. This allows us to basically send data um via API call
[02:39:05] to basically send data um via API call um from voice flow to make and it's
[02:39:08] um from voice flow to make and it's going to catch it here. And this little
[02:39:09] going to catch it here. And this little lightning bolt means that anything we
[02:39:11] lightning bolt means that anything we build after is going to be triggered
[02:39:13] build after is going to be triggered whenever it receives one of those uh
[02:39:15] whenever it receives one of those uh whenever a new bit of mail arrives. It's
[02:39:17] whenever a new bit of mail arrives. It's going to then trigger this multi-step
[02:39:18] going to then trigger this multi-step process. So we're going to put this into
[02:39:21] process. So we're going to put this into voice flow. We're going to trigger it
[02:39:22] voice flow. We're going to trigger it and make sure it knows what data to
[02:39:24] and make sure it knows what data to expect. And then we're going to be able
[02:39:25] expect. And then we're going to be able to use that data and put it into Google
[02:39:27] to use that data and put it into Google Sheets. So stick with me here, but this
[02:39:29] Sheets. So stick with me here, but this is another very very essential skill in
[02:39:31] is another very very essential skill in AI automation is how to set up a webbook
[02:39:33] AI automation is how to set up a webbook um and use it within different apps. So
[02:39:35] um and use it within different apps. So we have our webbook
[02:39:37] we have our webbook here. We've copied the address to
[02:39:39] here. We've copied the address to clipboard. We're going back setting up a
[02:39:41] clipboard. We're going back setting up a get request here. So it's not a post
[02:39:43] get request here. So it's not a post request this time. We're just uh getting
[02:39:45] request this time. We're just uh getting and we're technically not getting data.
[02:39:47] and we're technically not getting data. A get request is a much more kind of
[02:39:48] A get request is a much more kind of quick and dirty request. Um and as
[02:39:51] quick and dirty request. Um and as you'll see, we kind of just tack on a
[02:39:53] you'll see, we kind of just tack on a bunch of information after this. Um we
[02:39:54] bunch of information after this. Um we can do it through what's called
[02:39:56] can do it through what's called parameters. Here we want to be sending a
[02:39:59] parameters. Here we want to be sending a property. Oh, let's just say
[02:40:01] property. Oh, let's just say property
[02:40:04] property type. Actually, let's do this properly.
[02:40:07] type. Actually, let's do this properly. Let's go time
[02:40:09] Let's go time um
[02:40:11] um timestamp. So, in this Google sheet,
[02:40:14] timestamp. So, in this Google sheet, you're going to want to know when the
[02:40:15] you're going to want to know when the different leads came in. So, we can go
[02:40:16] different leads came in. So, we can go uh time stamp and get the time stamp
[02:40:18] uh time stamp and get the time stamp from voice flow. That's a default
[02:40:20] from voice flow. That's a default variable that they are automatically
[02:40:22] variable that they are automatically filling out for you. So, one of the
[02:40:23] filling out for you. So, one of the things, one of the rows in the
[02:40:25] things, one of the rows in the spreadsheet is going to be uh the time
[02:40:27] spreadsheet is going to be uh the time stamp. We're going to add another and
[02:40:29] stamp. We're going to add another and we're going to go um name. We're going
[02:40:32] we're going to go um name. We're going to put in the name here. So, now all the
[02:40:35] to put in the name here. So, now all the cogs in your head should start turning
[02:40:36] cogs in your head should start turning as we put this together. And we're going
[02:40:38] as we put this together. And we're going to go uh phone number and we go bracket
[02:40:44] to go uh phone number and we go bracket phone number
[02:40:47] phone number number. And if we add another, we can go
[02:40:51] number. And if we add another, we can go property
[02:40:52] property type. Let me go prop property
[02:40:58] type. We can go
[02:41:00] type. We can go property
[02:41:05] size and go property size. We can add
[02:41:10] size and go property size. We can add another one. We can go
[02:41:12] another one. We can go quoted prices so that the sales team
[02:41:15] quoted prices so that the sales team knows what we actually told them. in
[02:41:17] knows what we actually told them. in case you're playing around with pricing.
[02:41:18] case you're playing around with pricing. Um, raw quote data. And I'll probably
[02:41:22] Um, raw quote data. And I'll probably throw in one more here, which is their
[02:41:24] throw in one more here, which is their first question. Um, first question,
[02:41:31] uh, user first reply. So, that might
[02:41:33] uh, user first reply. So, that might give context to the sales team like what
[02:41:34] give context to the sales team like what did they actually contact us for in the
[02:41:36] did they actually contact us for in the first place? Maybe helpful, maybe not.
[02:41:37] first place? Maybe helpful, maybe not. But we can just send this all over to
[02:41:38] But we can just send this all over to the Google sheet.
[02:41:44] And so now we can see this is uh as this
[02:41:47] And so now we can see this is uh as this thing's spinning around, it's basically
[02:41:48] thing's spinning around, it's basically waiting for us to send some data to it.
[02:41:50] waiting for us to send some data to it. It's basically sitting there at the
[02:41:51] It's basically sitting there at the mailbox like waiting for it to come
[02:41:54] mailbox like waiting for it to come through. Um and we can go send here and
[02:41:57] through. Um and we can go send here and I'm going to put in uh gosh dug myself a
[02:42:00] I'm going to put in uh gosh dug myself a hole here. Um let's go name
[02:42:04] hole here. Um let's go name Liam. Um house probably size. Um
[02:42:09] Liam. Um house probably size. Um um lots of money. Um how much for
[02:42:12] um lots of money. Um how much for cleaning yarning?
[02:42:13] cleaning yarning? um send. And if we go back, bam,
[02:42:16] um send. And if we go back, bam, successfully determined. And what we've
[02:42:18] successfully determined. And what we've done and determined means is that make
[02:42:20] done and determined means is that make has received the the the request that we
[02:42:23] has received the the the request that we sent. And it now it knows that we're
[02:42:24] sent. And it now it knows that we're going to be sending it a time stamp and
[02:42:26] going to be sending it a time stamp and a property type and this this really
[02:42:29] a property type and this this really really key skill to understand because
[02:42:30] really key skill to understand because now when I go oh save now when I go to
[02:42:33] now when I go oh save now when I go to here and I go Google Sheets and I go add
[02:42:37] here and I go Google Sheets and I go add a
[02:42:38] a row, um you will need to set up your uh
[02:42:41] row, um you will need to set up your uh Google Sheets connection here. So, you
[02:42:43] Google Sheets connection here. So, you just sign in with Google, add your
[02:42:44] just sign in with Google, add your connection in. Um, I am going to have to
[02:42:49] connection in. Um, I am going to have to create a new spreadsheet for this
[02:42:55] quickly. I'm going go timestamp.
[02:43:00] quickly. I'm going go timestamp. So I'll zoom this up. Time stamp name
[02:43:05] So I'll zoom this up. Time stamp name phone
[02:43:06] phone property type property
[02:43:15] size. 1 2 3 4 5 6 7. Yeah, we've got
[02:43:19] size. 1 2 3 4 5 6 7. Yeah, we've got them all. Right. So then I can
[02:43:22] them all. Right. So then I can go. So call this my Connor cleaning
[02:43:26] go. So call this my Connor cleaning support agent leads.
[02:43:30] support agent leads. So now I want to go back to make and I
[02:43:33] So now I want to go back to make and I want to click here to
[02:43:37] want to click here to um Connor. There we go. Connor's
[02:43:40] um Connor. There we go. Connor's clearing. Why do I keep spelling
[02:43:42] clearing. Why do I keep spelling cleaning
[02:43:47] cleaning? Now we have the spreadsheet
[02:43:49] cleaning? Now we have the spreadsheet set up. The sheet name is just going to
[02:43:51] set up. The sheet name is just going to be sheet one. Sheet one. Does the table
[02:43:54] be sheet one. Sheet one. Does the table contain headers? Yes, it does. And now
[02:43:57] contain headers? Yes, it does. And now we get to put in all of our values. So,
[02:43:58] we get to put in all of our values. So, bam. Time stamp. Pop that in there.
[02:44:01] bam. Time stamp. Pop that in there. Name, pop that in there. Phone, pop that
[02:44:04] Name, pop that in there. Phone, pop that in there. Property type. So, you see
[02:44:08] in there. Property type. So, you see what such a key skill that uh I really,
[02:44:10] what such a key skill that uh I really, really want you guys to learn. Um,
[02:44:12] really want you guys to learn. Um, because this is a lot of like if you
[02:44:14] because this is a lot of like if you just have a couple of these key things
[02:44:15] just have a couple of these key things using these APIs and say voice flow or
[02:44:17] using these APIs and say voice flow or in NAD, building tools and relevance and
[02:44:19] in NAD, building tools and relevance and then using them via API, knowing how to
[02:44:22] then using them via API, knowing how to set up web hooks and then send data in
[02:44:24] set up web hooks and then send data in between them and to set this data
[02:44:25] between them and to set this data structure. You send that first initial
[02:44:27] structure. You send that first initial batch over to make in a test test
[02:44:29] batch over to make in a test test request. It's going to go okay this is
[02:44:31] request. It's going to go okay this is what they're going to send me in future
[02:44:32] what they're going to send me in future and then that's locked in and you can
[02:44:33] and then that's locked in and you can send thousands and thousands of requests
[02:44:35] send thousands and thousands of requests through it and it will operate as you
[02:44:36] through it and it will operate as you expect and first
[02:44:38] expect and first question. So uh it's got all those other
[02:44:41] question. So uh it's got all those other rows we don't need to worry about. Save.
[02:44:43] rows we don't need to worry about. Save. All right. And so that should be
[02:44:44] All right. And so that should be working. We can switch this to
[02:44:46] working. We can switch this to immediately. Oh, I need to save it.
[02:44:49] immediately. Oh, I need to save it. Save. Um I'm going
[02:44:51] Save. Um I'm going to immediately as data arrives. So, this
[02:44:54] to immediately as data arrives. So, this is going to be waiting all the damn
[02:44:55] is going to be waiting all the damn time. Actually, I'm I've got a whole
[02:44:57] time. Actually, I'm I've got a whole bunch of other stuff running in make for
[02:44:58] bunch of other stuff running in make for my my various businesses. So, I'm just
[02:45:00] my my various businesses. So, I'm just going to have this set up. If you wanted
[02:45:01] going to have this set up. If you wanted this to run around the clock, you turn
[02:45:03] this to run around the clock, you turn that on. I'm just going to turn it on to
[02:45:04] that on. I'm just going to turn it on to run once. And this is just going to be
[02:45:06] run once. And this is just going to be sitting there waiting for data. So, what
[02:45:07] sitting there waiting for data. So, what we can do is just finish this off
[02:45:08] we can do is just finish this off quickly. So, I'll just paste this
[02:45:13] quickly. So, I'll just paste this in. Got this all done. Thank you. That's
[02:45:16] in. Got this all done. Thank you. That's the end of it. Um, what we want to do is
[02:45:19] the end of it. Um, what we want to do is have a failure path. So, in case this
[02:45:21] have a failure path. So, in case this fails, we just pop that down there and
[02:45:26] say, "Darn it, something went
[02:45:31] say, "Darn it, something went wrong." I'm going to put that as a
[02:45:36] red. Um, and then this one is like that.
[02:45:40] red. Um, and then this one is like that. All righty. So, if we look at make, it's
[02:45:42] All righty. So, if we look at make, it's still expecting us to send some data to
[02:45:43] still expecting us to send some data to it. Let's hope that we've done all of
[02:45:46] it. Let's hope that we've done all of this right and it's going to work first
[02:45:48] this right and it's going to work first time, but you never really know, dear.
[02:45:50] time, but you never really know, dear. So, let's give this a run and we'll try
[02:45:52] So, let's give this a run and we'll try to go through that second path and we'll
[02:45:54] to go through that second path and we'll try to get that stuff added into the
[02:46:01] spreadsheet. I need weekend cleaning,
[02:46:05] spreadsheet. I need weekend cleaning, please.
[02:46:11] So asking a question is going straight
[02:46:12] So asking a question is going straight to price. You're looking for weekend
[02:46:15] to price. You're looking for weekend cleaning services and want to know the
[02:46:16] cleaning services and want to know the pricing. Is that correct? Yes. So our
[02:46:17] pricing. Is that correct? Yes. So our router is going to pick that up and say
[02:46:19] router is going to pick that up and say he's looking for pricing. Let's send him
[02:46:20] he's looking for pricing. Let's send him to the quote tool. Okay. Sure. To give
[02:46:22] to the quote tool. Okay. Sure. To give you an instant quote, I just need the
[02:46:23] you an instant quote, I just need the property type and size and square feet.
[02:46:24] property type and size and square feet. It's a property. Let's go aart
[02:46:27] It's a property. Let's go aart mint. It's detected that correctly. And
[02:46:30] mint. It's detected that correctly. And how many square feet? It's 500.
[02:46:34] typical
[02:46:37] typical apartment
[02:46:39] apartment size
[02:46:40] size and square
[02:46:44] feet. Okay, so 500 isn't actually
[02:46:47] feet. Okay, so 500 isn't actually ridiculous. Um, great. And then we get
[02:46:49] ridiculous. Um, great. And then we get our answer based on your 500 foot
[02:46:50] our answer based on your 500 foot apartment. Bam, bam, bam. There's all
[02:46:52] apartment. Bam, bam, bam. There's all the prices. Please provide your name and
[02:46:53] the prices. Please provide your name and phone number and I'll get one of the
[02:46:54] phone number and I'll get one of the teams to call you with a time that
[02:46:55] teams to call you with a time that works. Let's uh give this a a test. See
[02:46:58] works. Let's uh give this a a test. See if it's actually picking up on the fail.
[02:47:00] if it's actually picking up on the fail. Sure. My name
[02:47:03] Sure. My name is and
[02:47:05] is and phone
[02:47:11] is boom. Sorry, I didn't quite get that.
[02:47:14] is boom. Sorry, I didn't quite get that. So, it detected that it wasn't right.
[02:47:16] So, it detected that it wasn't right. So, we got the retry output. We got the
[02:47:18] So, we got the retry output. We got the retry output from this, which is what we
[02:47:20] retry output from this, which is what we wanted. Sorry, I didn't quite get that.
[02:47:21] wanted. Sorry, I didn't quite get that. Can you give me again? Um Liam
[02:47:26] Can you give me again? Um Liam Otley number is um 021
[02:47:34] 021. That's what numbers look like here
[02:47:36] 021. That's what numbers look like here in New
[02:47:38] in New Zealand. Okay. Just to confirm quickly,
[02:47:40] Zealand. Okay. Just to confirm quickly, your name is Liam Mley and your phone
[02:47:41] your name is Liam Mley and your phone number is that correct? Yes, sir. Name
[02:47:45] number is that correct? Yes, sir. Name and phone
[02:47:47] number. Oh, what has it done
[02:47:50] number. Oh, what has it done there? Oh, dame.
[02:47:53] there? Oh, dame. I don't know why it's I just want the
[02:47:56] I don't know why it's I just want the phone number. So, we have got a little
[02:47:57] phone number. So, we have got a little bit of an error there. I just go back
[02:47:58] bit of an error there. I just go back and tweak the prompt. Make sure it's
[02:48:00] and tweak the prompt. Make sure it's like only get the phone number. We don't
[02:48:01] like only get the phone number. We don't want anything apart from numbers here.
[02:48:03] want anything apart from numbers here. Great. Let me get the added to the
[02:48:04] Great. Let me get the added to the system. And then if we go back to make,
[02:48:06] system. And then if we go back to make, we see these are all green now. And we
[02:48:07] we see these are all green now. And we see these dots. So, this is the
[02:48:09] see these dots. So, this is the information that came through. Namely,
[02:48:10] information that came through. Namely, Mly phone number. And so, here's the
[02:48:12] Mly phone number. And so, here's the little mistake where we had a new line.
[02:48:14] little mistake where we had a new line. Apartment. Bam, bam, bam. All of that
[02:48:16] Apartment. Bam, bam, bam. All of that information. And then it's added it into
[02:48:18] information. And then it's added it into Google Sheets. Here we see updates,
[02:48:21] Google Sheets. Here we see updates, updated number of rows, all the values
[02:48:22] updated number of rows, all the values that it's updated and we can go
[02:48:28] to. Okay. Holy moly. Right. We're ready
[02:48:32] to. Okay. Holy moly. Right. We're ready to put this thing on our website and to
[02:48:34] to put this thing on our website and to also put it on a phone number. So, let's
[02:48:36] also put it on a phone number. So, let's just finish the job. Guys, I'm uh
[02:48:38] just finish the job. Guys, I'm uh getting real hungry, but we can uh we
[02:48:40] getting real hungry, but we can uh we can push through. So, I will just turn
[02:48:42] can push through. So, I will just turn this on actually so that if we are
[02:48:44] this on actually so that if we are testing it on the web and over the
[02:48:45] testing it on the web and over the phone, um it's ready to receive. Um, if
[02:48:49] phone, um it's ready to receive. Um, if we do want to be pedantic, I would go
[02:48:51] we do want to be pedantic, I would go back and I would change I have to do it.
[02:48:54] back and I would change I have to do it. It's going to piss me
[02:48:56] It's going to piss me off. I'll put their name. Oh, that's
[02:48:59] off. I'll put their name. Oh, that's why. I'll put their phone number only.
[02:49:02] why. I'll put their phone number only. My bad. I'll put their phone number
[02:49:11] only. And we do have these fail points
[02:49:14] only. And we do have these fail points here. Um, I'm not going to bother
[02:49:16] here. Um, I'm not going to bother filling them out. I think you guys can
[02:49:17] filling them out. I think you guys can figure out based off how I've handled
[02:49:19] figure out based off how I've handled this, how you can handle these as well.
[02:49:21] this, how you can handle these as well. So, what you'll find is when you're
[02:49:22] So, what you'll find is when you're building these, these kind of fail like
[02:49:24] building these, these kind of fail like error handling um is kind of a an
[02:49:27] error handling um is kind of a an endless thread that you keep pulling.
[02:49:28] endless thread that you keep pulling. It's like, oh, well, now I've got to
[02:49:29] It's like, oh, well, now I've got to handle this, this, and this this. So, um
[02:49:31] handle this, this, and this this. So, um I'm not going to this is a prototype.
[02:49:33] I'm not going to this is a prototype. I'm not going to be doing all of the the
[02:49:34] I'm not going to be doing all of the the error handling for you here. In the
[02:49:36] error handling for you here. In the template, there is actually a little bit
[02:49:37] template, there is actually a little bit more of it. Um some better examples. So,
[02:49:39] more of it. Um some better examples. So, maybe if you import that, you can just
[02:49:40] maybe if you import that, you can just steal the work that I've done there. But
[02:49:43] steal the work that I've done there. But what we need to do now is we can publish
[02:49:45] what we need to do now is we can publish this thing. We'll call it
[02:49:48] this thing. We'll call it V1 first
[02:50:00] drop. All right. So now it's published.
[02:50:03] drop. All right. So now it's published. We can add the agent to a website. Let's
[02:50:04] We can add the agent to a website. Let's click on that. And that takes us to this
[02:50:06] click on that. And that takes us to this integrations tab.
[02:50:08] integrations tab. Um let's put this down. I don't need to
[02:50:10] Um let's put this down. I don't need to see that. Um, they've got a new version
[02:50:13] see that. Um, they've got a new version of it. That's good to know. I said
[02:50:15] of it. That's good to know. I said installation is pretty straightforward.
[02:50:16] installation is pretty straightforward. So, we can just click copy here. And
[02:50:18] So, we can just click copy here. And then I'm going to open
[02:50:21] up I'm going to open up brackets here
[02:50:24] up I'm going to open up brackets here just to give you a demo of a website. I
[02:50:26] just to give you a demo of a website. I use this in all my tutorials. It's
[02:50:27] use this in all my tutorials. It's really easy to spin up. Um, I will leave
[02:50:29] really easy to spin up. Um, I will leave a link to this template if you want it.
[02:50:31] a link to this template if you want it. Um, and also some instructions on how
[02:50:32] Um, and also some instructions on how you can open up a website. I know this
[02:50:34] you can open up a website. I know this looks like code and it's all scary, but
[02:50:36] looks like code and it's all scary, but um, this is just allowing me to spin up
[02:50:38] um, this is just allowing me to spin up a website very quickly. So, I'll leave
[02:50:40] a website very quickly. So, I'll leave the template file. All you need to do is
[02:50:42] the template file. All you need to do is once you've downloaded the template
[02:50:43] once you've downloaded the template file, you need to download brackets,
[02:50:46] file, you need to download brackets, which is the software. You can go file,
[02:50:48] which is the software. You can go file, then open folder, and then you want to
[02:50:50] then open folder, and then you want to click on the folder when you've unzipped
[02:50:52] click on the folder when you've unzipped it, and it's going to open up the whole
[02:50:53] it, and it's going to open up the whole folder. And then you'll get all of this
[02:50:55] folder. And then you'll get all of this uh opened up like this. And you see all
[02:50:57] uh opened up like this. And you see all of these files ra. All you need to do is
[02:50:59] of these files ra. All you need to do is click on the
[02:51:00] click on the index.html. And then you'll see
[02:51:02] index.html. And then you'll see something similar to this. Well, I'm
[02:51:04] something similar to this. Well, I'm going to scroll down to the bottom of
[02:51:05] going to scroll down to the bottom of the index.html. I'm going to delete this
[02:51:07] the index.html. I'm going to delete this old voice agent I was testing on here.
[02:51:10] old voice agent I was testing on here. Drop this in here. Paste that. And then
[02:51:12] Drop this in here. Paste that. And then save it. Command S. Click this little
[02:51:14] save it. Command S. Click this little button up here. And it will show us a
[02:51:18] button up here. And it will show us a local version of the website running on
[02:51:20] local version of the website running on our computer here through brackets. So
[02:51:22] our computer here through brackets. So here's my man with a magnificent
[02:51:24] here's my man with a magnificent beard.
[02:51:26] beard. And we have the tester agent bubble down
[02:51:30] And we have the tester agent bubble down here. And there we go.
[02:51:36] I want to know where you
[02:51:40] I want to know where you live, my
[02:51:44] guy.
[02:51:49] Yep. Woo. Okay. Uh I didn't even program
[02:51:53] Yep. Woo. Okay. Uh I didn't even program that in there. Maybe you just thought it
[02:51:54] that in there. Maybe you just thought it was inappropriate. Um but we've got it
[02:51:57] was inappropriate. Um but we've got it working on a website. Now, if we pop
[02:51:58] working on a website. Now, if we pop back over to um uh Voice Flow here and
[02:52:02] back over to um uh Voice Flow here and you go to the integrations, the widget,
[02:52:04] you go to the integrations, the widget, you see we've got this test your agent
[02:52:05] you see we've got this test your agent thing. So, down here, we can play around
[02:52:07] thing. So, down here, we can play around with the look and feel of it. I'm not
[02:52:09] with the look and feel of it. I'm not really going to get into this here.
[02:52:10] really going to get into this here. There's quite a lot to play around with,
[02:52:11] There's quite a lot to play around with, but basically all of what you see on
[02:52:14] but basically all of what you see on here can be changed around. Different
[02:52:16] here can be changed around. Different logos, different text here, different
[02:52:18] logos, different text here, different icon, etc., different colors, and you
[02:52:20] icon, etc., different colors, and you can just make it look and feel however
[02:52:22] can just make it look and feel however you want it to. So, I'm sure you guys
[02:52:24] you want it to. So, I'm sure you guys are big enough and ugly enough to figure
[02:52:25] are big enough and ugly enough to figure that out yourself. we'd probably want to
[02:52:27] that out yourself. we'd probably want to switch over to uh this here. One thing
[02:52:29] switch over to uh this here. One thing you would want to do is turn off powered
[02:52:30] you would want to do is turn off powered by voice flow so it's not uh sending
[02:52:33] by voice flow so it's not uh sending traffic to them when it's on your own
[02:52:34] traffic to them when it's on your own website. And that's about it. For the
[02:52:36] website. And that's about it. For the sake of time, I'm not going to go
[02:52:37] sake of time, I'm not going to go through the entire flow again here. Just
[02:52:40] through the entire flow again here. Just know that the functionality that we
[02:52:41] know that the functionality that we built that I just showed you in the
[02:52:42] built that I just showed you in the builder is going to work cuz we just
[02:52:43] builder is going to work cuz we just deployed it. Like this is exactly what
[02:52:45] deployed it. Like this is exactly what we're interacting with. So, it's all
[02:52:47] we're interacting with. So, it's all working here. The only step to do now is
[02:52:49] working here. The only step to do now is to put it on this phone number so we can
[02:52:51] to put it on this phone number so we can have a chat to it over the phone, which
[02:52:52] have a chat to it over the phone, which we're going to do now. To do that, we
[02:52:53] we're going to do now. To do that, we need to go to the telefan bit here. It
[02:52:55] need to go to the telefan bit here. It is in beta right now, but for most of
[02:52:56] is in beta right now, but for most of you watching it is not going to be by
[02:52:58] you watching it is not going to be by the time you you are watching this. So,
[02:52:59] the time you you are watching this. So, we need to set up a phone number from
[02:53:01] we need to set up a phone number from Twilio, import it, and then connect our
[02:53:03] Twilio, import it, and then connect our agent and its functionality to that. So,
[02:53:04] agent and its functionality to that. So, we can go import number. You'll see that
[02:53:07] we can go import number. You'll see that we have this information here. So, we
[02:53:08] we have this information here. So, we can use Twilio or Vonnage. Twilio is
[02:53:10] can use Twilio or Vonnage. Twilio is usually the go-to here. So, if we click
[02:53:12] usually the go-to here. So, if we click on learn more, then they're going to
[02:53:14] on learn more, then they're going to help us. Basically, the best way to make
[02:53:15] help us. Basically, the best way to make sure you're getting the most up-to-date
[02:53:16] sure you're getting the most up-to-date information is go to the docs of the
[02:53:18] information is go to the docs of the platform. Finding and reading and
[02:53:19] platform. Finding and reading and extracting information from
[02:53:20] extracting information from documentation on these kinds of
[02:53:22] documentation on these kinds of platforms is another key skill that you
[02:53:24] platforms is another key skill that you need to pick up to succeed in the space.
[02:53:25] need to pick up to succeed in the space. So if we go to the docs here, we go to
[02:53:29] So if we go to the docs here, we go to um voice phone number setting up Twilio
[02:53:34] um voice phone number setting up Twilio integration and they have a video here
[02:53:36] integration and they have a video here adding a phone number to your agent. So
[02:53:37] adding a phone number to your agent. So if you ever get stuck, you know, you've
[02:53:38] if you ever get stuck, you know, you've got documentation here and for all of
[02:53:40] got documentation here and for all of the other platforms, but they'll keep
[02:53:41] the other platforms, but they'll keep updating these videos if things change,
[02:53:43] updating these videos if things change, which they likely will as this voice AI
[02:53:45] which they likely will as this voice AI space really takes off. So, if we go to
[02:53:48] space really takes off. So, if we go to Twilio, you will need to sign up and
[02:53:50] Twilio, you will need to sign up and create an account on
[02:54:04] Twilio. All right, so we are logged into
[02:54:06] Twilio. All right, so we are logged into Twilio. You'll need to create an account
[02:54:08] Twilio. You'll need to create an account for most of you, but Twilio is a uh
[02:54:10] for most of you, but Twilio is a uh phone number provider that you can
[02:54:11] phone number provider that you can connect to and interact with over the
[02:54:13] connect to and interact with over the internet. super helpful when you can buy
[02:54:14] internet. super helpful when you can buy lots of numbers from different locations
[02:54:16] lots of numbers from different locations and stuff. When it comes to phone
[02:54:18] and stuff. When it comes to phone numbers, it can there's a lot of rules
[02:54:19] numbers, it can there's a lot of rules and regulations around different like it
[02:54:21] and regulations around different like it varies a lot from country to country. So
[02:54:23] varies a lot from country to country. So depending like if you're in Germany, I
[02:54:24] depending like if you're in Germany, I believe in order to get a German phone
[02:54:26] believe in order to get a German phone number, you need to have a company
[02:54:27] number, you need to have a company registered and get the number through
[02:54:29] registered and get the number through your company registration and provide
[02:54:31] your company registration and provide those details. So can be difficult. I'm
[02:54:33] those details. So can be difficult. I'm just going to show you how to use a uh a
[02:54:34] just going to show you how to use a uh a US-based number here. So we can go over
[02:54:36] US-based number here. So we can go over to the phone numbers on the left here.
[02:54:38] to the phone numbers on the left here. There may be some setup that Twilio walk
[02:54:40] There may be some setup that Twilio walk you through. It can be kind of annoying
[02:54:41] you through. It can be kind of annoying sometimes. They say you need to do all
[02:54:43] sometimes. They say you need to do all of these declarations and forms and
[02:54:45] of these declarations and forms and stuff, but for the most part, it should
[02:54:46] stuff, but for the most part, it should be fairly straightforward if you follow
[02:54:48] be fairly straightforward if you follow their setup instructions when you create
[02:54:49] their setup instructions when you create your account to then come over and go to
[02:54:51] your account to then come over and go to your phone numbers and manage and go to
[02:54:54] your phone numbers and manage and go to buy a
[02:54:56] buy a number. Now, unless you have other
[02:54:57] number. Now, unless you have other purposes you want to use this for, you
[02:54:59] purposes you want to use this for, you can just snag any random one if you're
[02:55:00] can just snag any random one if you're following this tutorial. Um, if you're
[02:55:02] following this tutorial. Um, if you're obviously doing this for a client, you
[02:55:03] obviously doing this for a client, you could get one that's matched to their
[02:55:04] could get one that's matched to their location or their their state or even
[02:55:06] location or their their state or even their city. And when you click buy, you
[02:55:08] their city. And when you click buy, you can see there's all these kind of
[02:55:09] can see there's all these kind of registrations and RAR you need to do.
[02:55:11] registrations and RAR you need to do. But thankfully, voice is uh is ones that
[02:55:14] But thankfully, voice is uh is ones that don't need all of that. And you've got
[02:55:15] don't need all of that. And you've got global routing, etc. So, you can come
[02:55:17] global routing, etc. So, you can come down here and buy this. It's going to be
[02:55:18] down here and buy this. It's going to be a dollar a month. I know cost of
[02:55:20] a dollar a month. I know cost of starting up a business is ridiculous
[02:55:21] starting up a business is ridiculous these
[02:55:22] these days. How dare they? But just to walk
[02:55:25] days. How dare they? But just to walk things through and do it with you, I'm
[02:55:26] things through and do it with you, I'm going to buy this number even though I
[02:55:27] going to buy this number even though I really don't need
[02:55:29] really don't need it. There we go. I've got my number. I'm
[02:55:33] it. There we go. I've got my number. I'm just going to copy this so I don't
[02:55:35] just going to copy this so I don't forget it. 517. And then I go to active
[02:55:39] forget it. 517. And then I go to active numbers. I got my guy. Where is he? 517
[02:55:43] numbers. I got my guy. Where is he? 517 down
[02:55:44] down here. Copy this bad boy. Go back to
[02:55:46] here. Copy this bad boy. Go back to Twilio. Put our number in here. Our
[02:55:49] Twilio. Put our number in here. Our Twilio account SID. You need to pop back
[02:55:51] Twilio account SID. You need to pop back to Twilio. You go to your account
[02:55:54] to Twilio. You go to your account dashboard. This was a bit confusing when
[02:55:56] dashboard. This was a bit confusing when I first did it. So, I'm glad I'm glad I
[02:55:58] I first did it. So, I'm glad I'm glad I can help you guys through it because it
[02:55:59] can help you guys through it because it was a bit of a pain in the bum for me.
[02:56:01] was a bit of a pain in the bum for me. You think all this information is going
[02:56:02] You think all this information is going to be like tucked away in the side
[02:56:04] to be like tucked away in the side panels, but no, it's just on the
[02:56:05] panels, but no, it's just on the dashboard. Who the hell puts your or
[02:56:07] dashboard. Who the hell puts your or tokens and stuff on a dashboard? I mean,
[02:56:09] tokens and stuff on a dashboard? I mean, it's when you know it's there, it's
[02:56:10] it's when you know it's there, it's helpful, but it was a bit confusing at
[02:56:11] helpful, but it was a bit confusing at the time for me. Um, I'm going to paste
[02:56:15] the time for me. Um, I'm going to paste this in
[02:56:18] here. We're going to copy this or token
[02:56:22] here. We're going to copy this or token and paste this in here. And we're going
[02:56:24] and paste this in here. And we're going to say this is my you YouTube tutorial.
[02:56:29] to say this is my you YouTube tutorial. And I'm going to import that bad boy.
[02:56:31] And I'm going to import that bad boy. Select environment. I'm just going to
[02:56:33] Select environment. I'm just going to put it on development for now. uh we can
[02:56:35] put it on development for now. uh we can assign
[02:56:36] assign that. And with that, you can see if I
[02:56:38] that. And with that, you can see if I click unassign here, that means I'm
[02:56:39] click unassign here, that means I'm going to take it off. So, it's it's
[02:56:40] going to take it off. So, it's it's assigned and it should be ready to have
[02:56:42] assigned and it should be ready to have a chat with. So, if I click to copy this
[02:56:44] a chat with. So, if I click to copy this number here, I go back to my little
[02:56:47] number here, I go back to my little uh uh website code here. If I go find um
[02:56:52] uh uh website code here. If I go find um plus one. Oh, there we go. So, we have
[02:56:54] plus one. Oh, there we go. So, we have the call. Um this is in the header. Uh
[02:56:58] the call. Um this is in the header. Uh this is just me p wanting to put it on
[02:56:59] this is just me p wanting to put it on the site for you guys. So, you guys
[02:57:01] the site for you guys. So, you guys don't necessarily need to copy this. I'm
[02:57:03] don't necessarily need to copy this. I'm going to save that. If I go back to my
[02:57:05] going to save that. If I go back to my website here, now I have the actual
[02:57:06] website here, now I have the actual phone number. And if I pull up Skype on
[02:57:10] phone number. And if I pull up Skype on my phone, you guys, if you're in the US,
[02:57:12] my phone, you guys, if you're in the US, you can just or wherever your number is
[02:57:13] you can just or wherever your number is based, you can just call it stage plus
[02:57:17] based, you can just call it stage plus one. All right, let's give our mate a
[02:57:20] one. All right, let's give our mate a ring.
[02:57:24] Welcome to Conor's Cleaning. How can I
[02:57:25] Welcome to Conor's Cleaning. How can I help? Hey, uh, I was just wondering, uh,
[02:57:28] help? Hey, uh, I was just wondering, uh, where you guys are located.
[02:57:38] business. Is that correct? Yeah, that's
[02:57:41] business. Is that correct? Yeah, that's correct.
[02:57:49] We're located at 247 Beacon Street in
[02:57:52] We're located at 247 Beacon Street in Boston, Massachusetts 0216. We serve the
[02:57:55] Boston, Massachusetts 0216. We serve the greater Boston area, including
[02:57:57] greater Boston area, including neighborhoods like downtown Boston,
[02:57:58] neighborhoods like downtown Boston, Cambridge, Somerville, Brooklyn, and
[02:58:00] Cambridge, Somerville, Brooklyn, and several others. Is there anything else I
[02:58:03] several others. Is there anything else I can help you with today? Sweet. Okay, so
[02:58:05] can help you with today? Sweet. Okay, so that's done the
[02:58:07] that's done the uh knowledge the knowledgebased route.
[02:58:10] uh knowledge the knowledgebased route. Now, let's give it another spin. Call
[02:58:12] Now, let's give it another spin. Call him again. Okay.
[02:58:15] Hey, welcome to Connor's Cleaning. How
[02:58:17] Hey, welcome to Connor's Cleaning. How can I help? Hi there. I'm just getting
[02:58:20] can I help? Hi there. I'm just getting interested in getting uh some cleaning
[02:58:22] interested in getting uh some cleaning for my place on the weekends.
[02:58:29] It sounds like you're interested in
[02:58:30] It sounds like you're interested in booking a cleaning service for a
[02:58:32] booking a cleaning service for a licensed weekend. Is that correct? Yep.
[02:58:41] Okay. Sure. To give you an instant
[02:58:43] Okay. Sure. To give you an instant quote. I just need the property type and
[02:58:45] quote. I just need the property type and size and square feet. Is the property a
[02:58:47] size and square feet. Is the property a house or an apartment? It's a house.
[02:58:56] Sorry, I didn't get that. Is it a house
[02:58:58] Sorry, I didn't get that. Is it a house or an apartment? It is a house, a home.
[02:59:06] And how many square feet is it? It's
[02:59:08] And how many square feet is it? It's about a thousand.
[02:59:15] One sec while I generate your quote.
[02:59:18] One sec while I generate your quote. Based on your requirements, we can offer
[02:59:20] Based on your requirements, we can offer four different packages. Regular
[02:59:22] four different packages. Regular maintenance cleaning at $90, which
[02:59:24] maintenance cleaning at $90, which covers standard weekly or bi-weekly
[02:59:26] covers standard weekly or bi-weekly cleaning. Deep cleaning at $150 for a
[02:59:30] cleaning. Deep cleaning at $150 for a more thorough top to bottom refresh,
[02:59:32] more thorough top to bottom refresh, move in, move out. Cleaning at $170 for
[02:59:36] move in, move out. Cleaning at $170 for preparing or cleaning after a home
[02:59:38] preparing or cleaning after a home transition, and post renovation cleaning
[02:59:40] transition, and post renovation cleaning at $200 for handling construction dust
[02:59:43] at $200 for handling construction dust and debris. Please provide your name and
[02:59:45] and debris. Please provide your name and phone number and I'll get one of the
[02:59:46] phone number and I'll get one of the team to call you to find a time that
[02:59:48] team to call you to find a time that works. Sure. My name is Liam Otsley and
[02:59:51] works. Sure. My name is Liam Otsley and my phone number is 021 uh 1111 9792.
[03:00:03] Okay, just to quickly confirm, your name
[03:00:05] Okay, just to quickly confirm, your name is Liam Oxley and your phone number is
[03:00:08] is Liam Oxley and your phone number is 02119792. Is that correct? Yep, that's
[03:00:11] 02119792. Is that correct? Yep, that's spot on.
[03:00:19] Great. Let me get that added into our
[03:00:20] Great. Let me get that added into our system. All done. Thank you.
[03:00:24] system. All done. Thank you. Boom. All
[03:00:27] Boom. All righty. That is done. That is dunzos.
[03:00:30] righty. That is done. That is dunzos. All right. So, you guys learned a lot in
[03:00:32] All right. So, you guys learned a lot in that one. voice integration, website
[03:00:34] that one. voice integration, website integration, um connecting web hooks to
[03:00:37] integration, um connecting web hooks to make, setting up make automations,
[03:00:39] make, setting up make automations, sending data over, connecting relevance
[03:00:41] sending data over, connecting relevance AI tools into into voice flow. Um basic
[03:00:46] AI tools into into voice flow. Um basic integration with a CRM, in this case,
[03:00:47] integration with a CRM, in this case, it's a sheet, but there's so much in
[03:00:49] it's a sheet, but there's so much in there, guys. I hope you really really uh
[03:00:50] there, guys. I hope you really really uh learned a lot from that. This has been a
[03:00:52] learned a lot from that. This has been a big one. And we've still got uh one more
[03:00:54] big one. And we've still got uh one more to go. So, I hope you're sticking with
[03:00:56] to go. So, I hope you're sticking with us. Um but going back to our Figma here,
[03:01:00] us. Um but going back to our Figma here, um we have ticked off all of this. So,
[03:01:01] um we have ticked off all of this. So, we have it as a web chat widget and we
[03:01:03] we have it as a web chat widget and we have it as a a phone number. Now, as far
[03:01:05] have it as a a phone number. Now, as far as I know, you can have both options for
[03:01:06] as I know, you can have both options for the same agent on voice. You can have it
[03:01:08] the same agent on voice. You can have it on the website and over voice. You don't
[03:01:10] on the website and over voice. You don't need to duplicate it and sort of define
[03:01:11] need to duplicate it and sort of define what modality it's going to be. So,
[03:01:14] what modality it's going to be. So, we've ticked off all the boxes for this.
[03:01:15] we've ticked off all the boxes for this. All of the resources will be in here.
[03:01:17] All of the resources will be in here. All of the prompts, a template for that
[03:01:18] All of the prompts, a template for that whole final build as well. If you just
[03:01:20] whole final build as well. If you just want to snag all my hard work and go and
[03:01:21] want to snag all my hard work and go and sell it to someone, again, I don't I
[03:01:23] sell it to someone, again, I don't I really don't care. Um, that's what these
[03:01:24] really don't care. Um, that's what these videos are for. And we're getting into
[03:01:26] videos are for. And we're getting into agent build number four now.
[03:01:33] All righty. So, last but not least is an
[03:01:36] All righty. So, last but not least is an agent built on my own software. So, I
[03:01:38] agent built on my own software. So, I didn't want to make this. It's not about
[03:01:39] didn't want to make this. It's not about me selling you or getting you to use my
[03:01:41] me selling you or getting you to use my software. So, I thought I'd put it at
[03:01:42] software. So, I thought I'd put it at the end just so you know that I wasn't
[03:01:43] the end just so you know that I wasn't really This is about you guys learning
[03:01:45] really This is about you guys learning and my software happens to help you put
[03:01:47] and my software happens to help you put an agent onto WhatsApp very very easily.
[03:01:49] an agent onto WhatsApp very very easily. So, that's why it's included in here.
[03:01:50] So, that's why it's included in here. But again, this is nonsponsored,
[03:01:52] But again, this is nonsponsored, nonpromoted, non whatever. I'm just
[03:01:54] nonpromoted, non whatever. I'm just really trying to share with you what I
[03:01:55] really trying to share with you what I think is a really valuable skill set to
[03:01:57] think is a really valuable skill set to have. All right. Now getting into AI
[03:01:58] have. All right. Now getting into AI agent build number four. This is going
[03:02:00] agent build number four. This is going to be tada a WhatsApp based ARI customer
[03:02:04] to be tada a WhatsApp based ARI customer support and lead generation agent built
[03:02:06] support and lead generation agent built on agentive my software. So this is a
[03:02:09] on agentive my software. So this is a noode uh AI agent builder that is built
[03:02:11] noode uh AI agent builder that is built on top of OpenAI's assistance API. So
[03:02:13] on top of OpenAI's assistance API. So you're technically using your OpenAI
[03:02:15] you're technically using your OpenAI account getting very very cheap rates on
[03:02:17] account getting very very cheap rates on the uh token usage that you're running
[03:02:19] the uh token usage that you're running through this agent. But Agent just
[03:02:21] through this agent. But Agent just allows you to build on top of it very
[03:02:22] allows you to build on top of it very easily. but more importantly to deploy
[03:02:24] easily. but more importantly to deploy these agents not just onto web chat
[03:02:26] these agents not just onto web chat widgets like we've done with voice flow
[03:02:27] widgets like we've done with voice flow but easily onto things like WhatsApp and
[03:02:30] but easily onto things like WhatsApp and Instagram etc. So that's really the key
[03:02:31] Instagram etc. So that's really the key thing that Agenda focuses on doing right
[03:02:33] thing that Agenda focuses on doing right now is making it easy for you to get
[03:02:35] now is making it easy for you to get your agents onto these platforms. So as
[03:02:36] your agents onto these platforms. So as you can see it's a fairly similar build
[03:02:38] you can see it's a fairly similar build to what we just did on voice flow in
[03:02:39] to what we just did on voice flow in terms of functionality. We're going to
[03:02:40] terms of functionality. We're going to be having a uh a knowledge base that we
[03:02:43] be having a uh a knowledge base that we can ask questions over. It's going to be
[03:02:45] can ask questions over. It's going to be able to generate another instant quote.
[03:02:46] able to generate another instant quote. So we'll just quickly connect that same
[03:02:48] So we'll just quickly connect that same relevance tool here. And finally, we're
[03:02:50] relevance tool here. And finally, we're going to do a lead capture, but this
[03:02:51] going to do a lead capture, but this time it's going to be done through Air
[03:02:52] time it's going to be done through Air Table. So, I want to mix it up and show
[03:02:54] Table. So, I want to mix it up and show you how you can connect your agents to
[03:02:55] you how you can connect your agents to Air Table, which is a very, very common
[03:02:57] Air Table, which is a very, very common integration that you're going to need to
[03:02:58] integration that you're going to need to know. And the difference between this
[03:03:00] know. And the difference between this agent, you're going to see that it's
[03:03:01] agent, you're going to see that it's much much faster to build. This is not
[03:03:02] much much faster to build. This is not meant to be a side-by-side comparison of
[03:03:05] meant to be a side-by-side comparison of what's better, how much faster. It's
[03:03:06] what's better, how much faster. It's just that when you build on a more
[03:03:08] just that when you build on a more conversationalbased uh AI agent platform
[03:03:11] conversationalbased uh AI agent platform like agentive which is built on top of
[03:03:12] like agentive which is built on top of the assistance API, it's a very
[03:03:14] the assistance API, it's a very different way of building agents because
[03:03:15] different way of building agents because it's all just based on a prompt and
[03:03:17] it's all just based on a prompt and providing the right tools and all the
[03:03:18] providing the right tools and all the magic kind of happens itself through the
[03:03:20] magic kind of happens itself through the prompt. Whereas voice flow gives you a
[03:03:22] prompt. Whereas voice flow gives you a lot more control. So it's really
[03:03:23] lot more control. So it's really difference between structured AI agent
[03:03:25] difference between structured AI agent building versus more conversational and
[03:03:27] building versus more conversational and open-ended chats through more chat GBT
[03:03:30] open-ended chats through more chat GBT like experience that can just go on and
[03:03:31] like experience that can just go on and on and on which is what these agents can
[03:03:33] on and on which is what these agents can do. So the purpose is of course fairly
[03:03:35] do. So the purpose is of course fairly similar but the value of this is
[03:03:36] similar but the value of this is slightly different in that we are using
[03:03:38] slightly different in that we are using WhatsApp. So uh many people browsing for
[03:03:40] WhatsApp. So uh many people browsing for services online are hesitant to use
[03:03:42] services online are hesitant to use website contact forms or other or chat
[03:03:44] website contact forms or other or chat bots that they think are not going to
[03:03:45] bots that they think are not going to give them access to a real human due to
[03:03:47] give them access to a real human due to the potential delays that come from it.
[03:03:48] the potential delays that come from it. Right? You land in a website and you're
[03:03:50] Right? You land in a website and you're you're shopping around for a different
[03:03:51] you're shopping around for a different service or product and then there's this
[03:03:53] service or product and then there's this this contact form or there's a a web
[03:03:55] this contact form or there's a a web chat widget and you're going to go well
[03:03:56] chat widget and you're going to go well I don't really think I'm going to get
[03:03:57] I don't really think I'm going to get the help that I really need here at the
[03:03:58] the help that I really need here at the at the speed that I want. So you might
[03:04:00] at the speed that I want. So you might look for a WhatsApp widget and you know
[03:04:02] look for a WhatsApp widget and you know that if you click that WhatsApp widget
[03:04:03] that if you click that WhatsApp widget you're going to get to speak directly to
[03:04:04] you're going to get to speak directly to someone and this is kind of playing on
[03:04:06] someone and this is kind of playing on that fact that if you have the WhatsApp
[03:04:08] that fact that if you have the WhatsApp option on your uh website people are
[03:04:10] option on your uh website people are much more likely to just click that and
[03:04:11] much more likely to just click that and go through and try to have a
[03:04:12] go through and try to have a conversation directly to get what they
[03:04:14] conversation directly to get what they want. So by having a WhatsApp option on
[03:04:16] want. So by having a WhatsApp option on a website or other triggers eg you can
[03:04:18] a website or other triggers eg you can have a QR code that you could stick on
[03:04:20] have a QR code that you could stick on say a real estate sign and you build an
[03:04:21] say a real estate sign and you build an agent connect it to your WhatsApp number
[03:04:23] agent connect it to your WhatsApp number like we're going to do here and then you
[03:04:24] like we're going to do here and then you create a QR code that people can scan
[03:04:26] create a QR code that people can scan and immediately open WhatsApp and start
[03:04:28] and immediately open WhatsApp and start chatting with it. There's lots of
[03:04:29] chatting with it. There's lots of different ways that you can have an
[03:04:30] different ways that you can have an access point into a WhatsApp agent like
[03:04:32] access point into a WhatsApp agent like this. But it basically opens up more
[03:04:34] this. But it basically opens up more conversations through a more smartphone
[03:04:36] conversations through a more smartphone native platform. So they can hop on
[03:04:38] native platform. So they can hop on their phone and sort of have a chat away
[03:04:39] their phone and sort of have a chat away to it rather than being on a website on
[03:04:40] to it rather than being on a website on the computer or a little tiny website
[03:04:42] the computer or a little tiny website chatbot on their phone. Um, in order to
[03:04:45] chatbot on their phone. Um, in order to essentially engage more prospects or
[03:04:47] essentially engage more prospects or more people interested in the business
[03:04:48] more people interested in the business in conversation, quickly provide value
[03:04:51] in conversation, quickly provide value through either the knowledge base and
[03:04:52] through either the knowledge base and these tools here and real-time quotes.
[03:04:54] these tools here and real-time quotes. And ultimately, because you're providing
[03:04:56] And ultimately, because you're providing that instant value and instant feedback
[03:04:57] that instant value and instant feedback from them, collect their lead
[03:04:59] from them, collect their lead information, or better yet, even set
[03:05:01] information, or better yet, even set appointments through WhatsApp, which you
[03:05:02] appointments through WhatsApp, which you can build on agenda. But that use case
[03:05:04] can build on agenda. But that use case is a little bit more advanced and not
[03:05:05] is a little bit more advanced and not something I can show within this video,
[03:05:07] something I can show within this video, but it definitely is possible. But it's
[03:05:08] but it definitely is possible. But it's really only a few steps away from the
[03:05:10] really only a few steps away from the skills that you've learned in this video
[03:05:11] skills that you've learned in this video so far. So keep an eye on that
[03:05:12] so far. So keep an eye on that appointment setting use case because if
[03:05:14] appointment setting use case because if you can do that with AI agent, it's a
[03:05:16] you can do that with AI agent, it's a very, very valuable one. And I've done
[03:05:17] very, very valuable one. And I've done other videos on the channel here showing
[03:05:19] other videos on the channel here showing you how to do that. So, the usage of
[03:05:20] you how to do that. So, the usage of this is that they're going to find the
[03:05:22] this is that they're going to find the uh company's WhatsApp number on their
[03:05:24] uh company's WhatsApp number on their website or elsewhere, maybe a QR code
[03:05:26] website or elsewhere, maybe a QR code like I said, and they're going to start
[03:05:27] like I said, and they're going to start a conversation on WhatsApp, and then the
[03:05:29] a conversation on WhatsApp, and then the agent is immediately going to jump in
[03:05:30] agent is immediately going to jump in and start responding and be able to
[03:05:31] and start responding and be able to answer from the knowledge base, generate
[03:05:33] answer from the knowledge base, generate quotes, and then capture their lead
[03:05:34] quotes, and then capture their lead information. So, without further ado,
[03:05:36] information. So, without further ado, let's jump into building this agent. So,
[03:05:37] let's jump into building this agent. So, we can click up here to go to my
[03:05:39] we can click up here to go to my website, Agentive. You can click on
[03:05:41] website, Agentive. You can click on register now. You can just register with
[03:05:42] register now. You can just register with your Google account. I'm going to log in
[03:05:44] your Google account. I'm going to log in with mine.
[03:05:48] It is free to make an account and we
[03:05:50] It is free to make an account and we have a free plan so you can just
[03:05:51] have a free plan so you can just experiment around as much as you need
[03:05:52] experiment around as much as you need and then you're only going to be charged
[03:05:53] and then you're only going to be charged based on the amount of usage you use. So
[03:05:55] based on the amount of usage you use. So it's very very cheap and affordable and
[03:05:57] it's very very cheap and affordable and I wanted to make this platform for you
[03:05:58] I wanted to make this platform for you guys to all get on and experiment with
[03:06:00] guys to all get on and experiment with building AI agents without coding. That
[03:06:02] building AI agents without coding. That was really the the core of why we
[03:06:03] was really the the core of why we started this whole thing. So we've got
[03:06:05] started this whole thing. So we've got the dashboard here which will load in my
[03:06:06] the dashboard here which will load in my data in a
[03:06:07] data in a second. So you can see here what the
[03:06:09] second. So you can see here what the dashboard will look like when you've got
[03:06:10] dashboard will look like when you've got your own agents running. We are running
[03:06:12] your own agents running. We are running the Agentive customer support chatbot
[03:06:14] the Agentive customer support chatbot through this uh through this account
[03:06:16] through this uh through this account that I'm I'm using right now. So you can
[03:06:18] that I'm I'm using right now. So you can see usage costs very cheap sessions etc.
[03:06:20] see usage costs very cheap sessions etc. So it's really cool when you go into
[03:06:21] So it's really cool when you go into analytics and you can use agentive to
[03:06:23] analytics and you can use agentive to see how people are using your agents but
[03:06:25] see how people are using your agents but that's obviously something for a little
[03:06:26] that's obviously something for a little bit later once you put these into
[03:06:27] bit later once you put these into production. Uh now what we're going to
[03:06:29] production. Uh now what we're going to do is of course we can go to agents or
[03:06:30] do is of course we can go to agents or we can just create an agent from here
[03:06:33] we can just create an agent from here and I call this um Connor's cleaning
[03:06:36] and I call this um Connor's cleaning WhatsApp agent. Oh we got a little
[03:06:39] WhatsApp agent. Oh we got a little description as well. um answers
[03:06:41] description as well. um answers questions from KB provides real
[03:06:48] time so answers questions from the
[03:06:50] time so answers questions from the knowledge base provides real-time
[03:06:52] knowledge base provides real-time cleaning quotes and can capture leads to
[03:06:54] cleaning quotes and can capture leads to air table. So you're going to see the
[03:06:55] air table. So you're going to see the setup is a lot faster than some of these
[03:06:57] setup is a lot faster than some of these other platforms. Again, I'm not not
[03:06:59] other platforms. Again, I'm not not trying to gas myself up here. It's just
[03:07:01] trying to gas myself up here. It's just a different way of approaching u
[03:07:02] a different way of approaching u building agents. So it's a lot more fast
[03:07:04] building agents. So it's a lot more fast and and rapid prototyping and easy to
[03:07:06] and and rapid prototyping and easy to get things up and running. Of course, if
[03:07:08] get things up and running. Of course, if you need much more advanced
[03:07:08] you need much more advanced functionality, you do need to go the
[03:07:10] functionality, you do need to go the extra mile and go on to platforms like
[03:07:12] extra mile and go on to platforms like Voice Flow. But in this case, we have a
[03:07:13] Voice Flow. But in this case, we have a prompt, very easy. We have a knowledge
[03:07:15] prompt, very easy. We have a knowledge and we have tools. So, remember when we
[03:07:16] and we have tools. So, remember when we went back to being a a chef and the
[03:07:18] went back to being a a chef and the three ingredients concept, these are
[03:07:20] three ingredients concept, these are your three ingredients, right? The
[03:07:21] your three ingredients, right? The prompt that you get to provide as the
[03:07:23] prompt that you get to provide as the instructions, the knowledge that you
[03:07:24] instructions, the knowledge that you provide as the external knowledge base
[03:07:26] provide as the external knowledge base and the tools that we can connect to it
[03:07:28] and the tools that we can connect to it as well. And we can select the model
[03:07:29] as well. And we can select the model here. So, I think I want a nice and
[03:07:31] here. So, I think I want a nice and snappy response time because this is
[03:07:33] snappy response time because this is going to be on WhatsApp and customerf
[03:07:34] going to be on WhatsApp and customerf facing. So I'll go to GPT4 mini. So it's
[03:07:38] facing. So I'll go to GPT4 mini. So it's nice and quick. Now we can just put a
[03:07:39] nice and quick. Now we can just put a test test test in there or you are a
[03:07:44] help. Just put that in there for now as
[03:07:46] help. Just put that in there for now as the prompt. The knowledge base we can
[03:07:48] the prompt. The knowledge base we can turn this on. We can create a new
[03:07:50] turn this on. We can create a new knowledge base. Call
[03:07:55] this. We're going to click here and
[03:07:57] this. We're going to click here and we're going to upload that same file
[03:07:58] we're going to upload that same file that we used on voice flow. The same
[03:08:00] that we used on voice flow. The same document that will be available in the
[03:08:01] document that will be available in the resources for this uh for this
[03:08:03] resources for this uh for this particular guide. Give that a second to
[03:08:05] particular guide. Give that a second to process. Once this goes green, we're
[03:08:06] process. Once this goes green, we're good to upload it. And you can add
[03:08:07] good to upload it. And you can add multiple files in here. We allowed five
[03:08:09] multiple files in here. We allowed five files at a time, but you can add dozens
[03:08:11] files at a time, but you can add dozens and dozens of files. So, you have a
[03:08:12] and dozens of files. So, you have a massive knowledge base to work
[03:08:15] with. And just like that, we have
[03:08:17] with. And just like that, we have connected our knowledge base. And the
[03:08:19] connected our knowledge base. And the cool thing about Agent is because we're
[03:08:20] cool thing about Agent is because we're built on the assistance API, this is
[03:08:22] built on the assistance API, this is actually an independent knowledge base.
[03:08:24] actually an independent knowledge base. So, you can create a knowledge base and
[03:08:25] So, you can create a knowledge base and connect it to multiple different agents.
[03:08:27] connect it to multiple different agents. The the knowledge is not restricted to
[03:08:28] The the knowledge is not restricted to the agent that you build it within. So,
[03:08:30] the agent that you build it within. So, I can go and create a new agent and
[03:08:31] I can go and create a new agent and connect this exact same knowledge base.
[03:08:32] connect this exact same knowledge base. And I have all of these other ones here.
[03:08:34] And I have all of these other ones here. And then when we go into the tools
[03:08:35] And then when we go into the tools section, we are going to have two tools
[03:08:36] section, we are going to have two tools for this. Well, the knowledge base, if
[03:08:38] for this. Well, the knowledge base, if we go back to our Figma here,
[03:08:40] we go back to our Figma here, technically the knowledge base is a form
[03:08:41] technically the knowledge base is a form of tool that the agent is using. But on
[03:08:44] of tool that the agent is using. But on platforms like the assistance API and
[03:08:45] platforms like the assistance API and and many platforms, you'll see knowledge
[03:08:47] and many platforms, you'll see knowledge treated as its own thing, but
[03:08:49] treated as its own thing, but essentially it is just another tool that
[03:08:50] essentially it is just another tool that the agent is using at the right time
[03:08:52] the agent is using at the right time when it needs to pull in knowledge to
[03:08:54] when it needs to pull in knowledge to answer questions. So, OpenAI separates
[03:08:56] answer questions. So, OpenAI separates it out into its own thing here. And so
[03:08:58] it out into its own thing here. And so do we because we built on top of it. So
[03:09:00] do we because we built on top of it. So we do have three different tools but
[03:09:02] we do have three different tools but knowledge is its own tool that gets set
[03:09:03] knowledge is its own tool that gets set up through this knowledgebased um
[03:09:05] up through this knowledgebased um connection that we just made before.
[03:09:07] connection that we just made before. Then we have the tools and here we have
[03:09:09] Then we have the tools and here we have our instant quote from relevance and we
[03:09:11] our instant quote from relevance and we have our capture lead information. So we
[03:09:12] have our capture lead information. So we know the process of going on to
[03:09:14] know the process of going on to relevance. So we can just go create a
[03:09:15] relevance. So we can just go create a new tool here and this is going to show
[03:09:17] new tool here and this is going to show you a schema. Remember back to when we
[03:09:19] you a schema. Remember back to when we talked about schemas it explains to the
[03:09:21] talked about schemas it explains to the agent how to use the tool. So to add a
[03:09:23] agent how to use the tool. So to add a tool to this agent we need to add a
[03:09:25] tool to this agent we need to add a schema to it. And thankfully our buddies
[03:09:27] schema to it. And thankfully our buddies at relevance AI provide a very very easy
[03:09:29] at relevance AI provide a very very easy way to create schemas to import into
[03:09:31] way to create schemas to import into agents like on aentive. So here I can
[03:09:33] agents like on aentive. So here I can grab that same cost estimate tool for
[03:09:35] grab that same cost estimate tool for the instant quotation for cleaning
[03:09:36] the instant quotation for cleaning services that we've used previously.
[03:09:38] services that we've used previously. Again this will be linked. You can just
[03:09:39] Again this will be linked. You can just clone this if you haven't got it
[03:09:40] clone this if you haven't got it already. I will provide a link for you
[03:09:42] already. I will provide a link for you to clone this into your relevant account
[03:09:43] to clone this into your relevant account that will be in the resources for this
[03:09:45] that will be in the resources for this video. And it's just like the previous
[03:09:47] video. And it's just like the previous tutorial that we did where it's got
[03:09:48] tutorial that we did where it's got property type square footage and an LLM
[03:09:50] property type square footage and an LLM step here to calculate it. It's going to
[03:09:52] step here to calculate it. It's going to spit that back and we're going to turn
[03:09:54] spit that back and we're going to turn that into a nice response uh with our
[03:09:56] that into a nice response uh with our agent on Agent. We can make sure that
[03:09:57] agent on Agent. We can make sure that we've saved this. So, the cool thing
[03:09:58] we've saved this. So, the cool thing here is that in order to get this
[03:10:00] here is that in order to get this connected to uh Agent and our agent over
[03:10:02] connected to uh Agent and our agent over there, we can just go to custom actions
[03:10:04] there, we can just go to custom actions here on the tools page. As you can see
[03:10:06] here on the tools page. As you can see here, it's mainly intended for use with
[03:10:08] here, it's mainly intended for use with OpenAI's custom GPTs, which you can get
[03:10:10] OpenAI's custom GPTs, which you can get access through chat GPT. And I highly
[03:10:12] access through chat GPT. And I highly recommend you do check out the OpenAI
[03:10:14] recommend you do check out the OpenAI GPTs because it's a super simple way to
[03:10:15] GPTs because it's a super simple way to spin up your own agents um on the chat
[03:10:17] spin up your own agents um on the chat GPT site. And so, we can select our tool
[03:10:19] GPT site. And so, we can select our tool here and we can get a schema for it. But
[03:10:21] here and we can get a schema for it. But what I've just realized is that I
[03:10:22] what I've just realized is that I actually do have an air table lead
[03:10:24] actually do have an air table lead capture tool here that I've already
[03:10:25] capture tool here that I've already created on relevance. And it's actually
[03:10:26] created on relevance. And it's actually going to be easier for us to set it up
[03:10:28] going to be easier for us to set it up here on relevance than to have to do it
[03:10:30] here on relevance than to have to do it all separately. So let's just quickly
[03:10:31] all separately. So let's just quickly set that up. Now if we go air table,
[03:10:35] set that up. Now if we go air table, let's just get a simple one that
[03:10:36] let's just get a simple one that captures the name and phone. I'll
[03:10:38] captures the name and phone. I'll provide the template for this tool so
[03:10:39] provide the template for this tool so you can clone it in. But basically it
[03:10:41] you can clone it in. But basically it takes an input of the name of the lead
[03:10:42] takes an input of the name of the lead and the email address of the lead and
[03:10:44] and the email address of the lead and the phone as well. So, it's capturing
[03:10:46] the phone as well. So, it's capturing all three of these as lead information
[03:10:48] all three of these as lead information and then it's sending it over to Air
[03:10:49] and then it's sending it over to Air Table which we're going to set up just
[03:10:51] Table which we're going to set up just now and it's using a post request to
[03:10:53] now and it's using a post request to push that data that we collected here
[03:10:55] push that data that we collected here and we will collect through WhatsApp
[03:10:56] and we will collect through WhatsApp eventually and it's pushing it into the
[03:10:58] eventually and it's pushing it into the Air Table database. So, let's get that
[03:11:00] Air Table database. So, let's get that set up quickly. If you go to Air
[03:11:05] Table and I'm just going to use a dummy
[03:11:07] Table and I'm just going to use a dummy CRM that I use for all of these
[03:11:09] CRM that I use for all of these tutorials and you guys are going to be
[03:11:10] tutorials and you guys are going to be able to clone this if you want. In the
[03:11:11] able to clone this if you want. In the resources for this video, there will be
[03:11:12] resources for this video, there will be a link like this. So, if I share this um
[03:11:15] a link like this. So, if I share this um share
[03:11:18] publicly, you guys will get something
[03:11:20] publicly, you guys will get something that looks a bit like this and this
[03:11:22] that looks a bit like this and this button up here says copy base. That will
[03:11:24] button up here says copy base. That will copy it into your account. So, all you
[03:11:26] copy it into your account. So, all you need to do to copy this air table base
[03:11:27] need to do to copy this air table base is to create an air table account and
[03:11:29] is to create an air table account and then click on this copy base and it will
[03:11:30] then click on this copy base and it will copy it over. So, you can get this with
[03:11:32] copy it over. So, you can get this with the column source preset up. It is
[03:11:34] the column source preset up. It is fairly easy to set up these fields
[03:11:35] fairly easy to set up these fields yourself, but I want to make it easier
[03:11:36] yourself, but I want to make it easier for you guys. So, you can just copy
[03:11:37] for you guys. So, you can just copy this. It'll be included in the
[03:11:38] this. It'll be included in the resources. But here we have the fields
[03:11:40] resources. But here we have the fields that we're looking for. So now all we
[03:11:42] that we're looking for. So now all we need to do to send data into this
[03:11:43] need to do to send data into this database through our WhatsApp based
[03:11:45] database through our WhatsApp based agentive agent. So when someone provides
[03:11:47] agentive agent. So when someone provides their details that it gets shot into
[03:11:48] their details that it gets shot into here is we need to go and see our
[03:11:50] here is we need to go and see our details for the air tableable web API.
[03:11:52] details for the air tableable web API. So air tableable has their own API which
[03:11:54] So air tableable has their own API which allows us to interact with our databases
[03:11:56] allows us to interact with our databases like this programmatically. So all we
[03:11:58] like this programmatically. So all we need to do is go up to the right hand
[03:11:59] need to do is go up to the right hand corner here go to builder hub and if we
[03:12:02] corner here go to builder hub and if we go to the developer docs here and scroll
[03:12:04] go to the developer docs here and scroll down to the web
[03:12:06] down to the web API this is a reference for the air
[03:12:08] API this is a reference for the air table web API. So this documentation is
[03:12:10] table web API. So this documentation is essentially going to tell us how to
[03:12:11] essentially going to tell us how to interact with our air table
[03:12:13] interact with our air table programmatically through our agents and
[03:12:14] programmatically through our agents and through voice flow and through relevance
[03:12:16] through voice flow and through relevance and and through agentive as well. So any
[03:12:18] and and through agentive as well. So any way you want to interact with it, you
[03:12:19] way you want to interact with it, you can now take this knowledge that you've
[03:12:21] can now take this knowledge that you've gained in this video look through this
[03:12:22] gained in this video look through this and model what we're going to do here in
[03:12:24] and model what we're going to do here in relevance. You can take that same idea
[03:12:25] relevance. You can take that same idea and put it into say voice flow and you
[03:12:27] and put it into say voice flow and you can build an air table integration
[03:12:28] can build an air table integration within voice flow yourself where you can
[03:12:30] within voice flow yourself where you can send and pull data. So these skills all
[03:12:32] send and pull data. So these skills all stack on top of each other and it really
[03:12:33] stack on top of each other and it really centers around understanding how APIs
[03:12:35] centers around understanding how APIs work and that comes down to reading
[03:12:37] work and that comes down to reading documentation as well. So in this case,
[03:12:39] documentation as well. So in this case, if you go back to our relevance tool
[03:12:41] if you go back to our relevance tool here, we need to get our URL, which is
[03:12:44] here, we need to get our URL, which is our endpoint, which we've talked about
[03:12:45] our endpoint, which we've talked about before. This is the address that we are
[03:12:46] before. This is the address that we are sending the request to and agentive
[03:12:49] sending the request to and agentive where we're building the agent. It's
[03:12:50] where we're building the agent. It's going to be using relevance to call air
[03:12:52] going to be using relevance to call air table. It's a bit of a a roundabout way
[03:12:53] table. It's a bit of a a roundabout way of doing things. But to get all of this
[03:12:55] of doing things. But to get all of this information, the easiest way is to go
[03:12:57] information, the easiest way is to go back to this documentation. And the
[03:12:59] back to this documentation. And the easiest way for us to find the
[03:13:00] easiest way for us to find the information that allows us to interact
[03:13:02] information that allows us to interact with our own Air Table base that we're
[03:13:03] with our own Air Table base that we're setting up, is to come down here and
[03:13:05] setting up, is to come down here and find the base that you've just cloned
[03:13:07] find the base that you've just cloned into your account, which will likely be
[03:13:08] into your account, which will likely be Smith Solar CRM. Don't worry about the
[03:13:10] Smith Solar CRM. Don't worry about the name. And Air Table does a really,
[03:13:11] name. And Air Table does a really, really good job of making this super
[03:13:13] really good job of making this super easy. And that we can just come here to
[03:13:14] easy. And that we can just come here to the leads table. So, if we go back to um
[03:13:17] the leads table. So, if we go back to um Air Table here, you see we are on the
[03:13:20] Air Table here, you see we are on the leads table. We have these different
[03:13:21] leads table. We have these different tabs. You can just ignore these are just
[03:13:22] tabs. You can just ignore these are just different projects that I've done on
[03:13:24] different projects that I've done on YouTube. Um they're all kind of there in
[03:13:25] YouTube. Um they're all kind of there in case people are also cloning this into
[03:13:27] case people are also cloning this into their account. But we're looking at the
[03:13:28] their account. But we're looking at the leads tab here. So, we go to the leads
[03:13:30] leads tab here. So, we go to the leads here and we want to create records. And
[03:13:33] here and we want to create records. And then it gives us all of the information
[03:13:34] then it gives us all of the information we need here in order to create records.
[03:13:36] we need here in order to create records. So, um you can see that it's a post
[03:13:38] So, um you can see that it's a post request and it's got
[03:13:41] HTTPS and all of this information. So,
[03:13:44] HTTPS and all of this information. So, this is the endpoint. We want to copy
[03:13:45] this is the endpoint. We want to copy all of this all the way down to leads.
[03:13:47] all of this all the way down to leads. Copy this. Go back to
[03:13:50] Copy this. Go back to relevance and paste this in. Oh, maybe
[03:13:53] relevance and paste this in. Oh, maybe that was already there. And paste that
[03:13:55] that was already there. And paste that in there. And then we need to add in two
[03:13:57] in there. And then we need to add in two headers. So we have authorization and
[03:13:59] headers. So we have authorization and content type. Now remembering what we
[03:14:00] content type. Now remembering what we learned before, you can see we have H
[03:14:02] learned before, you can see we have H and this H tag means that there's a
[03:14:04] and this H tag means that there's a header. And so the header is
[03:14:06] header. And so the header is authorization. And then the value is
[03:14:08] authorization. And then the value is going to be bearer and then our token.
[03:14:10] going to be bearer and then our token. This is something that tripped me up
[03:14:11] This is something that tripped me up when I was first learning this uh using
[03:14:13] when I was first learning this uh using APIs. Is that you need to add this
[03:14:16] APIs. Is that you need to add this bearer word and then a space and then
[03:14:18] bearer word and then a space and then your API key. It's a weird way of doing
[03:14:19] your API key. It's a weird way of doing things. I don't really know why uh why
[03:14:21] things. I don't really know why uh why it's like that but sometimes when you're
[03:14:23] it's like that but sometimes when you're doing these authorizations you need to
[03:14:25] doing these authorizations you need to add in bearer space and then your API
[03:14:27] add in bearer space and then your API key. So it's it's there for a reason um
[03:14:29] key. So it's it's there for a reason um is what I'm saying. And then we have the
[03:14:30] is what I'm saying. And then we have the content type being application JSON. So
[03:14:33] content type being application JSON. So we're already familiar with that. So
[03:14:34] we're already familiar with that. So going back to relevance we have the
[03:14:36] going back to relevance we have the header of authorization and content type
[03:14:38] header of authorization and content type here. Application JSON. And now we need
[03:14:40] here. Application JSON. And now we need to add in our Air Table API key so that
[03:14:42] to add in our Air Table API key so that we are authenticated and we have
[03:14:44] we are authenticated and we have permission to send an API request. So
[03:14:46] permission to send an API request. So they're not going to let anyone use this
[03:14:47] they're not going to let anyone use this details and and start sending data to
[03:14:49] details and and start sending data to our our database, right? They need to be
[03:14:51] our our database, right? They need to be authenticated and that's what API keys
[03:14:53] authenticated and that's what API keys do. So to get our Air Table API key, of
[03:14:55] do. So to get our Air Table API key, of course, we go to Air Table. We can come
[03:14:57] course, we go to Air Table. We can come up to the top right here, go back to our
[03:14:59] up to the top right here, go back to our builder
[03:15:00] builder hub, go to personal access
[03:15:03] hub, go to personal access tokens, and we can create a new token.
[03:15:06] tokens, and we can create a new token. Call this
[03:15:07] Call this YouTube. We can go um add the base. This
[03:15:11] YouTube. We can go um add the base. This will be um Smith's Solar CRM. We can add
[03:15:15] will be um Smith's Solar CRM. We can add a scope
[03:15:18] a scope read write and sometimes I find it handy
[03:15:20] read write and sometimes I find it handy to have the schemas read in there as
[03:15:22] to have the schemas read in there as well. So basically what we're doing here
[03:15:23] well. So basically what we're doing here is saying that I give this API key that
[03:15:25] is saying that I give this API key that we're creating permission to interact
[03:15:27] we're creating permission to interact with this uh this air table and I give
[03:15:29] with this uh this air table and I give it permissions to do these things like
[03:15:31] it permissions to do these things like read what's in the database write to the
[03:15:33] read what's in the database write to the databases and create new things and also
[03:15:35] databases and create new things and also to see the overall structure of the base
[03:15:36] to see the overall structure of the base and the field types. So we can add that
[03:15:39] and the field types. So we can add that and create the token. We get this token,
[03:15:41] and create the token. We get this token, head back to relevance. And again, this
[03:15:43] head back to relevance. And again, this template so that you can clone it into
[03:15:45] template so that you can clone it into your account is going to be on the uh on
[03:15:47] your account is going to be on the uh on the resources. So, if you're following
[03:15:48] the resources. So, if you're following along, you should just clone it into
[03:15:49] along, you should just clone it into your account and then come down here and
[03:15:51] your account and then come down here and make the changes as I do them. So, we
[03:15:52] make the changes as I do them. So, we can add a make sure we have a space
[03:15:54] can add a make sure we have a space after bearer and then paste our key
[03:15:56] after bearer and then paste our key because if we go back to the web API
[03:15:57] because if we go back to the web API docs, we can see we have authorization
[03:15:59] docs, we can see we have authorization bearer space your API key content type
[03:16:02] bearer space your API key content type and then application/json. Then we have
[03:16:03] and then application/json. Then we have the data as the payload. Remember, like
[03:16:05] the data as the payload. Remember, like this is what's inside the envelope. Then
[03:16:08] this is what's inside the envelope. Then we have records and we have the fields
[03:16:10] we have records and we have the fields name, phone, and status. And then it's
[03:16:11] name, phone, and status. And then it's provided us an example of how we would
[03:16:13] provided us an example of how we would send data into that which we don't need
[03:16:14] send data into that which we don't need to worry too much about because I've
[03:16:16] to worry too much about because I've already got this fitted in here. It can
[03:16:17] already got this fitted in here. It can be quite fiddly. In fact, for this I'm
[03:16:19] be quite fiddly. In fact, for this I'm actually going to add another field in
[03:16:21] actually going to add another field in here. This is one thing about relevance
[03:16:23] here. This is one thing about relevance I'm not a huge fan of. This can feel
[03:16:25] I'm not a huge fan of. This can feel super fiddly
[03:16:27] super fiddly sometimes. So if we go
[03:16:30] sometimes. So if we go email, this will already be in the
[03:16:32] email, this will already be in the template that I give you, by the way.
[03:16:34] template that I give you, by the way. Email. Why would that delete that?
[03:16:43] Okay, so we have the URL has been
[03:16:45] Okay, so we have the URL has been updated. The method is post. That's
[03:16:47] updated. The method is post. That's correct. We have the authentication. We
[03:16:48] correct. We have the authentication. We have the content type. We have the body
[03:16:50] have the content type. We have the body all set up. We've added in our fields of
[03:16:54] all set up. We've added in our fields of name, phone, and email, which we have
[03:16:56] name, phone, and email, which we have name, email, and phone. So, we can give
[03:16:59] name, email, and phone. So, we can give it a spin here. If we say
[03:17:01] it a spin here. If we say Liam, there we go.
[03:17:06] and we give it a spin. Run the
[03:17:09] and we give it a spin. Run the tool. We'll see if it accepts
[03:17:18] us. Yep. And there we go. If we go back
[03:17:21] us. Yep. And there we go. If we go back to Air
[03:17:22] to Air Table, open the base
[03:17:24] Table, open the base up. There we have it. Liam phone email.
[03:17:27] up. There we have it. Liam phone email. So, we can take this tool and we can
[03:17:29] So, we can take this tool and we can take the instant quote generator. we can
[03:17:31] take the instant quote generator. we can put those into uh Agent and before you
[03:17:33] put those into uh Agent and before you know it, we're going to have our agent
[03:17:35] know it, we're going to have our agent ready to go. So, let's head back to
[03:17:36] ready to go. So, let's head back to relevance here. We'll save this tool and
[03:17:39] relevance here. We'll save this tool and we'll change this to name,
[03:17:41] we'll change this to name, email, and phone. Um, and just quickly
[03:17:44] email, and phone. Um, and just quickly before we do that integration, this is
[03:17:46] before we do that integration, this is when the description comes into play
[03:17:48] when the description comes into play here. Remember those natural language
[03:17:49] here. Remember those natural language descriptions of what the tool does, what
[03:17:52] descriptions of what the tool does, what each of the parameters and inputs are.
[03:17:53] each of the parameters and inputs are. It's really important to get these right
[03:17:55] It's really important to get these right in relevance, and I see a lot of people
[03:17:56] in relevance, and I see a lot of people skipping over this step, but this is
[03:17:58] skipping over this step, but this is what's going to be put into that schema,
[03:17:59] what's going to be put into that schema, right? So when relevance generates a
[03:18:01] right? So when relevance generates a schema for us, that onepage manual on
[03:18:03] schema for us, that onepage manual on how to use this tool and use the API in
[03:18:05] how to use this tool and use the API in order to interact with this
[03:18:07] order to interact with this functionality when we give it into
[03:18:09] functionality when we give it into agentive, it's going to be reading over
[03:18:11] agentive, it's going to be reading over everything in there. And it's going to
[03:18:12] everything in there. And it's going to be those little descriptions around what
[03:18:13] be those little descriptions around what the tool does and what it's supposed to
[03:18:15] the tool does and what it's supposed to take in. And and these parts here in
[03:18:17] take in. And and these parts here in relevance is where we get to set that
[03:18:18] relevance is where we get to set that up. A proper description is needed
[03:18:20] up. A proper description is needed before we do this integration. So this
[03:18:22] before we do this integration. So this tool captures lead information, stores
[03:18:23] tool captures lead information, stores in Air Table CRM, requires lead's name,
[03:18:26] in Air Table CRM, requires lead's name, phone, and email. Name, phone, and
[03:18:27] phone, and email. Name, phone, and email. The name is name of the lead.
[03:18:29] email. The name is name of the lead. Yep. Email, email address of the lead
[03:18:31] Yep. Email, email address of the lead and phone is the phone number of the
[03:18:32] and phone is the phone number of the lead. So that's all good there and ready
[03:18:35] lead. So that's all good there and ready to
[03:18:37] to integrate. Might even do a quick check
[03:18:39] integrate. Might even do a quick check on the sparkly cost estimate as
[03:18:43] well. Yep. Type of property, square
[03:18:47] well. Yep. Type of property, square footage of the property, and we are
[03:18:49] footage of the property, and we are ready to go. So now we can click on the
[03:18:50] ready to go. So now we can click on the custom action step here. Scroll down and
[03:18:53] custom action step here. Scroll down and click on both of these. Bam. Bam.
[03:18:59] click on both of these. Bam. Bam. Scroll down. We're going to change this
[03:19:00] Scroll down. We're going to change this to custom orth. We're going to generate
[03:19:03] to custom orth. We're going to generate an API
[03:19:05] an API key. There we go. And we're going to
[03:19:07] key. There we go. And we're going to generate our open API, not open AI, open
[03:19:10] generate our open API, not open AI, open API. It's essentially a type of API and
[03:19:12] API. It's essentially a type of API and a way of describing how the API works.
[03:19:14] a way of describing how the API works. And it gives us all of this information
[03:19:16] And it gives us all of this information here. I will actually expand it out so
[03:19:17] here. I will actually expand it out so you guys can see at least some of it.
[03:19:20] you guys can see at least some of it. It's probably easier over on agentive
[03:19:21] It's probably easier over on agentive actually. And then we head back to
[03:19:23] actually. And then we head back to agentive.
[03:19:25] agentive. What we can do is paste in the
[03:19:28] What we can do is paste in the schema. And now if we scroll through
[03:19:30] schema. And now if we scroll through this quickly, I just want you to see
[03:19:31] this quickly, I just want you to see what a schema looks like under the hood
[03:19:32] what a schema looks like under the hood because we have some important parts uh
[03:19:34] because we have some important parts uh that's going to really connect the dots
[03:19:35] that's going to really connect the dots for you after everything that we've
[03:19:36] for you after everything that we've learned in this video. So I'll zoom in a
[03:19:38] learned in this video. So I'll zoom in a bit here. Um we have the title of the
[03:19:41] bit here. Um we have the title of the tool. So we have a few key things in
[03:19:42] tool. So we have a few key things in here that we can break down. Basically
[03:19:44] here that we can break down. Basically the paths. We have two paths in here.
[03:19:46] the paths. We have two paths in here. This is one of them and this is the
[03:19:48] This is one of them and this is the other. These represent the two tools
[03:19:50] other. These represent the two tools that we are integrating. You can see one
[03:19:52] that we are integrating. You can see one here is the operation ID is basically
[03:19:54] here is the operation ID is basically the name of the tool and that is taken
[03:19:56] the name of the tool and that is taken from relevance directly the air table
[03:19:57] from relevance directly the air table lead capture and the summary here is the
[03:19:59] lead capture and the summary here is the actual name or the title of the tool
[03:20:00] actual name or the title of the tool that we had in relevance. This is just a
[03:20:02] that we had in relevance. This is just a a version where they put in um
[03:20:04] a version where they put in um underscores to connect the uh the gaps
[03:20:06] underscores to connect the uh the gaps and the description here you can see
[03:20:07] and the description here you can see it's the same as a description that we
[03:20:09] it's the same as a description that we set up over I don't want to go back on
[03:20:11] set up over I don't want to go back on there but that was a description that we
[03:20:12] there but that was a description that we put under the name to describe what the
[03:20:14] put under the name to describe what the tool does and then as for the inputs
[03:20:16] tool does and then as for the inputs relevance has made it a little bit more
[03:20:18] relevance has made it a little bit more complicated by putting a schema in here.
[03:20:19] complicated by putting a schema in here. Um, so we'll cover that in a second, but
[03:20:21] Um, so we'll cover that in a second, but basically here's the second tool.
[03:20:22] basically here's the second tool. Sparkly cost estimate. This tool does
[03:20:24] Sparkly cost estimate. This tool does this. This about estimating the cost of
[03:20:26] this. This about estimating the cost of an apartment. Then down here we have the
[03:20:28] an apartment. Then down here we have the schemas for the inputs. So we have
[03:20:30] schemas for the inputs. So we have things like the name. This is for the
[03:20:32] things like the name. This is for the lead capture tool. The name um this is
[03:20:35] lead capture tool. The name um this is one of the fields. It's going to be in
[03:20:36] one of the fields. It's going to be in type string and it's required. We have
[03:20:38] type string and it's required. We have the email which is type string which is
[03:20:40] the email which is type string which is required. And we have the email which is
[03:20:42] required. And we have the email which is a description
[03:20:43] a description here. And of course you can see all the
[03:20:45] here. And of course you can see all the descriptions that we put in on relevance
[03:20:47] descriptions that we put in on relevance showing up here. then the phone number
[03:20:49] showing up here. then the phone number of the lead, the email of the lead, etc.
[03:20:50] of the lead, the email of the lead, etc. And here it's specifying how the AI
[03:20:52] And here it's specifying how the AI agent should be sending inputs into
[03:20:54] agent should be sending inputs into that. So that's probably the most
[03:20:55] that. So that's probably the most difficult technical part of this whole
[03:20:56] difficult technical part of this whole video, but I did want to give you a bit
[03:20:58] video, but I did want to give you a bit of context on how that kind of fits
[03:20:59] of context on how that kind of fits together. This is quite a complex
[03:21:01] together. This is quite a complex schema. Relevance puts it together in a
[03:21:03] schema. Relevance puts it together in a little bit more complex way um by using
[03:21:05] little bit more complex way um by using these uh these schemas for the inputs
[03:21:07] these uh these schemas for the inputs down here. But long story short, if we
[03:21:09] down here. But long story short, if we then go to the add or button, we need to
[03:21:11] then go to the add or button, we need to set up our authentication, which we can
[03:21:14] set up our authentication, which we can do by coming back to relevance and
[03:21:15] do by coming back to relevance and copying this. We go back to here, paste
[03:21:18] copying this. We go back to here, paste this in. We go custom orth and we go
[03:21:22] this in. We go custom orth and we go authorize a
[03:21:24] authorize a orization with a
[03:21:27] orization with a zed. Oh, I need to create the tool.
[03:21:30] zed. Oh, I need to create the tool. Sorry. So, we can just click create
[03:21:32] Sorry. So, we can just click create tool. So, the tool has been created
[03:21:34] tool. So, the tool has been created successfully. And there we go. We have
[03:21:36] successfully. And there we go. We have both of the tools added in because we
[03:21:38] both of the tools added in because we did them both in one bundle on
[03:21:39] did them both in one bundle on relevance. And then if we go edit off,
[03:21:42] relevance. And then if we go edit off, we can then put in API keys for both of
[03:21:44] we can then put in API keys for both of these so that we have permission to use
[03:21:55] them. And we can do the same for this
[03:22:03] one. And there we go. Now we have our
[03:22:05] one. And there we go. Now we have our knowledge set up, our two tools set up,
[03:22:08] knowledge set up, our two tools set up, and you can see that we're pretty darn
[03:22:09] and you can see that we're pretty darn close to completing this build. We have
[03:22:11] close to completing this build. We have all of these three done. Might as well
[03:22:13] all of these three done. Might as well make them green for the sake of it. And
[03:22:16] make them green for the sake of it. And now the only thing left to do is to
[03:22:17] now the only thing left to do is to write a prompt that connects this all
[03:22:19] write a prompt that connects this all together. And that's really the glue
[03:22:20] together. And that's really the glue that holds it together. My go-to method
[03:22:21] that holds it together. My go-to method of rapidly creating prompts for AI
[03:22:23] of rapidly creating prompts for AI agents is using a relevance tool. Um,
[03:22:28] agents is using a relevance tool. Um, perfect that I've created, and I I said
[03:22:30] perfect that I've created, and I I said I'd give this to you guys for free as
[03:22:31] I'd give this to you guys for free as well. That's going to be included in the
[03:22:33] well. That's going to be included in the resources. But if I go to use
[03:22:35] resources. But if I go to use here, it's a prompt writer that includes
[03:22:38] here, it's a prompt writer that includes all of the information from how we do
[03:22:40] all of the information from how we do prompting at Morningside, which is based
[03:22:41] prompting at Morningside, which is based on research and includes all the key
[03:22:43] on research and includes all the key things like RO, task, specifics,
[03:22:45] things like RO, task, specifics, context, um, explaining how to use the
[03:22:46] context, um, explaining how to use the tools that it's been provided as well.
[03:22:48] tools that it's been provided as well. So, I'm just going to fill this out
[03:22:49] So, I'm just going to fill this out quickly here and then get a prompt. And
[03:22:50] quickly here and then get a prompt. And you guys can steal my prompt from the
[03:22:52] you guys can steal my prompt from the resources or you can use this as well to
[03:22:54] resources or you can use this as well to create your own. But, it's a pretty good
[03:22:56] create your own. But, it's a pretty good exercise because you can see here we
[03:22:57] exercise because you can see here we have the agent name being
[03:23:04] Um, and what I like to do here is, so
[03:23:06] Um, and what I like to do here is, so this is just a quick rundown of what the
[03:23:07] this is just a quick rundown of what the agent does, where it is being deployed,
[03:23:09] agent does, where it is being deployed, and
[03:23:18] why. So you can pause the video and look
[03:23:20] why. So you can pause the video and look at that there. But just a bit of context
[03:23:21] at that there. But just a bit of context on what the agent does, where it is
[03:23:23] on what the agent does, where it is being deployed, and why. Conversions
[03:23:25] being deployed, and why. Conversions context, we can say
[03:23:36] knowledge context. We can say with a
[03:23:43] contain. Then we get to the tools
[03:23:45] contain. Then we get to the tools available section and we can
[03:23:56] say and then we have the other tool
[03:23:58] say and then we have the other tool which is uh
[03:24:07] And then for the ideal input and output
[03:24:09] And then for the ideal input and output examples, I'm just going to say none to
[03:24:13] examples, I'm just going to say none to provide friendly helpful
[03:24:18] assistant. And so just like that, in
[03:24:20] assistant. And so just like that, in maybe a few minutes, I've typed in all
[03:24:22] maybe a few minutes, I've typed in all of this information about the agent and
[03:24:23] of this information about the agent and what it does. And now I can just click
[03:24:25] what it does. And now I can just click run tool here. And it's going to take
[03:24:27] run tool here. And it's going to take all of this information, run it through
[03:24:29] all of this information, run it through the prompt that I've written that bakes
[03:24:31] the prompt that I've written that bakes in the best prompting practices for AI
[03:24:33] in the best prompting practices for AI agents from my experience and from the
[03:24:34] agents from my experience and from the projects that we do at Morningside AI
[03:24:36] projects that we do at Morningside AI and also all the research that we've
[03:24:37] and also all the research that we've used to make those prompting practices.
[03:24:39] used to make those prompting practices. And it's going to spit us out an AI
[03:24:41] And it's going to spit us out an AI agent prompt that we can throw straight
[03:24:42] agent prompt that we can throw straight into Agent and it'll just glue
[03:24:44] into Agent and it'll just glue everything that we've done together,
[03:24:45] everything that we've done together, tell it who it is and what it's trying
[03:24:46] tell it who it is and what it's trying to do, tell it how it's supposed to use
[03:24:48] to do, tell it how it's supposed to use the knowledge base, and tell it how and
[03:24:50] the knowledge base, and tell it how and when it's supposed to use those tools in
[03:24:51] when it's supposed to use those tools in order to reach its objective of
[03:24:52] order to reach its objective of capturing those leads for us via
[03:24:54] capturing those leads for us via WhatsApp. And there we go. So, if we
[03:24:56] WhatsApp. And there we go. So, if we scroll down, we can see it's spit out
[03:24:58] scroll down, we can see it's spit out this entire prompt. I'm going to change
[03:24:59] this entire prompt. I'm going to change it to the raw text so we get all this
[03:25:01] it to the raw text so we get all this markdown formatting included. We can
[03:25:04] markdown formatting included. We can view all here. I'm going to copy it all
[03:25:07] view all here. I'm going to copy it all and we're going to take it over to the
[03:25:10] and we're going to take it over to the here and paste this in. And there we go.
[03:25:12] here and paste this in. And there we go. Act as corner cleaning WhatsApp support
[03:25:14] Act as corner cleaning WhatsApp support and lead generation agent. Engage with
[03:25:16] and lead generation agent. Engage with potential customers on WhatsApp to
[03:25:17] potential customers on WhatsApp to provide potential information about our
[03:25:19] provide potential information about our cleaning services. Answer FAQs. answer
[03:25:21] cleaning services. Answer FAQs. answer off instant quotes
[03:25:23] off instant quotes ra when pricing inquiries arise use the
[03:25:26] ra when pricing inquiries arise use the instant quote generator tool tools you
[03:25:28] instant quote generator tool tools you have this tool and this tool examples
[03:25:30] have this tool and this tool examples I'm just going to cut that out for now
[03:25:33] I'm just going to cut that out for now and then notes ra so that should be all
[03:25:36] and then notes ra so that should be all good we can start to give this a spin
[03:25:37] good we can start to give this a spin here I am going to zoom out a bit right
[03:25:38] here I am going to zoom out a bit right all right so I'm just going to publish
[03:25:39] all right so I'm just going to publish this and make sure that everything is
[03:25:41] this and make sure that everything is baked in the second and now we can chat
[03:25:44] baked in the second and now we can chat to it here um hey how's it
[03:25:47] to it here um hey how's it going actually slide this across
[03:25:51] going actually slide this across Um, I want to know where you guys are
[03:25:55] Um, I want to know where you guys are located. There you go. Connor's cleaning
[03:25:57] located. There you go. Connor's cleaning is located at XYZ. So, it's obviously
[03:25:59] is located at XYZ. So, it's obviously using the knowledge base correctly and
[03:26:00] using the knowledge base correctly and say, "What what services do you
[03:26:03] say, "What what services do you provide?" And we're not asking about
[03:26:06] provide?" And we're not asking about pricing. So, it shouldn't go for the
[03:26:09] quote or it might try to do it at the
[03:26:11] quote or it might try to do it at the end. Yes. So, see, it's asking if you
[03:26:13] end. Yes. So, see, it's asking if you have any specific requirements, need a
[03:26:14] have any specific requirements, need a quote, just let me know. Yeah, sure. I'd
[03:26:16] quote, just let me know. Yeah, sure. I'd like like a quote. Boom. I need the
[03:26:19] like like a quote. Boom. I need the property type and square footage. It's a
[03:26:21] property type and square footage. It's a house and it's 1,00 square ft. So now
[03:26:24] house and it's 1,00 square ft. So now the agent is trying to trigger that tool
[03:26:26] the agent is trying to trigger that tool by taking the house and taking the 1,00
[03:26:28] by taking the house and taking the 1,00 and then putting them into the relevance
[03:26:30] and then putting them into the relevance tool based off what the schema has told
[03:26:31] tool based off what the schema has told it how to use the API. It's going to go
[03:26:33] it how to use the API. It's going to go grab that from relevance, send it back
[03:26:35] grab that from relevance, send it back to us and there we go. Here are the
[03:26:37] to us and there we go. Here are the quotes for you. Ra, if you're interested
[03:26:39] quotes for you. Ra, if you're interested in any specific further service and need
[03:26:41] in any specific further service and need assistant, just let me know. I can also
[03:26:42] assistant, just let me know. I can also help you with booking. Now here I would
[03:26:44] help you with booking. Now here I would probably change the prompt and make it a
[03:26:45] probably change the prompt and make it a bit more forceful and say send me like
[03:26:48] bit more forceful and say send me like like let's go to the next step right
[03:26:49] like let's go to the next step right now. But for now it's good enough. Um we
[03:26:51] now. But for now it's good enough. Um we can say uh sure I'd like to book a deep
[03:26:54] can say uh sure I'd like to book a deep clean. Now it should ask me for my lead
[03:26:58] clean. Now it should ask me for my lead information. Okay. Huge
[03:27:01] information. Okay. Huge Jackman is the
[03:27:03] Jackman is the name is the phone and huge Jack Jackman
[03:27:08] name is the phone and huge Jack Jackman is email.
[03:27:10] is email. We should be able to see if we go back
[03:27:12] We should be able to see if we go back to our handy dandy air table
[03:27:14] to our handy dandy air table here. Huge popping up here.
[03:27:26] Oh, bang. And huge Jackman is in the CRM
[03:27:31] Oh, bang. And huge Jackman is in the CRM here. It does say that it's booked. I
[03:27:33] here. It does say that it's booked. I would play around with the prompt a
[03:27:34] would play around with the prompt a little bit more to be like, hey, look,
[03:27:35] little bit more to be like, hey, look, this is just setting up the next step
[03:27:37] this is just setting up the next step for someone to call them and book in the
[03:27:38] for someone to call them and book in the service. But you can also do appointment
[03:27:40] service. But you can also do appointment setting through agentive as well. Again,
[03:27:41] setting through agentive as well. Again, like I said, it's a little bit more
[03:27:42] like I said, it's a little bit more advanced than what we want to do here.
[03:27:44] advanced than what we want to do here. But as you can see, this is a very
[03:27:46] But as you can see, this is a very different way of approaching building
[03:27:48] different way of approaching building agents because you tell it, you
[03:27:50] agents because you tell it, you basically provide all of the ingredients
[03:27:51] basically provide all of the ingredients and you use that kind of chef's
[03:27:52] and you use that kind of chef's approach. The knowledge and the tools
[03:27:54] approach. The knowledge and the tools and you connect it all up and you make
[03:27:55] and you connect it all up and you make sure the tools have well described
[03:27:56] sure the tools have well described schemas so they know how to use it and
[03:27:58] schemas so they know how to use it and they know when to trigger them. The
[03:27:59] they know when to trigger them. The knowledge base has been included in the
[03:28:01] knowledge base has been included in the prompt and also the tools as well have
[03:28:02] prompt and also the tools as well have been included in the prompt um telling
[03:28:04] been included in the prompt um telling it how and when to use it. It's really a
[03:28:06] it how and when to use it. It's really a much faster way of building agents from
[03:28:07] much faster way of building agents from the highle prompting and then people are
[03:28:10] the highle prompting and then people are just asking and having sort of a free
[03:28:11] just asking and having sort of a free flowing conversation with it. Okay. And
[03:28:12] flowing conversation with it. Okay. And just quickly before we go to the step of
[03:28:14] just quickly before we go to the step of putting it onto WhatsApp which won't
[03:28:15] putting it onto WhatsApp which won't take long at all. I do want to show you
[03:28:17] take long at all. I do want to show you how you can debug and when you're
[03:28:18] how you can debug and when you're working in agentive um it's helpful to
[03:28:20] working in agentive um it's helpful to know when tools are being triggered and
[03:28:22] know when tools are being triggered and why. So for example, if we go into the
[03:28:24] why. So for example, if we go into the transcripts here and we look at this big
[03:28:26] transcripts here and we look at this big transcript here with 14 messages that we
[03:28:27] transcript here with 14 messages that we just had. Hey, how's it going? Ra. We
[03:28:31] just had. Hey, how's it going? Ra. We can see here it's using the tools and we
[03:28:33] can see here it's using the tools and we can hover over it and we can see it's
[03:28:34] can hover over it and we can see it's calling the tool with the URL. It's a
[03:28:36] calling the tool with the URL. It's a post method and we can see the data
[03:28:38] post method and we can see the data here. I'll just zoom in on that. The
[03:28:40] here. I'll just zoom in on that. The property type and the square footage
[03:28:42] property type and the square footage that was sent away to relevance are
[03:28:44] that was sent away to relevance are here. So if you're having issues with
[03:28:45] here. So if you're having issues with your tools or it's giving weird
[03:28:46] your tools or it's giving weird responses, um you can either come in
[03:28:48] responses, um you can either come in here to the transcripts after the fact.
[03:28:49] here to the transcripts after the fact. So say maybe this is on WhatsApp um and
[03:28:52] So say maybe this is on WhatsApp um and something's going wrong or customers are
[03:28:54] something's going wrong or customers are getting upset. You can come into the
[03:28:56] getting upset. You can come into the transcripts here and pick through and
[03:28:57] transcripts here and pick through and see what's going wrong with the tools.
[03:28:58] see what's going wrong with the tools. And just like down here as well, the
[03:29:00] And just like down here as well, the lead capture, we can see the name,
[03:29:02] lead capture, we can see the name, email, and phone were all put into this
[03:29:03] email, and phone were all put into this request and sent away to relevance AI.
[03:29:05] request and sent away to relevance AI. And then onto Air Table as a second
[03:29:07] And then onto Air Table as a second step. Um, and you can also see the
[03:29:08] step. Um, and you can also see the output as well. So the output of the
[03:29:10] output as well. So the output of the tool is all in here. It's basically just
[03:29:13] tool is all in here. It's basically just giving us a confirmation back from Air
[03:29:14] giving us a confirmation back from Air Table that, yep, everything went well.
[03:29:16] Table that, yep, everything went well. And up here, you can see the
[03:29:19] And up here, you can see the output as uh the response with the deep
[03:29:22] output as uh the response with the deep cleaning estimates and stuff like that.
[03:29:23] cleaning estimates and stuff like that. You can see it a lot more easily if we
[03:29:25] You can see it a lot more easily if we say, "Hey, can I get a quote?
[03:29:30] Okay. And if you give this a second once
[03:29:32] Okay. And if you give this a second once it's finished generating agentive will
[03:29:34] it's finished generating agentive will then pop up this show usage and bang
[03:29:36] then pop up this show usage and bang there in the editor here. You can then
[03:29:37] there in the editor here. You can then debug. Okay. How many tokens are being
[03:29:39] debug. Okay. How many tokens are being used? How much is this costing? What was
[03:29:40] used? How much is this costing? What was the model? Um etc. And then you can see
[03:29:43] the model? Um etc. And then you can see the tools input here. Apartment 500 ft
[03:29:46] the tools input here. Apartment 500 ft etc. And the output as well. So it's
[03:29:47] etc. And the output as well. So it's really easy to debug those tools while
[03:29:49] really easy to debug those tools while you're in Agent. Let's make sure that
[03:29:50] you're in Agent. Let's make sure that we've published
[03:29:51] we've published this. I'm going to publish it again. In
[03:29:54] this. I'm going to publish it again. In Agent, we do have version history. So,
[03:29:55] Agent, we do have version history. So, if you do publish it and you want to
[03:29:57] if you do publish it and you want to roll back or look at how you had it set
[03:29:58] roll back or look at how you had it set up previously, you can now see that I've
[03:30:00] up previously, you can now see that I've got two versions, V1 here, and I just
[03:30:02] got two versions, V1 here, and I just took away this little full stop here and
[03:30:04] took away this little full stop here and you can see that that's I've changed the
[03:30:06] you can see that that's I've changed the prompt. So you can update it over time.
[03:30:07] prompt. So you can update it over time. You can make edits within Agentive here
[03:30:09] You can make edits within Agentive here and test test test. And then when you're
[03:30:11] and test test test. And then when you're ready to push that to production and
[03:30:12] ready to push that to production and basically if we had this on a WhatsApp
[03:30:14] basically if we had this on a WhatsApp agent and say I published this,
[03:30:16] agent and say I published this, connected to WhatsApp and it was working
[03:30:18] connected to WhatsApp and it was working and then I looked through the the
[03:30:19] and then I looked through the the transcripts and something wasn't quite
[03:30:20] transcripts and something wasn't quite how I liked it, I could come in here and
[03:30:22] how I liked it, I could come in here and make edits and then test test and then
[03:30:24] make edits and then test test and then when I was ready to publish it, I click
[03:30:26] when I was ready to publish it, I click publish and then it's going to push
[03:30:27] publish and then it's going to push those live to the agent. So you're not
[03:30:28] those live to the agent. So you're not going to mess things up by playing
[03:30:30] going to mess things up by playing around with things on here. So the final
[03:30:31] around with things on here. So the final step is of course to deploy it to
[03:30:32] step is of course to deploy it to WhatsApp.
[03:30:36] Go to the deploy tab here. You can then
[03:30:38] Go to the deploy tab here. You can then click connect
[03:30:41] click connect WhatsApp. I'm going to click
[03:30:43] WhatsApp. I'm going to click continue, get started. You will of
[03:30:45] continue, get started. You will of course need a Facebook business manager
[03:30:47] course need a Facebook business manager to set up this integration fully. That's
[03:30:48] to set up this integration fully. That's free with every Facebook account. So, if
[03:30:50] free with every Facebook account. So, if you haven't got one already, I'll leave
[03:30:51] you haven't got one already, I'll leave a link in the description so that you
[03:30:52] a link in the description so that you can set it up. Takes a few clicks. Then
[03:30:54] can set it up. Takes a few clicks. Then you will see this page here. And you can
[03:30:55] you will see this page here. And you can select the business manager you've
[03:30:56] select the business manager you've created. In this case, I'll be using
[03:30:58] created. In this case, I'll be using this testing one. And then you'll be
[03:30:59] this testing one. And then you'll be able to set up a new WhatsApp business
[03:31:00] able to set up a new WhatsApp business account, which I can click here. I'll go
[03:31:02] account, which I can click here. I'll go next. set up a business account
[03:31:05] next. set up a business account name. And then this is the display name
[03:31:08] name. And then this is the display name for the business. And we're going to
[03:31:10] for the business. And we're going to call this a a retail business. Now, you
[03:31:14] call this a a retail business. Now, you need to provide the phone number that
[03:31:15] need to provide the phone number that you want to connect your agent to. Um,
[03:31:16] you want to connect your agent to. Um, unfortunately, you can't have your own
[03:31:18] unfortunately, you can't have your own personal WhatsApp number and also have a
[03:31:20] personal WhatsApp number and also have a business account running through it. So,
[03:31:21] business account running through it. So, you need to either buy another SIM card
[03:31:23] you need to either buy another SIM card or borrow a friend's number who doesn't
[03:31:24] or borrow a friend's number who doesn't have WhatsApp, etc. In this case, I'll
[03:31:26] have WhatsApp, etc. In this case, I'll be using a spare number that I have.
[03:31:28] be using a spare number that I have. Then, they're going to send you a
[03:31:29] Then, they're going to send you a verification code to your number, which
[03:31:30] verification code to your number, which you have to enter in. And then you
[03:31:32] you have to enter in. And then you should see the screen once you've
[03:31:33] should see the screen once you've successfully passed that verification.
[03:31:35] successfully passed that verification. So when we continue, it's verifying our
[03:31:37] So when we continue, it's verifying our information for a second. And now our
[03:31:39] information for a second. And now our agent is connected to that phone number
[03:31:40] agent is connected to that phone number and we're ready to give it a test. So if
[03:31:42] and we're ready to give it a test. So if we go finish here, there's one more
[03:31:44] we go finish here, there's one more thing that we need to do on Agentive,
[03:31:45] thing that we need to do on Agentive, which is to click this. Yours may say
[03:31:47] which is to click this. Yours may say not registered. Don't worry, you can
[03:31:48] not registered. Don't worry, you can just click this check box here and click
[03:31:50] just click this check box here and click confirm. Give it a second to connect.
[03:31:53] confirm. Give it a second to connect. Now we've successfully connected our
[03:31:54] Now we've successfully connected our agent to that WhatsApp number. Now thing
[03:31:56] agent to that WhatsApp number. Now thing here is this interval. If you're not
[03:31:58] here is this interval. If you're not sure what the interval is, you can read
[03:31:59] sure what the interval is, you can read this tool tip here. And if you're done
[03:32:01] this tool tip here. And if you're done with the deployment and you want to
[03:32:02] with the deployment and you want to remove it from that number, you can
[03:32:03] remove it from that number, you can always come back and click deactivate
[03:32:04] always come back and click deactivate deployment here. But all that's left to
[03:32:06] deployment here. But all that's left to do now is to test our functionality.
[03:32:07] do now is to test our functionality. Right. So I have it connected to my
[03:32:09] Right. So I have it connected to my phone here. So I'm just going to show
[03:32:10] phone here. So I'm just going to show you a little bit of a on screen here of
[03:32:12] you a little bit of a on screen here of me creating this contact and having a
[03:32:13] me creating this contact and having a message with it. So the number that I
[03:32:15] message with it. So the number that I set up, I can create a new contact and
[03:32:17] set up, I can create a new contact and then I can send them a message.
[03:32:22] Hey, and you can see on screen here it
[03:32:24] Hey, and you can see on screen here it says this is the business using a secure
[03:32:26] says this is the business using a secure service from Meta. So, this means this
[03:32:27] service from Meta. So, this means this is a business account um as we've
[03:32:29] is a business account um as we've connected it through our WhatsApp uh
[03:32:30] connected it through our WhatsApp uh business profile that we set up
[03:32:33] business profile that we set up before. And there we go. We get a
[03:32:35] before. And there we go. We get a message back. Hello, thank you for
[03:32:36] message back. Hello, thank you for sharing your information. How can I
[03:32:37] sharing your information. How can I assist you today? Um if you have any
[03:32:39] assist you today? Um if you have any questions about cleaning service or need
[03:32:40] questions about cleaning service or need a quote, feel free to let me know. So, I
[03:32:42] a quote, feel free to let me know. So, I can say um yes, a quote. Let's ask a
[03:32:45] can say um yes, a quote. Let's ask a question to the knowledge base. Where
[03:32:47] question to the knowledge base. Where are you
[03:32:51] based? There we go. We are based in the
[03:32:53] based? There we go. We are based in the greater Boston area. It's giving me the
[03:32:55] greater Boston area. It's giving me the uh the correct location there. So, we
[03:32:57] uh the correct location there. So, we can go for the lead capture now. So, if
[03:32:58] can go for the lead capture now. So, if we say um I'd like a
[03:33:06] quote. So, property type uh it's a house
[03:33:10] quote. So, property type uh it's a house that is
[03:33:12] that is about 800 square
[03:33:18] ft. There we go. We're getting the uh
[03:33:21] ft. There we go. We're getting the uh estimations and our quote back. Um, it's
[03:33:23] estimations and our quote back. Um, it's asking if we're interested in any of
[03:33:24] asking if we're interested in any of these services. I'd say yes, I'd like
[03:33:27] these services. I'd say yes, I'd like the deep cleaning,
[03:33:31] please. Now, it should ask me for my
[03:33:33] please. Now, it should ask me for my contact
[03:33:35] contact information. There we go. So, Liam, I
[03:33:38] information. There we go. So, Liam, I mean, Liam at mail.
[03:33:41] mean, Liam at mail. Cool. And then we should see it appear
[03:33:43] Cool. And then we should see it appear over here on our Smith Solar
[03:33:46] over here on our Smith Solar CRM. And boom, there it is. So, we've
[03:33:49] CRM. And boom, there it is. So, we've got everything done. That is just one
[03:33:50] got everything done. That is just one run through of using this WhatsApp
[03:33:52] run through of using this WhatsApp agent. But as you can see, uh the the
[03:33:54] agent. But as you can see, uh the the messages don't come back instantly. So
[03:33:56] messages don't come back instantly. So it it feels like it is like it's
[03:33:58] it it feels like it is like it's actually could be a real human there
[03:33:59] actually could be a real human there applying and it's giving just clear
[03:34:01] applying and it's giving just clear information right through WhatsApp.
[03:34:03] information right through WhatsApp. Imagine you are reaching out to maybe
[03:34:04] Imagine you are reaching out to maybe book an accommodation or you're reaching
[03:34:06] book an accommodation or you're reaching out to a a cleaning service like this or
[03:34:08] out to a a cleaning service like this or you're reaching out to any kind of
[03:34:09] you're reaching out to any kind of business and you want some real
[03:34:10] business and you want some real information directly from what feels
[03:34:11] information directly from what feels like a person. And then you also have
[03:34:13] like a person. And then you also have the functions of getting a real quote of
[03:34:15] the functions of getting a real quote of I mean a great use case for this kind of
[03:34:17] I mean a great use case for this kind of thing is like barbers. Like I say, if
[03:34:18] thing is like barbers. Like I say, if you you message a barber on WhatsApp,
[03:34:20] you you message a barber on WhatsApp, maybe you're in in Europe somewhere,
[03:34:22] maybe you're in in Europe somewhere, you're in South America or you're in
[03:34:23] you're in South America or you're in Central America or and and you want to
[03:34:25] Central America or and and you want to go to a barber and this is a common
[03:34:27] go to a barber and this is a common issue that I've run into when I'm
[03:34:28] issue that I've run into when I'm traveling. It's like, I want to message
[03:34:29] traveling. It's like, I want to message this barber, but I might not speak the
[03:34:32] this barber, but I might not speak the language that well. And then if you
[03:34:33] language that well. And then if you message them in English, it will be able
[03:34:34] message them in English, it will be able to handle that in in English as well as
[03:34:36] to handle that in in English as well as in Spanish or in Portuguese or wherever
[03:34:38] in Spanish or in Portuguese or wherever you are. So, this kind of functionality
[03:34:39] you are. So, this kind of functionality built through WhatsApp is a really
[03:34:40] built through WhatsApp is a really really great use case for you guys to
[03:34:41] really great use case for you guys to pick up, which is why I wanted to teach
[03:34:43] pick up, which is why I wanted to teach you guys it. And we can also go back to
[03:34:45] you guys it. And we can also go back to agentive here. And if we go to our
[03:34:47] agentive here. And if we go to our transcripts for this agent, we can see
[03:34:50] transcripts for this agent, we can see the one for today is here. So 12
[03:34:51] the one for today is here. So 12 messages. You can go through the entire
[03:34:53] messages. You can go through the entire transcript and you can see it's calling
[03:34:54] transcript and you can see it's calling the quote tool here. We see all the
[03:34:56] the quote tool here. We see all the information that went in and out of it.
[03:34:57] information that went in and out of it. And then we see the air table lead
[03:34:59] And then we see the air table lead capture information as well. Input and
[03:35:00] capture information as well. Input and output. So that is how you use a genty
[03:35:02] output. So that is how you use a genty my software for building these WhatsApp
[03:35:04] my software for building these WhatsApp based and also other deployments as
[03:35:05] based and also other deployments as well. So if we go to studio and we go to
[03:35:07] well. So if we go to studio and we go to deploy, we have Instagram as well. So
[03:35:09] deploy, we have Instagram as well. So via our mini chat template. You can hook
[03:35:10] via our mini chat template. You can hook into Instagram and do appointment
[03:35:12] into Instagram and do appointment settings and things on Instagram. You
[03:35:13] settings and things on Instagram. You can go through Messenger if you want to
[03:35:14] can go through Messenger if you want to run some Facebook lead ads to Messenger
[03:35:17] run some Facebook lead ads to Messenger through voice flow as well. Telegram,
[03:35:18] through voice flow as well. Telegram, Discord, we have integrations with
[03:35:20] Discord, we have integrations with everything you need as well. So that's
[03:35:22] everything you need as well. So that's the end of this build. I hope you
[03:35:23] the end of this build. I hope you enjoyed and uh this is a super handy use
[03:35:25] enjoyed and uh this is a super handy use case um and and deployment really for
[03:35:27] case um and and deployment really for your AI
[03:35:32] agents. So now that you understand how
[03:35:34] agents. So now that you understand how AI agents works and can build them for
[03:35:36] AI agents works and can build them for yourself, let's talk about the most
[03:35:38] yourself, let's talk about the most important part of this, which is
[03:35:39] important part of this, which is actually making money with these skills.
[03:35:41] actually making money with these skills. But first, we need to destroy a huge
[03:35:43] But first, we need to destroy a huge misconception and that you don't need to
[03:35:45] misconception and that you don't need to build the next chat GBT or create some
[03:35:47] build the next chat GBT or create some revolutionary AI startup in order to
[03:35:49] revolutionary AI startup in order to make money in the AI space. The real
[03:35:51] make money in the AI space. The real opportunity is much much simpler. It's
[03:35:53] opportunity is much much simpler. It's just helping businesses to understand
[03:35:55] just helping businesses to understand and implement AI. This is how I
[03:35:57] and implement AI. This is how I monetized my AI agent skills and it has
[03:35:59] monetized my AI agent skills and it has been the most explosive growth I've ever
[03:36:01] been the most explosive growth I've ever experienced in my career. And the good
[03:36:03] experienced in my career. And the good news is, if you've made it this far in
[03:36:04] news is, if you've made it this far in the video, you are so much closer to
[03:36:06] the video, you are so much closer to being able to tap into this starving
[03:36:08] being able to tap into this starving market for AI services than you think.
[03:36:10] market for AI services than you think. But don't take my word for it. I'm just
[03:36:11] But don't take my word for it. I'm just some guy on the internet after all.
[03:36:13] some guy on the internet after all. Maybe you should listen to some of the
[03:36:14] Maybe you should listen to some of the world's most famous businessmen saying
[03:36:15] world's most famous businessmen saying that this is the opportunity to get into
[03:36:17] that this is the opportunity to get into right now. If I was 25 years old today
[03:36:19] right now. If I was 25 years old today in 2024, what would I do? What's a good
[03:36:22] in 2024, what would I do? What's a good sector to get involved in? What business
[03:36:24] sector to get involved in? What business would I get involved in? I think
[03:36:26] would I get involved in? I think everything is looking at AI now in a
[03:36:28] everything is looking at AI now in a different way. And I think AI growth is
[03:36:30] different way. And I think AI growth is going to be exponential. So, anything to
[03:36:32] going to be exponential. So, anything to do with AI now, what could that be? In
[03:36:34] do with AI now, what could that be? In the simplest form is helping people use
[03:36:36] the simplest form is helping people use the technology. there's going to be a
[03:36:38] the technology. there's going to be a massive amount of people wanting to use
[03:36:40] massive amount of people wanting to use it that don't know how to and they're
[03:36:41] it that don't know how to and they're willing to pay to solve that pain point.
[03:36:44] willing to pay to solve that pain point. So, is that consulting? Not really. It's
[03:36:47] So, is that consulting? Not really. It's implementation and execution. And so,
[03:36:50] implementation and execution. And so, helping a business do that transfer into
[03:36:52] helping a business do that transfer into a world where they're controlling their
[03:36:54] a world where they're controlling their data and getting information from it.
[03:36:56] data and getting information from it. Now, the majority of businesses in
[03:36:58] Now, the majority of businesses in America, for example, are between 5 and
[03:37:00] America, for example, are between 5 and 500 employees. So, they're small
[03:37:02] 500 employees. So, they're small businesses. They create 62% of the jobs.
[03:37:05] businesses. They create 62% of the jobs. They want to use AI. you should help
[03:37:07] They want to use AI. you should help them solve for that and they'll pay you.
[03:37:09] them solve for that and they'll pay you. Even another shark, Mark Cuban, is
[03:37:11] Even another shark, Mark Cuban, is saying the exact same thing that the
[03:37:13] saying the exact same thing that the biggest opportunity right now is helping
[03:37:14] biggest opportunity right now is helping these small to mediumsiz businesses who
[03:37:16] these small to mediumsiz businesses who don't understand AI yet, but desperately
[03:37:19] don't understand AI yet, but desperately need it to keep up. And they're
[03:37:20] need it to keep up. And they're absolutely right. If we look at the
[03:37:22] absolutely right. If we look at the data, it's pretty obvious. According to
[03:37:24] data, it's pretty obvious. According to recent data, there's 1.7 million
[03:37:26] recent data, there's 1.7 million businesses in the US alone that are
[03:37:27] businesses in the US alone that are making between $500,000 and $10 million
[03:37:30] making between $500,000 and $10 million per year. These are small businesses,
[03:37:32] per year. These are small businesses, which, as Kevin Oer says, make up 62% of
[03:37:35] which, as Kevin Oer says, make up 62% of the jobs in the USA. They create 62% of
[03:37:37] the jobs in the USA. They create 62% of the jobs. They want to use AI. You
[03:37:40] the jobs. They want to use AI. You should help them solve for that and
[03:37:41] should help them solve for that and they'll pay you. These businesses know
[03:37:43] they'll pay you. These businesses know they need AI to stay competitive, but
[03:37:45] they need AI to stay competitive, but they don't have the time to learn it
[03:37:46] they don't have the time to learn it themselves. And there's basically no one
[03:37:48] themselves. And there's basically no one there to help them. All of the big
[03:37:50] there to help them. All of the big consulting firms are looking at other
[03:37:52] consulting firms are looking at other big businesses and just leaving these
[03:37:53] big businesses and just leaving these smaller businesses completely ignored,
[03:37:55] smaller businesses completely ignored, but they still make lots of money and
[03:37:57] but they still make lots of money and they still have a lot of money to invest
[03:37:58] they still have a lot of money to invest in these kinds of services. Basically,
[03:38:00] in these kinds of services. Basically, all small businesses are starving for
[03:38:01] all small businesses are starving for some kind of AI services, either
[03:38:03] some kind of AI services, either education services to help them
[03:38:05] education services to help them understand what AI is in the first place
[03:38:06] understand what AI is in the first place and why they might need it. There's the
[03:38:08] and why they might need it. There's the huge need for consulting services where
[03:38:10] huge need for consulting services where you help them to identify where AI can
[03:38:12] you help them to identify where AI can help with them most in their particular
[03:38:13] help with them most in their particular business. And of course, there's
[03:38:15] business. And of course, there's implementation services where you help
[03:38:16] implementation services where you help them to build and maintain the AI
[03:38:18] them to build and maintain the AI systems like the AI agents we've just
[03:38:20] systems like the AI agents we've just built. And right now, based on the data
[03:38:21] built. And right now, based on the data collected in my community, and we are
[03:38:23] collected in my community, and we are the largest AI business community on the
[03:38:25] the largest AI business community on the planet right now, for every person or
[03:38:26] planet right now, for every person or agency that is currently offering AI
[03:38:28] agency that is currently offering AI services, there are over 1,100
[03:38:30] services, there are over 1,100 businesses in the USA alone that need
[03:38:32] businesses in the USA alone that need help. So, that's a 1 to 1,100 ratio,
[03:38:35] help. So, that's a 1 to 1,100 ratio, which means this is a completely
[03:38:37] which means this is a completely untapped market. And that's where people
[03:38:38] untapped market. And that's where people like you and I come in, helping these
[03:38:40] like you and I come in, helping these hardworking small business owners to
[03:38:41] hardworking small business owners to understand AI and implement it so that
[03:38:44] understand AI and implement it so that they have a chance to keep up. And
[03:38:45] they have a chance to keep up. And that's really what drives me and the
[03:38:46] that's really what drives me and the team at Morningside because our company
[03:38:48] team at Morningside because our company vision is a world where the benefits of
[03:38:50] vision is a world where the benefits of generative AI are distributed as fairly
[03:38:52] generative AI are distributed as fairly as possible and they make it to people
[03:38:53] as possible and they make it to people like me and you and the small business
[03:38:56] like me and you and the small business owners rather than just all going to
[03:38:57] owners rather than just all going to these giants at the top. And this whole
[03:38:58] these giants at the top. And this whole concept of selling services around an
[03:39:00] concept of selling services around an emerging technology is nothing new. And
[03:39:02] emerging technology is nothing new. And we saw the exact same pattern when the
[03:39:04] we saw the exact same pattern when the internet first came out. Companies that
[03:39:05] internet first came out. Companies that helped businesses to adapt to the web
[03:39:07] helped businesses to adapt to the web and sort of get online made fortunes.
[03:39:09] and sort of get online made fortunes. You know, agency.com, Razerfish, etc.
[03:39:11] You know, agency.com, Razerfish, etc. And I spotted this opportunity within
[03:39:13] And I spotted this opportunity within the AI space in 2023 when it wasn't
[03:39:15] the AI space in 2023 when it wasn't anywhere near as clear as it was now. No
[03:39:17] anywhere near as clear as it was now. No one really knew how to make money out of
[03:39:18] one really knew how to make money out of this stuff. And then I started Morning
[03:39:20] this stuff. And then I started Morning Side AI. And since then, we've generated
[03:39:22] Side AI. And since then, we've generated over $5 million in selling these kinds
[03:39:24] over $5 million in selling these kinds of AI services of education, consulting,
[03:39:26] of AI services of education, consulting, and implementation. And we're literally
[03:39:28] and implementation. And we're literally still only just getting started. And the
[03:39:30] still only just getting started. And the best part out of all of this is that as
[03:39:31] best part out of all of this is that as we've proved in this video already, you
[03:39:33] we've proved in this video already, you don't need to be a technical genius to
[03:39:35] don't need to be a technical genius to understand AI and even to build AI
[03:39:37] understand AI and even to build AI agents. You just need to be one step
[03:39:39] agents. You just need to be one step ahead of the businesses that you're
[03:39:41] ahead of the businesses that you're going to be helping. So, let me show you
[03:39:42] going to be helping. So, let me show you the three specific ways that you can
[03:39:44] the three specific ways that you can start making money with your AI agent
[03:39:47] start making money with your AI agent skills. So, as I said, there's basically
[03:39:49] skills. So, as I said, there's basically three types of services that you can
[03:39:51] three types of services that you can provide to businesses in order to
[03:39:52] provide to businesses in order to monetize your skills. Firstly, there's
[03:39:54] monetize your skills. Firstly, there's education, and this is teaching
[03:39:56] education, and this is teaching businesses about AI, running workshops,
[03:39:58] businesses about AI, running workshops, and doing presentations, training their
[03:40:00] and doing presentations, training their teams, and creating courses for them to
[03:40:01] teams, and creating courses for them to watch. Businesses are desperate for
[03:40:03] watch. Businesses are desperate for someone who can explain what this stuff
[03:40:05] someone who can explain what this stuff is in simple terms and more importantly
[03:40:07] is in simple terms and more importantly what it can do for them. After watching
[03:40:08] what it can do for them. After watching this video and probably my other huge
[03:40:11] this video and probably my other huge video that I did on AI agents, which
[03:40:12] video that I did on AI agents, which I'll link down below, um you will know
[03:40:14] I'll link down below, um you will know more than enough to start educating
[03:40:16] more than enough to start educating businesses on AI and AI agents. Secondly
[03:40:18] businesses on AI and AI agents. Secondly is consulting. And this is where you
[03:40:20] is consulting. And this is where you analyze a business's operations and you
[03:40:21] analyze a business's operations and you show them where AI can help them save
[03:40:23] show them where AI can help them save time or make more money. You're
[03:40:25] time or make more money. You're essentially being their AI strategist.
[03:40:27] essentially being their AI strategist. For example, you could go into a
[03:40:29] For example, you could go into a business and then recommend something
[03:40:30] business and then recommend something like the sales co-pilot system that we
[03:40:32] like the sales co-pilot system that we just made in order to help their
[03:40:34] just made in order to help their struggling sales department. And third
[03:40:35] struggling sales department. And third is implementation. So this is where you
[03:40:37] is implementation. So this is where you actually build and deploy AI solutions
[03:40:39] actually build and deploy AI solutions for businesses. Or better yet, like my
[03:40:41] for businesses. Or better yet, like my agency, you can do all three of these,
[03:40:43] agency, you can do all three of these, but it did take us 2 years to get here.
[03:40:45] but it did take us 2 years to get here. So there is really no rush. You just
[03:40:46] So there is really no rush. You just pick where you want to enter and work
[03:40:48] pick where you want to enter and work your way up to doing more and more if it
[03:40:49] your way up to doing more and more if it makes sense. Believe it or not, there
[03:40:51] makes sense. Believe it or not, there are people with only a few months
[03:40:52] are people with only a few months experience in the AI space selling all
[03:40:54] experience in the AI space selling all of these right now. And the demand from
[03:40:56] of these right now. And the demand from businesses is increasing insanely fast
[03:40:58] businesses is increasing insanely fast right now. I we're seeing this at
[03:40:59] right now. I we're seeing this at Morningside. Just so many more
[03:41:00] Morningside. Just so many more businesses reaching out. But here's the
[03:41:02] businesses reaching out. But here's the thing. You have one small problem, and
[03:41:04] thing. You have one small problem, and that's that you don't quite know enough
[03:41:06] that's that you don't quite know enough to start moving on this. You are close,
[03:41:08] to start moving on this. You are close, but you're not quite there. The way to
[03:41:09] but you're not quite there. The way to make money in the AI space or with any
[03:41:11] make money in the AI space or with any services really is to create a knowledge
[03:41:13] services really is to create a knowledge gap between yourself and the people that
[03:41:15] gap between yourself and the people that you're helping. Your knowledge gap is
[03:41:17] you're helping. Your knowledge gap is your money maker, and businesses will
[03:41:18] your money maker, and businesses will pay you in proportion to how much more
[03:41:20] pay you in proportion to how much more you know about AI agents and their
[03:41:22] you know about AI agents and their business applications than they do. Now,
[03:41:24] business applications than they do. Now, while this video has taught you a lot,
[03:41:26] while this video has taught you a lot, your knowledge gap is still small. But
[03:41:28] your knowledge gap is still small. But we can fix
[03:41:30] we can fix that. So, let me break down exactly what
[03:41:33] that. So, let me break down exactly what you need to do next in order to extend
[03:41:34] you need to do next in order to extend your knowledge gap to the point where
[03:41:35] your knowledge gap to the point where you can start making money. We can call
[03:41:37] you can start making money. We can call this video as step one. So, as long as
[03:41:39] this video as step one. So, as long as you've taken notes and followed all the
[03:41:40] you've taken notes and followed all the tutorials and built the agents alongside
[03:41:42] tutorials and built the agents alongside me, you're already ahead of most people
[03:41:44] me, you're already ahead of most people who have no idea about what agents are,
[03:41:46] who have no idea about what agents are, how they work, or how to build them. So,
[03:41:47] how they work, or how to build them. So, it's a big step forward with this video.
[03:41:49] it's a big step forward with this video. But step two is building even more
[03:41:52] But step two is building even more experience building AI agents. So you
[03:41:54] experience building AI agents. So you are more familiar with the platforms and
[03:41:55] are more familiar with the platforms and better understand the different ways
[03:41:57] better understand the different ways that they can be used to deliver
[03:41:58] that they can be used to deliver different kinds of AI agent use cases or
[03:42:00] different kinds of AI agent use cases or even just AI tools in general. I've only
[03:42:03] even just AI tools in general. I've only really given you a taster here, but I
[03:42:04] really given you a taster here, but I tried to make it as as diverse as
[03:42:06] tried to make it as as diverse as possible as you could probably tell. In
[03:42:07] possible as you could probably tell. In order to do this second step of
[03:42:09] order to do this second step of extending your knowledge gap further and
[03:42:10] extending your knowledge gap further and building more experience, you can go to
[03:42:12] building more experience, you can go to my free course on school where you'll be
[03:42:14] my free course on school where you'll be able to build another 5 to 10 agents
[03:42:15] able to build another 5 to 10 agents following the tutorials that are in
[03:42:17] following the tutorials that are in there for you. So the link to join my
[03:42:18] there for you. So the link to join my free school will be in the description.
[03:42:20] free school will be in the description. So, if you blast through all those
[03:42:21] So, if you blast through all those tutorials in there, this is going to
[03:42:22] tutorials in there, this is going to further expand your knowledge gap. And
[03:42:24] further expand your knowledge gap. And remember that the more that you know
[03:42:26] remember that the more that you know compared to the businesses that you're
[03:42:27] compared to the businesses that you're trying to help, the more they're going
[03:42:28] trying to help, the more they're going to pay you. So, step two is building a
[03:42:30] to pay you. So, step two is building a few more agents out and getting a bit
[03:42:32] few more agents out and getting a bit more experience on the tools, seeing
[03:42:33] more experience on the tools, seeing different use cases, etc. And once
[03:42:35] different use cases, etc. And once you've done that, you'll have what I
[03:42:37] you've done that, you'll have what I call foundational knowledge. So, you
[03:42:38] call foundational knowledge. So, you understand the core AI concepts that
[03:42:40] understand the core AI concepts that we've been through in this video. You
[03:42:42] we've been through in this video. You can build basic solutions on these
[03:42:43] can build basic solutions on these platforms. You know what's possible for
[03:42:45] platforms. You know what's possible for businesses with agents right now. And
[03:42:46] businesses with agents right now. And then comes the big decision. Do you want
[03:42:49] then comes the big decision. Do you want to go deeper technically on this
[03:42:50] to go deeper technically on this building side of getting your hands
[03:42:52] building side of getting your hands dirty or do you want to start monetizing
[03:42:54] dirty or do you want to start monetizing what you already know? As we've covered,
[03:42:56] what you already know? As we've covered, the building and implementing of the AI
[03:42:58] the building and implementing of the AI systems is only one of the services that
[03:42:59] systems is only one of the services that you can sell. So naturally, the
[03:43:02] you can sell. So naturally, the technical skills needed in order to make
[03:43:03] technical skills needed in order to make money in the implementation services.
[03:43:06] money in the implementation services. Actually building these systems and
[03:43:07] Actually building these systems and businesses is much more greater than
[03:43:09] businesses is much more greater than just having a foundation. But with a
[03:43:10] just having a foundation. But with a good foundation, you're basically ready
[03:43:12] good foundation, you're basically ready to start having a crack at the other two
[03:43:14] to start having a crack at the other two services of AI education and AI
[03:43:16] services of AI education and AI consulting. So, the decision of what to
[03:43:18] consulting. So, the decision of what to do next comes down to really knowing who
[03:43:19] do next comes down to really knowing who you are and what you are really
[03:43:21] you are and what you are really interested in. And this sounds all woo
[03:43:22] interested in. And this sounds all woo woo and like, oh, you got to know
[03:43:24] woo and like, oh, you got to know yourself and stuff, but this is I mean
[03:43:27] yourself and stuff, but this is I mean it very very seriously in that if I use
[03:43:29] it very very seriously in that if I use myself an example, I've always loved
[03:43:31] myself an example, I've always loved making things, right? I used to build
[03:43:32] making things, right? I used to build block houses with kids. I used to like
[03:43:34] block houses with kids. I used to like brew beer with my grandpa. I've always
[03:43:36] brew beer with my grandpa. I've always loved tinkering with engines. So when I
[03:43:37] loved tinkering with engines. So when I hit this foundational level that you
[03:43:39] hit this foundational level that you guys will be at after completing those
[03:43:40] guys will be at after completing those extra builds in the free course, I kind
[03:43:42] extra builds in the free course, I kind of naturally just dove deeper into the
[03:43:44] of naturally just dove deeper into the technical side into building more stuff.
[03:43:45] technical side into building more stuff. I I kept building more and more complex
[03:43:47] I I kept building more and more complex AI systems and building upon those
[03:43:49] AI systems and building upon those skills that I've I've built already,
[03:43:51] skills that I've I've built already, which led me ultimately to starting
[03:43:52] which led me ultimately to starting Morningside AI where our first service
[03:43:54] Morningside AI where our first service was building AI solutions and systems
[03:43:56] was building AI solutions and systems for clients. But here's the thing, of
[03:43:58] for clients. But here's the thing, of course, a lot of people aren't like me.
[03:43:59] course, a lot of people aren't like me. They don't get as much of a buzz out of
[03:44:01] They don't get as much of a buzz out of building things. many of you are going
[03:44:02] building things. many of you are going to be much better or enjoy more the
[03:44:05] to be much better or enjoy more the teaching aspect or working with people
[03:44:06] teaching aspect or working with people and doing the consulting aspect rather
[03:44:08] and doing the consulting aspect rather than building stuff. So in these cases
[03:44:10] than building stuff. So in these cases using the foundational knowledge that
[03:44:12] using the foundational knowledge that you're going to build up to sell AI
[03:44:13] you're going to build up to sell AI education to businesses or AI consulting
[03:44:16] education to businesses or AI consulting makes a lot more sense. Goes back to the
[03:44:17] makes a lot more sense. Goes back to the whole Einstein thing about like judging
[03:44:19] whole Einstein thing about like judging a fish on its ability to climb a tree.
[03:44:21] a fish on its ability to climb a tree. If to you the building is like a tree
[03:44:22] If to you the building is like a tree and you feel like a fish and it's not a
[03:44:23] and you feel like a fish and it's not a really good fit, then there's better
[03:44:25] really good fit, then there's better stuff that you can do and you can find a
[03:44:26] stuff that you can do and you can find a way to make money in the AI space that
[03:44:28] way to make money in the AI space that leans more into your strengths. like in
[03:44:30] leans more into your strengths. like in the case of a fish would be swimming,
[03:44:32] the case of a fish would be swimming, right? So, by being honest with yourself
[03:44:33] right? So, by being honest with yourself and saying, "Hey, look, that's not
[03:44:34] and saying, "Hey, look, that's not really me. Yeah, sure, I did get it
[03:44:36] really me. Yeah, sure, I did get it done. I know how that works now, but I
[03:44:38] done. I know how that works now, but I don't feel any kind of attraction to
[03:44:39] don't feel any kind of attraction to doing more of that." While you may see
[03:44:41] doing more of that." While you may see that as a negative and saying like, "Oh,
[03:44:42] that as a negative and saying like, "Oh, I don't have what it takes." It's
[03:44:43] I don't have what it takes." It's actually can be very empowering if you
[03:44:45] actually can be very empowering if you say, "Bang, I'm stopping it here. I'm
[03:44:47] say, "Bang, I'm stopping it here. I'm stopping the learning. I'm stopping the
[03:44:48] stopping the learning. I'm stopping the procrastination. Now, I'm going straight
[03:44:50] procrastination. Now, I'm going straight into actually monetizing." It's
[03:44:51] into actually monetizing." It's basically putting a stop on when you do
[03:44:53] basically putting a stop on when you do this learning big long phase and saying,
[03:44:55] this learning big long phase and saying, "No, action starts now. I'm not I'm
[03:44:57] "No, action starts now. I'm not I'm never going to get there, but with this
[03:44:59] never going to get there, but with this base, I can do a lot and I'm going to
[03:45:00] base, I can do a lot and I'm going to start taking action with it and making
[03:45:02] start taking action with it and making money with it today. So, this
[03:45:03] money with it today. So, this self-reflection is really what prevents
[03:45:04] self-reflection is really what prevents you from getting stuck in an endless
[03:45:06] you from getting stuck in an endless learning phase of procrastination when
[03:45:08] learning phase of procrastination when you could be out there making money. So,
[03:45:09] you could be out there making money. So, in summary, the two routes you have and
[03:45:11] in summary, the two routes you have and the two options you have from here are
[03:45:13] the two options you have from here are if you love building and you kind of
[03:45:15] if you love building and you kind of naturally feel like you want to learn
[03:45:17] naturally feel like you want to learn more like like myself when I was at your
[03:45:19] more like like myself when I was at your stage, then just keep going. go and
[03:45:21] stage, then just keep going. go and watch the free course tutorials on my
[03:45:22] watch the free course tutorials on my school and then start going and building
[03:45:24] school and then start going and building your own projects and ones for friends
[03:45:25] your own projects and ones for friends and family and whatever you you sort of
[03:45:27] and family and whatever you you sort of pulled towards naturally and within two
[03:45:29] pulled towards naturally and within two to three months you'll have enough
[03:45:30] to three months you'll have enough skills and experience to actually start
[03:45:32] skills and experience to actually start selling implementation properly. But on
[03:45:34] selling implementation properly. But on the other hand, if you haven't fallen in
[03:45:35] the other hand, if you haven't fallen in love with the building aspect, then it's
[03:45:37] love with the building aspect, then it's probably best that you just go go into
[03:45:39] probably best that you just go go into the free course, smash out the rest of
[03:45:40] the free course, smash out the rest of those tutorials and finish your
[03:45:42] those tutorials and finish your foundation and then just get started on
[03:45:44] foundation and then just get started on monetizing your skills either through
[03:45:45] monetizing your skills either through selling AI education or through selling
[03:45:47] selling AI education or through selling AI consulting.
[03:45:50] AI consulting. So once you're clear on what kind of AI
[03:45:52] So once you're clear on what kind of AI services you want to sell, getting your
[03:45:54] services you want to sell, getting your first few clients is actually pretty
[03:45:55] first few clients is actually pretty straightforward. People try to over
[03:45:56] straightforward. People try to over complicate it, but there's really just
[03:45:58] complicate it, but there's really just two main ways that I'd recommend you do
[03:45:59] two main ways that I'd recommend you do this based off all the success I've seen
[03:46:00] this based off all the success I've seen over thousand thousands of people across
[03:46:02] over thousand thousands of people across my free and paid communities. The first
[03:46:04] my free and paid communities. The first and by far the easiest method is through
[03:46:05] and by far the easiest method is through your warm connections or warm contacts.
[03:46:07] your warm connections or warm contacts. This means reaching out to people that
[03:46:08] This means reaching out to people that you already have some kind of
[03:46:09] you already have some kind of relationship with, whether it's friends
[03:46:11] relationship with, whether it's friends or family or kind of acquaintances or
[03:46:13] or family or kind of acquaintances or even friends of friends that you've met
[03:46:14] even friends of friends that you've met once kind of thing. All of these people
[03:46:16] once kind of thing. All of these people count as warm connections. So instead of
[03:46:17] count as warm connections. So instead of trying to convince complete strangers to
[03:46:19] trying to convince complete strangers to trust you with your business, you can
[03:46:20] trust you with your business, you can start with people that you already know
[03:46:22] start with people that you already know or have some previous relationship with
[03:46:23] or have some previous relationship with and therefore have an increased level of
[03:46:25] and therefore have an increased level of trust with you through your
[03:46:26] trust with you through your relationship. And I've covered this
[03:46:28] relationship. And I've covered this many, many times on the channel before.
[03:46:30] many, many times on the channel before. So on the school post for this video, I
[03:46:31] So on the school post for this video, I will add in my complete guides for warm
[03:46:33] will add in my complete guides for warm outreach, including resources directly
[03:46:35] outreach, including resources directly from my AAA accelerator program. The
[03:46:36] from my AAA accelerator program. The second way is using what I call the
[03:46:38] second way is using what I call the community content flywheel. So this is
[03:46:40] community content flywheel. So this is how you can build long-term momentum
[03:46:42] how you can build long-term momentum beyond just warm outreach. So here's how
[03:46:43] beyond just warm outreach. So here's how it works. You join the free school
[03:46:46] it works. You join the free school community. you start making content
[03:46:47] community. you start making content about what you're learning at each
[03:46:48] about what you're learning at each stage. This could be through YouTube
[03:46:49] stage. This could be through YouTube tutorials, which I mean that worked for
[03:46:51] tutorials, which I mean that worked for me. LinkedIn post is another one um or
[03:46:53] me. LinkedIn post is another one um or whatever platform you really prefer to
[03:46:55] whatever platform you really prefer to create content on. But here's the key.
[03:46:57] create content on. But here's the key. You share that content back into the
[03:46:59] You share that content back into the community. So with over 120,000 members,
[03:47:03] community. So with over 120,000 members, by posting it into the community, you
[03:47:05] by posting it into the community, you get an instant audience and people who
[03:47:06] get an instant audience and people who are really interested in the stuff that
[03:47:08] are really interested in the stuff that you're talking about. So, a perfect
[03:47:09] you're talking about. So, a perfect example of this is a guy called Rory
[03:47:11] example of this is a guy called Rory Ridges, a a young guy from the UK who
[03:47:13] Ridges, a a young guy from the UK who joined my free community and basically
[03:47:14] joined my free community and basically followed this exact process that I've
[03:47:16] followed this exact process that I've told you in this video so far. So, he
[03:47:17] told you in this video so far. So, he took my free course, he learned all the
[03:47:19] took my free course, he learned all the basics, built his foundation, then he
[03:47:21] basics, built his foundation, then he started posting simple tutorials on
[03:47:23] started posting simple tutorials on relevance AI, which you've used in this
[03:47:25] relevance AI, which you've used in this video already, and he literally just
[03:47:26] video already, and he literally just started sharing what he'd learned from
[03:47:28] started sharing what he'd learned from my videos and making other videos about
[03:47:29] my videos and making other videos about it. And at the start, he was literally
[03:47:31] it. And at the start, he was literally just sharing what he'd learned from my
[03:47:32] just sharing what he'd learned from my videos. So, he'd watch a video, then go
[03:47:34] videos. So, he'd watch a video, then go and kind of make his own video on the
[03:47:35] and kind of make his own video on the same sort of topic. And every time he
[03:47:37] same sort of topic. And every time he made a tutorial, he'd then share it into
[03:47:39] made a tutorial, he'd then share it into the community and the community would
[03:47:41] the community and the community would watch it. They'd give him feedback, go
[03:47:42] watch it. They'd give him feedback, go and subscribe to his channel. This not
[03:47:44] and subscribe to his channel. This not only helped him grow faster on YouTube,
[03:47:45] only helped him grow faster on YouTube, but it also started to position himself
[03:47:47] but it also started to position himself as an expert in the community. And he's
[03:47:49] as an expert in the community. And he's also building his authority in the AI
[03:47:50] also building his authority in the AI agency space by getting more momentum on
[03:47:52] agency space by getting more momentum on YouTube. Now, his YouTube channel brings
[03:47:54] YouTube. Now, his YouTube channel brings him in enough leads to support his
[03:47:55] him in enough leads to support his growing agency. And I've just seen him
[03:47:57] growing agency. And I've just seen him recently in the community saying he's
[03:47:58] recently in the community saying he's hiring. So, that's usually a bloody good
[03:48:00] hiring. So, that's usually a bloody good sign that he's making some good money
[03:48:01] sign that he's making some good money off the back of it. He basically started
[03:48:02] off the back of it. He basically started the same flywheel that took me from zero
[03:48:04] the same flywheel that took me from zero to where I am now. Over $5 million in
[03:48:07] to where I am now. Over $5 million in revenue generated across all my
[03:48:08] revenue generated across all my businesses and $450,000 plus subscribers
[03:48:11] businesses and $450,000 plus subscribers in just two years. And so the community
[03:48:13] in just two years. And so the community gives you an audience and the content
[03:48:15] gives you an audience and the content gives you credibility and together this
[03:48:17] gives you credibility and together this method brings you clients. In the
[03:48:18] method brings you clients. In the resources for this video on school, I
[03:48:20] resources for this video on school, I will leave links to my complete guide
[03:48:22] will leave links to my complete guide for creating content to generate leads
[03:48:23] for creating content to generate leads just like Rory and I have done
[03:48:25] just like Rory and I have done successfully. And of course, I'll
[03:48:26] successfully. And of course, I'll include a link to Rory's channel in the
[03:48:28] include a link to Rory's channel in the resources in the school community. Now,
[03:48:29] resources in the school community. Now, the really important thing to notice
[03:48:30] the really important thing to notice with both of these methods we've just
[03:48:32] with both of these methods we've just talked about, the warm outreach and the
[03:48:34] talked about, the warm outreach and the uh community content flywheel is that
[03:48:36] uh community content flywheel is that both of these methods start with giving
[03:48:37] both of these methods start with giving value first. Whether it's helping your
[03:48:40] value first. Whether it's helping your warm connections to understand AI or
[03:48:41] warm connections to understand AI or sharing your knowledge through content,
[03:48:43] sharing your knowledge through content, you have to give before you start to
[03:48:47] you have to give before you start to get. Now, I know all of this businessy
[03:48:49] get. Now, I know all of this businessy stuff may feel a little bit overwhelming
[03:48:50] stuff may feel a little bit overwhelming or out of reach for some of you, but
[03:48:52] or out of reach for some of you, but you'll seriously be amazed at what baby
[03:48:55] you'll seriously be amazed at what baby steps add up to in the AI space. you've
[03:48:57] steps add up to in the AI space. you've already taken the first step by watching
[03:48:58] already taken the first step by watching this and following through to the end of
[03:49:00] this and following through to the end of the video. So, congratulations on that
[03:49:02] the video. So, congratulations on that and I seriously seriously want to give
[03:49:04] and I seriously seriously want to give you a pat on the back and you should
[03:49:05] you a pat on the back and you should give one to yourself. But all you need
[03:49:06] give one to yourself. But all you need to do from now is to keep this momentum
[03:49:08] to do from now is to keep this momentum going. The next step for all of you is
[03:49:11] going. The next step for all of you is pretty damn clear. You need to jump in
[03:49:13] pretty damn clear. You need to jump in the free community. That's by far the
[03:49:14] the free community. That's by far the best place if you're moderately
[03:49:16] best place if you're moderately interested in doing any of this stuff.
[03:49:17] interested in doing any of this stuff. My community is the number one place to
[03:49:18] My community is the number one place to go. It is 100% free to get into. And
[03:49:20] go. It is 100% free to get into. And once you're in there, drop an
[03:49:21] once you're in there, drop an introduction post saying who you are,
[03:49:23] introduction post saying who you are, what you're about, why you want to do
[03:49:24] what you're about, why you want to do this. Then start working your way
[03:49:25] this. Then start working your way through my free course material. I've
[03:49:27] through my free course material. I've poured everything I've learned about AI
[03:49:29] poured everything I've learned about AI and AI business into videos like these.
[03:49:31] and AI business into videos like these. And on the free course, they're all
[03:49:32] And on the free course, they're all there in a nice sequence for you to work
[03:49:33] there in a nice sequence for you to work through on school. And each time you
[03:49:35] through on school. And each time you complete a video and you complete the
[03:49:37] complete a video and you complete the tutorial, you can click the little check
[03:49:38] tutorial, you can click the little check box so that you can keep stacking those
[03:49:40] box so that you can keep stacking those small wins and those baby steps towards
[03:49:41] small wins and those baby steps towards AI literacy and succeeding in the space.
[03:49:43] AI literacy and succeeding in the space. All of the resources mentioned in the
[03:49:45] All of the resources mentioned in the selling part of this video will be on
[03:49:46] selling part of this video will be on the school post for this video. So you
[03:49:48] the school post for this video. So you go into school, you go to the YouTube
[03:49:49] go into school, you go to the YouTube resources tab, and then this video will
[03:49:51] resources tab, and then this video will be right there. So don't forget to check
[03:49:52] be right there. So don't forget to check all those out. And of course, all of the
[03:49:54] all those out. And of course, all of the resources for the tutorials, if you
[03:49:56] resources for the tutorials, if you haven't already done them, are included
[03:49:57] haven't already done them, are included on those posts as well. And finally, if
[03:49:59] on those posts as well. And finally, if you made it this far, could you please
[03:50:00] you made it this far, could you please do me a favor, leave a like on the
[03:50:02] do me a favor, leave a like on the video, and drop a comment down below.
[03:50:04] video, and drop a comment down below. Let me know what you like the most, what
[03:50:05] Let me know what you like the most, what you want to see more of. Click the share
[03:50:06] you want to see more of. Click the share button, send it to your friends and
[03:50:08] button, send it to your friends and family and loved ones so they can start
[03:50:09] family and loved ones so they can start learning these skills, too. All of these
[03:50:11] learning these skills, too. All of these actions really help my video to reach
[03:50:12] actions really help my video to reach more people in the YouTube algorithm.
[03:50:13] more people in the YouTube algorithm. And if you subscribe to the channel,
[03:50:15] And if you subscribe to the channel, you'll be able to see a lot more content
[03:50:16] you'll be able to see a lot more content like this helping you to understand AI
[03:50:18] like this helping you to understand AI and more so how to build businesses
[03:50:20] and more so how to build businesses around this incredible opportunity. And
[03:50:22] around this incredible opportunity. And if you're still hungry for more and you
[03:50:23] if you're still hungry for more and you want to watch my complete guide to
[03:50:24] want to watch my complete guide to building an AI business, that's going to
[03:50:26] building an AI business, that's going to be linked up here. But that is all for
[03:50:28] be linked up here. But that is all for the video. I'm so excited for you to get
[03:50:30] the video. I'm so excited for you to get cracking on this. I sincerely hope
[03:50:32] cracking on this. I sincerely hope you've got something out of this because
[03:50:33] you've got something out of this because I put a lot of work into it as did my
[03:50:34] I put a lot of work into it as did my team. So I'm just really really wishing
[03:50:36] team. So I'm just really really wishing you all all the all all the best. I'll
[03:50:37] you all all the all all the best. I'll see you in the next one.