00:02In a world being transformed by AI, one skill stands above all others: AI automation

00:04Master this, and you won't just survive the AI revolution, you'll thrive in it

00:07I'm living proof of this

00:10Just two years ago, I taught myself how to build no-code AI automations without any prior experience

00:12And since then, I've built multiple AI businesses, generated millions of dollars in revenue, and grown this channel to over 500,000 subscribers, and built AI systems for some of the biggest brands in the world

00:18It's pretty safe to say that learning how to build AI automations has completely changed my life

00:24So, in this full course, I'll teach you everything that I've learned about building AI automations and making money with them

00:28them, even if you don't know how to code

00:32And as they say, AI will not replace you, but the person using AI will

00:36So, my hope is that with this video, you too can learn this incredibly powerful skill to build the life of your dreams before it's too late

00:42And as you can tell by the length of this video, I'm not going to be holding anything back

00:48So, I've split it into three different chapters

00:54Firstly, we'll build your foundational understanding of AI automation, covering what it actually is, the different types of AI automations, how they work under the hood, and the key concepts you need to know before we start building

01:00There's no technical background required to understand any of what I'm going to teach you there

01:05Secondly, we'll dive deep into building out actual AI automations, taking you over my shoulder every step of the way as we build some of the most in-demand AI automation use cases in the market today

01:11This includes building things like cutting-edge voice agents, too

01:17And in the third and final chapter, I'll be giving you my proven blueprint for monetizing your AI automation skills while this technology explodes

01:24I'll share the exact strategies that I've used to generate millions of dollars with this skill set

01:31So, if you're new to the channel and don't know who I am, let me quickly share why I am qualified to teach you about AI automations in the first place

01:36So, my name is Liam Mley, and just two years ago, I started Learning AI with no prior experience in the field

01:42Teaching myself how to build AI automations and chatbots through my own self-study, which I documented here on this YouTube channel from day one

01:47This led me to starting Morningside AI, my AI automation agency, where we build AI systems and agents for businesses, from basic customer support systems when we started to now full AI SaaS platforms for some of the biggest brands in the world

01:53And I also have my own AI SaaS called Agentive, which has over 70,000 users on it

01:59At Morningside AI, we've worked with publicly traded companies and even an NBA team recently

02:05And I also run the world's largest AI automation and business community with over 180,000 members on Skool

02:12So through this community and my YouTube channel, I've taught hundreds of thousands of people from all backgrounds how to build and make money from AI automation

02:19And everything I'm about to teach you today is exactly what helped me to achieve all of this

02:22So let's dive in

02:25So there's a lot to cover here

02:28I don't want you to give up halfway

02:31So let's quickly get clear on why learning AI automation is one of the most valuable skills anyone can have over the coming decade, whether you're a student, an employee, or an entrepreneur

02:36Here's some quick truths about AI and jobs

02:40McKenzie predicts that AI and automation can replace up to 50% of current work activities by 2030, and the World Economic Forum states that 41% of Companies plan to reduce staff due to AI

02:45Now, this is a lot of doom and gloom, and many are naturally worried about their career in the future when they hear this stuff, but it's not actually all bad if you know where to look

02:56So, on the flip side of this same data, these same reports reveal an enormous opportunity for those willing to seize it

03:02The World Economic Forum's future of jobs report states that 50% of employees plan to reorient their business in response to artificial intelligence, and 66% of employees plan to hire talent with specific AI skills, such as AI workflow automation

03:15So, on one hand, we have the expectation of massive layoffs and automation of work over the next 5 to 10 years, but on the other, we have the majority of employers searching for people who have AI skills or really just some form of basic AI literacy

03:26Why is this? Well, it's because AI literate individuals who can identify opportunities for automation and automate them themselves can have five to ten times the output of someone who doesn't know this and can't automate their own work

03:38And I promise you that brushing up on your AI and actually becoming AI literate so that you can be on the winning side of this next five to ten years is so much easier than you think

03:43I mean, it's it's literally as easy as watching this entire video in order to build your AI skills base

03:49If you don't believe me when I say that a little bit of self-study like this video goes a long way, here is an Excellent clip from the All-In podcast from one of the most respected investors and technologists in the world, Naval Ravikant, alongside a whole bunch of other biners

03:59Again, I would say the easiest way to see that AI is not taking jobs or creating opportunities is go brush up on your AI, 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

04:07This video is exactly what Naval is talking about

04:15This is why I create these

04:22So whether you're a student wanting to stand out in a competitive job market, or an employee aiming to become irreplaceable at work, or an entrepreneur like me looking to scale your business with cutting-edge tools

04:28And automations, I have made this video for you

04:35Now, close out of all your other tabs, get a notebook and a pen and a beverage of your choice, and make a commitment right now to yourself to finish this training and to ensure that you're going to be empowered by AI and not replaced by it

04:39That is all I want out of this video for you all

04:43So, if you've done all that, let's get stuck into it

04:46All right

04:50So, step one in building AI automations is knowing what an automation actually is

04:53And the term gets thrown around a lot these days

04:56First thing we need to realize is that the AI part of the term is, is relatively new

04:59Automation itself has been around for a long time

05:02So, let's start there to make this super easy to grasp

05:05In simple terms, an Automation is a system that does a task for you without you having to lift a finger

05:10It's kind of like setting up a little robot to do boring, repetitive stuff automatically, so you don't have to waste your time on it

05:14These are what we'll call old-school automation, the kind that existed way before ChatGPT came along

05:18They were often built on platforms like Zapier, and lots of small to medium-sized businesses used them for the past 5, 10 years

05:22And they did basic things like automatically saving info

05:27For example, when someone filled out a form on a website, you could make an automation that would take their name and their email and then just pop it into a spreadsheet

05:32So, just a little automation, automating that boring stuff

05:36Or for example, when an email came in, it would send a quick alert to a chat app like Slack

05:40So it's kind of like having a little helper who's following a super simple checklist

05:43If this happens, then do that

05:47No thinking, just just doing, right? And the benefit of this is huge

05:49It freed humans from doing super basic and boring work

05:52And for business owners, it meant not having to pay more people just to handle these tiny and annoying tasks

05:55It's kind of like having a tireless assistant who never complains about doing the same boring thing over and over and over again

06:01So for decades, all was well in the automation space

06:06And these old school automation saved time and money, and everyone was super happy

06:12That was Until the release of ChatGPT in late 2022, it blew the entire field wide open, turning automation from some niche trick used by some savvy companies into the biggest thing since the internet

06:18Generative AI models like ChatGPT added to automation was like putting a V12 onto a bicycle for this automation space

06:24They made it possible to do more than just simple tasks because these powerful AI models could handle much trickier stuff that used to require a human brain

06:34Instead of just updating a spreadsheet row automatically, these automation platforms can now use the power of ChatGPT to do things that only people could have done before

06:40So platforms like Make.com, which you'll be learning more about later

06:45In this video, enable us to automate things like writing a whole post for LinkedIn sounding just like you, pulling out names, places, and phone numbers from giant documents in seconds, reading and figuring out if an incoming email is someone asking for a refund or just wondering where their order is, shrinking huge piles of info into short and easy-to-read reports, spotting things in the picture like identifying a product in a photo, or even creating brand new images and videos from just a few words

07:08So what ChatGPT and the explosion of other amazing generative AI tools gave us was basically human intelligence on demand

07:14These AI models are kind of like having a super-smart friend who can do almost anything that you ask

07:18them, as long as you tell them clearly what you want

07:22And using automation platforms, we can easily set up these super smart friends into our systems and use these kinds of models in thousands of different ways

07:26All you have to do is pick the right AI tool for the job, give it a clear instruction, call a prompt, and watch the magic happen before our eyes

07:32And that is how the AI automation industry was born

07:38So, with that little history lesson out of the way, let's get back to our original question of what is an AI automation

07:44Well, it turns out that this field is so new that there isn't even an official definition for what an AI automation is

07:48So, here's mine, just keeping it nice and simple

07:51An AI automation is a system that uses AI to automatically do complex tasks that would normally require a human

07:54So, the big difference between these old-school automations that we've just talked about and today's AI automation is the kinds of tasks that they can handle

08:00Thanks to these recent advances in AI technology, we've gone from just moving data around and putting stuff in spreadsheets to being able to solve problems that need thinking, creativity, and decision-making

08:11It's kind of like upgrading from a basic toy robot that only moves forward to a high-tech robot that can solve puzzles and move around the world

08:17So, when you learn AI automation, you are basically learning how to build digital workers that can do very powerful things for you

08:22Without ever having to lift a finger

08:27This is why so many people are racing to pick up the skill right now before it's too late to stay ahead

08:32It's like the ultimate cheat code because you can build them to do exactly what you need, tailored to any kind of job or workflow

08:36For example, for students, it's kind of like having a helper that can organize your study notes automatically

08:40Or for employees, your AI automations can be like a buddy that handles the boring paperwork so you can shine on bigger projects

08:44And for entrepreneurs, it's like having a team member who runs your business tasks while you sleep

08:50And the great thing is that they all cost way less than hiring extra people, and they don't need breaks or vacation

08:56days, and they don't grumble about doing the boring stuff

09:02So, I'm sure you can see why businesses and students and anyone looking to save time and money are so excited about this technology, and why anyone who knows how to build these systems is instantly 10x more valuable

09:09Just imagine automating something simple in your life or work, like sorting emails or scheduling tasks, and how much time you'd be able to save to focus on what really matters in your life

09:22Now, before we dive deeper, it's important to understand that AI automation is a super broad term these days, covering wide ranges of different systems and applications that can be built with AI

09:27This is largely due to the rapid advances in areas like AI agents and AI tools

09:34So, over the past two years, as I built my own AI agency, Morningside AI, and helped thousands through my communities to do the same, I've had to create a clear system for making sense of the chaos that is the AI automation landscape

09:46And I really want to share that with you today because it's been super helpful for me and many of my students to be able to figure this space out and at least have some mental buckets that you can put things in

09:50Here are the three different categories that you need to keep in mind, and please stick with me

09:54This will all make sense in a second

09:57So, firstly, we have conversational AI

10:00These are systems that chat with people, handing back and forth conversations

10:03It's kind of like having a friendly robot that talks to customers for you

10:06These kinds of chatbots can be found on things like websites and answer questions, or they can be voice agents that pick up phone calls

10:09These used to need real people to talk, but now AI can automate these kinds of conversations

10:14The second category is AI tools, and these are systems that use AI to do a specific job when a person asks them to, and it's mostly to help workers get more done

10:22For example, I can make a custom AI tool that takes a link to a cool blog post that I found, grabs the info from the web page, does extra searches on the topic, and then uses something like ChatGPT to write a new beta version for my own blog

10:33And third and final is AI workflow automations

10:39These are systems that do a whole series of tasks by themselves, starting when something happens, like a trigger or on a set schedule, like once a day

10:44They use AI to make decisions that used to need a human brain

10:50It's kind of like having a smart robot manager that runs the whole process for you

10:57For example, an automation can call customers of an online store 14 days after they buy something, using an AI voice agent to ask for feedback and review, all without you having to do a thing

11:03So, you set it up on that trigger of 14 days after purchase, then execute this workflow

11:08Now, those three categories might be a little bit confusing if you are completely new to the space, but don't worry

11:13In the building section of this video, we're going to be creating three automations which integrate each of these different types, and you get to see them in action, which will make it super clear

11:19So, AI automation is essentially an umbrella term under which all of the exciting stuff in the AI space is happening right now

11:24However, when people talk about AI automations, they are typically referring to the last type that I mentioned, so AI workflow automation, and these are what we're going to be building later in the video

11:30And an automation refers to one chain of steps that uses AI in various ways to do certain tasks

11:35And if I'm honest, this last category of AI workflow automation is really the most powerful because it can incorporate all elements of AI automation

11:41like agents, conversational AI, and tools in order to build end-to-end processes that are much more valuable than if they were just alone

11:46So, what I'm saying is that what you're about to learn is the key skill that lets you do pretty much anything in the AI space these days

11:52It is the foundation for building systems that save time, make money, or just make life easier, whether you're at school or work or running your own show

11:59And after years in the game, I can tell you that it's been one of the most valuable skills that I have ever picked up

12:04So, now that you understand what AI automations are, let's take a little peek under the hood and see how they actually work

12:10So, don't worry if this sounds tricky

12:14I've been breaking down this kind of complex AI stuff for years now

12:18So, I'm going to make this super easy to understand for you

12:22So, you can think of an AI automation like a factory's assembly line, right? There are different stations, and they're all working together to build something awesome from start to finish

12:26It's kind of like having a team of little robots, each with a special job, passing the project along until it's done

12:31So, let's go through the five key parts to make this magic happen

12:34Firstly, we have the trigger

12:37This is the very first step of an automation

12:40You can think of it as the factory's start button or the whistle that says, "Let's go." It's what kicks everything into gear

12:43It could be something like a new email popping into your inbox, a form being filled out on a website, or even a specific time of day

12:47This is more of a schedule

12:50Secondly, we have a filter

12:53So, not everything that starts in the automation should keep going through it

12:57So, a filter essentially checks if what came in is the right stuff to work on

13:02It's like how a factory worker does some kind of quality control and checks that if the materials that they've received are good enough to use in the final product

13:08If they are not, then they get tossed out, and if they are, then they move forward to the next part of the sequence

13:14You can think of it kind of like a bounce at a club, where only the important stuff and the good things that you want inside the club or in your automation are allowed

13:16Through

13:19Thirdly, we have actions

13:21So this is where the real work gets done

13:23Actions are the steps your automation takes, like the different stations in a factory where each one does a specific job

13:26So, for example, your automation might send an email, update a list, or create some kind of report

13:31Often, there are going to be several actions one after another, just like a product moving down the line, getting built bit by bit in order to achieve one of these outcomes

13:35Next, we have the intelligence layer

13:38So this is where the AI magic shines

13:42This part is like having a super smart robot on the assembly line that can think, analyze, and make decisions on the spot

13:48And you can tell it how to think using prompting

13:54The AI inside your Automation can look at each task, figure out what's needed, and adapt based on the context you provided, like deciding how urgent something is, writing a custom message, or pulling out key info from a big mess of data

14:00These intelligent steps can go way beyond just following some kind of preset rules that we saw with old-school automations

14:06Next, we have the format

14:11So, just like items in a production line may need some sanding or trimming before another piece can be added on top, the data in our automations often needs some kind of adjustments along the way

14:14And this is where we use a formatter to prepare things for the next step

14:16And finally, we have the output

14:19This is your finished product, just how Carac Factory packages up the final item and ships it out

14:22Your automation delivers the completed work at the end of the sequence

14:28This could be a message sent to your team, an updated file in your system, or a finished document that's ready to go

14:32At the end of the line, it's where everything comes together

14:35It's like after making pizza and putting all the toppings on and prepping the dough, you're finally getting it out of the oven

14:38It's hot, it's ready to eat, and ready to go

14:42So, let me show you how all of these parts work together with a real example that anyone in a job can relate to

14:45Say you're an employee who wants an automation to handle incoming customer emails while at work

14:48So the trigger is going to be when a new email lands in your inbox

14:51company's support inbox

14:55The filter is going to check if it's something important, like if the email mentions "urgent" or "problem," then it will pass it along to the next step

14:58If not, it will end the sequence there

15:01Thirdly, we have the intelligence layer, which is going to use AI to read the email, figure out what it's about, and then helps to draft a helpful response

15:04And in this case, the intelligence layer also acts as a formatter, which is essentially packaging the response and making sure it's in the format we want

15:10Then the actions in the automation can actually send that reply and alert the boss on Slack if needed

15:16The output logs everything neatly in your system and marks it as handled

15:20So that's just a simple example

15:23But these same building blocks are used to automate much bigger things too, which is why AI automations are such a game changer these days

15:27They combine these parts to create truly smart systems that can save time and boost efficiency, whether you're juggling tasks at work, crushing it in school, or running your own business

15:38So, now that you've got a handle on what AI automations are and how they're built, let's take a quick look at the tools that make all of this possible

15:44Now, don't worry if this sounds a little bit too techy

15:48Soon, these tools are going to literally be second nature for you, and it's going to feel so easy to do

15:52Creating automation starts with picking a main automation platform

15:56These Platforms are typically called workflow builders, and they are the command center of your automation factory

16:01They give you a blank canvas to design your automation on using the building blocks we talked about, some of which are going to be powered by AI like Chatbot

16:06Popular workflow builders include Make.com, which we're going to be using later in this video in the tutorial section

16:12We have Zapier, which is great for quick setups, and we have n8n, which is perfect if you want a bit more control

16:18They are the brain of your operation, and they're really just controlling how everything fits together

16:21So, workflow builders don't work alone

16:23They are essentially a place to hook up all sorts of other tools to get the job done

16:26So, These are the categories of tools which you can connect to your workflow builders

16:29Firstly, we have databases and spreadsheets

16:32So for storing information and data, you can use things like Airtable or Google Sheets

16:35You can think of them as basically the filing cabinets where you keep all your data neat and tidy so that you can save new things to the database or you can pull it into your automations as needed

16:41Secondly, we have communication tools for sending messages

16:45Things like Slack or Google

16:49They're like kind of walkie-talkies that can pass information around automatically for you

16:54Then we have AI models, and these can add that smart human-level thinking, like OpenAI's ChatGPT, which you can think of, kind of like a genius buddy who solves problems for you when you give him the instructions that he needs

16:58Then we have scheduling tools, which can handle time and meetings, things like Calendly or Google Calendar, and these are essentially like your personal planner to keep things running on schedule

17:05Then we have forms and intake tools

17:09So this can collect information from people, where you have things like Typeform or Tally

17:13These are essentially input forms and triggers for your automations when someone fills them out

17:16So as your automation goes through, it's like calling up all your friends on a group project

17:19Each one is bringing their own special knowledge or capabilities to the table in order to help you to get to the end

17:22Of that sequence and finish off the automation to create the final product

17:26By building out a workflow, you are basically the boss at the factory

17:30Once you know what each tool can do, you can mix and match them to work together smoothly along this assembly line

17:33It's kind of like building with Lego blocks

17:36You can just like snap the right pieces together to make something awesome

17:40You get to decide which tools you connect in what order and how AI can make the whole system smarter as well

17:45Which AI models do you use? Gemini, do you use OpenAI? To use complexity for searching

17:49There's so many different decisions you have to make

17:53Uh, but it's really cool to be able to flex your kind of creativity in order to solve these

17:55problems

17:58It's really like a new age form of problem-solving, which is why I love it so much

18:00I say, I know I need to take this and get to this

18:03How can I use AI to do that? And it really forces you to explore what's out there in terms of AI tools these days

18:08So, what kinds of workflows can we build? So for students, for example, you could build a study material organizer that automatically summarizes lecture recordings for you, creates flashcards from notes, and schedules review sessions based on your exam dates

18:19An employee could improve their workflow with a meeting assistant that records and transcribes their meetings, and then generates action item summaries off that and updates project management tools

18:26Entrepreneurs could design a lead qualification system, which automatically qualifies leads, calls them with an AI voice agent, and then sends them a custom proposal to automate that whole process

18:33And that is exactly what you'll learn how to build by following along with me in this next section

18:38So, I'm going to show you how to build out a lead qualification automation step by step, starting simple and getting more complex as we go

18:43We're going to be focusing on this business-based workflow because these kinds of business systems offer the best opportunity for monetizing your new skills, which I'll go into depth on at the very end

18:50So, stick with me and you're going to be learning how you can start to make money

18:56immediately with these kinds of skills

19:00So, before we get into that, let's do a quick summary of this section

19:05So, firstly, an AI automation is a system that uses AI to automatically perform complex tasks that used to require humans

19:09Secondly, we build them inside of workflow builders that incorporate integrations with tons and tons of other tools

19:15And every automation has six key components: firstly, a trigger, what starts the workflow; a filter, conditions that need to be met; the intelligence layer, which processes info and makes decisions with AI; the actions, which are the tasks that actually get performed; formatters, which clean things up; and the output, the final result or deliverable

19:34So, if If you're feeling unclear about anything we've covered so far, feel free to go back and rewatch some of those sections and be ready to join us in the next step when we begin building

19:40So, it's really, really important that you do understand everything that we've gone over there because you're not going to have a solid foundation to build your technical skills on top of, which we're doing in the next section

19:46So, please, please, please, I've taken a lot of time to put all of this information very, very gradually together

19:52So, you must understand everything that I've gone over just here before we go into the next phase

19:57If that's all good, then let's take a look at what we're going to build together

20:02Okay, so now that we have The foundational knowledge built that you need, we can now get into the second chapter of this video where we're going to be building three AI automations from scratch

20:08We're going to be starting off with something super beginner-friendly to get you started and then working our way up to a much more advanced and valuable one by the end

20:14Now, very important note is that each of these automations build on each other

20:20So, you have to be able to do the first one in order to be able to make the second and so on

20:23So, you cannot skip ahead

20:26I've planned this out very carefully to gradually layer on your skills

20:28So, it's all very intentional

20:31So, please just trust the process

20:34So, over the next chapter, you'll learn almost all of the key skills you need to start building your own AI automations from scratch and be able to tap into this enormous opportunity that is AI automation

20:37The system that we're going to be building gradually over the next three sections is an AI lead qualification and proposal generation system for a business

20:47In the first tutorial, we'll be setting up the base using AI to automatically qualify leads after they submit a form on their website

20:53In the second tutorial, we'll improve that qualification ability by implementing an AI voice agent that can call the lead for more information

20:58And finally, in the third tutorial, we'll implement an automated proposal generator that can instantly create proposals for

21:04qualified leads using the information collected on the phone call and in the lead form

21:10The whole point of this is that as soon as someone's interested in contacting the business, they can kick things off with them immediately by getting a proposal in their hand

21:16So this process of qualification is a crucial part of running any business at scale because, at the end of the day, not all people who come to a business are going to be a good fit for their services

21:22So, for example, someone may run an accountancy business, but they only choose to work with doctors

21:26They are specialized in helping doctors with their finances

21:31But if a builder fills out their website form, then that lead would not be qualified, right? Taking a call with them would be a waste of time because they are not a doctor

21:35Therefore, to stop wasting time, almost all businesses need some kind of qualification system

21:40And for qualified leads, most businesses need to make some kind of proposal for them in order to kind of look at it and see what they're proposing and then agree to that proposal

21:46Since most proposals don't lead to a deal, maybe 20% if you're lucky, this is a huge waste of time and resources for the company

21:52So, long story short, what we're about to build will solve a number of key problems for basically any business, making it extremely valuable for you to be learning how to do it

21:58And in fact, this is something you'll be able to go and sell directly to

22:03Businesses when you're done

22:08Here's what this process looks like without AI automation first

22:13So, a human sales rep must constantly check for new form submissions from the website, review each lead's details, and evaluate if they're worth pursuing, research the company to understand how to help them, make phone calls, and deliver competent pitches, and then manually create custom proposals

22:18That is hours of repetitive work per week, and it could lead to potential leads slipping through the cracks

22:25If maybe they get the qualification wrong, they don't understand what the business is doing, they don't properly research it, or they're just too slow at getting back

22:27They may have to wait a whole day for the lead

22:30to hear anything back

22:33So decreasing the time it's going to take for a qualified lead to hear back from them is going to drastically increase their conversions

22:36With AI automation, we can transform this tedious process into something much more efficient, which is exactly what we're going to be building together

22:42So here's how it works

22:46It's going to start, as usual, with a lead filling out the form on the website

22:50Then the system is going to automatically qualify them using AI

22:54Then it's going to further research the company using AI also

22:57Then it's going to send an automated phone call to pitch your offer using an outbound AI voice agent

23:00The system then saves the call outcome, summarizes the conversation, and generates a personalized proposal for them, all without a human having to lift a single finger and in a super scalable way

23:06This is the power of AI automation

23:11We're taking tasks that used to demand hours of manual work and turning them into workflows that run all by themselves

23:15And we're going to build it all using several of the most popular tools from the automation ecosystem

23:19So, if you're as excited to learn this as I'm to teach you, then let's get started

23:23And everything that you need to follow along with it, including all resources, templates, prompts, etc., is going to be available for free on my Skool community

23:27You can find it in the first link in the description

23:30You'll need to request to join

23:34It will take one to 2 minutes to be accepted

23:37Once you're in, you can just search for the title of this video, and then you'll be able to find all the resources attached to it

23:40So, that is how you can get all the resources to follow along

23:44Let's get stuck into it

23:46Alrighty, guys

23:49Just to clarify things before we jump in, it's very important that you understand what we're doing in this first build, but also in the second and the third, and how it all fits together and you get, kind of, an idea of where we're going

23:52Understanding this technology and then being thrown in a whole bunch of random things, like Airtable and Slack and Make, and all of these different terms, can be a bit confusing

23:59So, I just want, very quickly, to give you a bit of an Orientation before we jump into things of what we're building and why and how it works because I've touched on it before, but I don't think I did a good enough job

24:05So, I'm filming this after just to really make sure you guys are fully clear on what we're building here

24:09So, and why it's valuable, really, as well

24:13So, um, as we touched on, this is going to be an AI qualification system, um, for inbound leads to a business

24:18So, the easiest way to explain this is if we had a, a website and say we had this "book a free consultation" form, and we might be running ads to it

24:26We might just have that on a website and people just discover it by searching the web, or, or we're showing up in Google results

24:34But at some point, a business, like the example I gave before, If you're an accountant and you only work with, uh, builders or plumbers, or whatever the, the example I gave, some people are going to fill out this form who are not necessarily the right person for you

24:42Like, my accountancy firm that only works with plumbers, if a surgeon comes in, or if a pilot comes in and fills this thing out and wants to get accountancy services, we would ask them questions around, okay, well, what's your name? What do you do? Uh, what sort of industry do you work in? And we'll collect this information here

25:00And as I mentioned before, not all of the people who fill out your forms, particularly if you're running ads or doing content and it's driving traffic to this landing page as a business, not all of them

25:06them are going to be people that you actually want to get on calls with because if you get on calls with them and they're not your ICP or the person that you could potentially work with, then it's going to be a complete waste of time

25:15So, qualification is a very essential part in, in pretty much any business

25:25And what you're going to build is a very, very powerful system, starting off with something basic like this, and then we're going to progress it to something a bit more advanced like this, and then finally, something extremely valuable and powerful that you guys are all going to be able to build along and ultimately sell this to someone if you wanted to afterwards

25:29So that's going to be covered in the monetization

25:33section

25:37But just to clarify, sort of what we're going to be doing here in this first build, uh, you'll start off with building a form on Tally

25:40So we're essentially replicating this kind of website form, but we're just going to build it in Tally in this case

25:45You can embed these into different websites, etc

25:49But just think of this as a form that people will get sent to

25:54So maybe they clicked on an ad and then they get sent to this, "How can we help?" We're going to build out this form, and then when people click submit on this form, it's going to send them into this, basically a fancy spreadsheet

25:57And in this case, we're using Airtable

26:00Airtable is like a really awesome platform, which you're going to get to use a lot within this

26:04build

26:07But Airtable, you can think of it like a fancy spreadsheet, and we're going to be able to map each of these answers to a row in this database here

26:11So every time someone fills this form out that we create, it's going to load it and add it as a row into this database

26:16And the cool thing there is that Airtable allows us to, within Make.com, our workflow builder, it allows us to set up events that when things happen in Airtable, like, okay, let's watch for new records that arrive, and that's what this here is doing

26:29So this trigger of our automation is going to be watching for new records that arrive in this, and then it's going to take anything that arrives in here, say this first row, and then it's going to put it through this

26:35automation here

26:41And so this is going to be a very basic one where we've taken actually the AI component out of this

26:47Before Airtable really got advanced with the AI features, what you're doing here is taking the information from the Airtable, you'd use some ChatGPT step here, and then you'd be able to do things afterwards

26:53But in this case, I'm making it extra simple for you guys, and that we're actually just using Airtable's built-in AI features

26:58So down here, you can see in the tutorial that you're about to go into, we will use Airtable to create an AI column here that's going to take in information like, uh, like here where they're talking about their company, their budget, and about their needs

27:03We can write a prompt

27:07in here, and it's going to automatically fill out this row

27:12So as soon as a new person arrives in this spreadsheet, this field that we're creating here is going to automatically qualify them and use AI and this prompt that we write here to analyze the information that they gave us and then output if they are qualified or if they're not

27:23So we're doing the qualification with AI built into Airtable, which is going to save us a lot of time and messing around with jumping back and forth

27:33So, so that is basically the start of build one

27:44We will do immediate qualification with AI within Airtable, and then we're going to, if they are qualified, we're going to send an email to them, and because we're already doing the qualification here in Airtable, it makes it a lot easier for us over at Make.com because for this particular node, as you'll see in a second, we're going to set it up so that it's only actually going to look for, uh, the rows or records in this table that have been AI qualified as qualified

27:54So if this prompt here that we've written analyzes all the information in the row and then outputs qualified, then and only then will it pass it into here

27:59And this is when we're going to be sending an email to the prospect and saying, "Hey, we're interested in hopping on a call

28:05Here's a link to book in a call with us." But at the same time, it'll also send a message to our sales team in Slack and say, "Hey, look, we've just had a new qualified lead." So, this is very much a, a minimized version of what you could do, uh, maybe a year ago

28:17But because of the Airtable's AI features, uh, we can do a lot of the heavy lifting here

28:24And writing a prompt that's going to analyze what the person has filled out here, aka, are you a builder or are you a pilot? And if they were a builder, in the case of the example I just gave, it's we're going to be using a different example in the build

28:32Um, but it would come out as saying qualified here

28:40And because it says qualified, then it would automatically trigger, uh, the rest of this automation, which is sending an email to them and taking the next step and saying, "Yes, we are interested in talking to you further, making sure that we're not talking to anyone that we shouldn't be talking to and at the same time letting the sales team know

28:45So, that is build one

28:49Um, that is how it all fits together

28:54And I'm going to be doing these little updates just before each build so that you guys are 100% clear on what we're going to be doing

28:59To get started, we need a way to gather our leads' information

29:04While there are several great options for this build, we'll be using Tally, an easy-to-use form builder

29:09Just sign up for free or log into your account

29:12Then we'll click on new form and give our form a title

29:15Anyone using the form will see this title

29:19So, we want it to make sense for the user

29:21So, in our case, we can name it, "How can we help?" I want to build it from scratch

29:24So, I'll hit enter

29:27The way we create forms in Tally is with building blocks

29:30So, if we click the plus button, we can select the type of block we need from this list of input options

29:33We'll start with a short answer input for the user to write in their first name, and we'll do the same for their last name

29:39Notice how we're adding a label above each input, which tells the user what to write in each of these

29:44Then, we'll select the email block for the user's email, add in a phone number block, then another short answer input for the name of their company

29:51Since their budget is a number, we'll add a number block to grab that, and finally, we'll add a long answer input where leads can describe their specific needs

30:03Now that our form inputs are ready, we can customize the form's appearance to match our branding

30:08We can adjust elements like the background color, text color, button color, and the accent color

30:13Feel free to choose whichever colors you'd like

30:17Now, we can go ahead and publish the form

30:20When it's ready, we'll see a sharable link

30:24Let's copy this and actually visit the published form

30:27It's looking great and ready to use

30:30In the real world, you could either use this as a landing page or embed it into a website

30:33Whenever a new lead fills out this form, we need to be storing that response somewhere

30:36For our build, we'll store our form response inside Airtable

30:40You can think of Airtable kind of like Google Sheets on steroids

30:44It's your database that not only stores information

30:48but can process information and, if you push it far enough, can even be used to build out more complex apps

30:52So sign up for free or sign in if you already have an account

30:57On the home screen, you can see that we could use AI to build things or start with a template like one for a marketing campaign or a project tracker

31:01But for our build, we'll start by creating a base from scratch

31:06Base is just Airtable's name for a database

31:10Again, it's really similar to a Google Sheet or Excel sheet, but can be layered with complexity

31:16We'll name it "lead base." We'll reference this name later when setting up the connections between our Tally form and Airtable, and later between Make and Airtable

31:21For every field in our form, we need a matching field in Airtable

31:27So, we'll add fields for our leads: first name, last name, email, phone, company, budget

31:51We'll reference this to determine a lead's qualification, notes, details they submit about their needs, created on, when the lead was added to this base

31:56Importantly, we need to know if our lead is qualified or not

32:01Ultimately, lead qualification can be more nuanced, but for our needs, we'll qualify leads whose budget is $10,000 plus

32:07By using Airtable's AI assistant, we can prompt it to create a custom field for us by asking it to create an AI field called qualification that sets the lead as qualified or not qualified based on whether the budget field is greater than or equal to $10,000

32:20Now, Airtable will use the power of an LLM, OpenAI at the time of this recording, to help with creating this custom field

32:27After processing, the AI fields modal will appear

32:33Since we want leads to be auto-qualified, we'll enable the automatic generation option

32:38If you encounter errors about missing or invalid fields while saving your AI prompt, it's typically because the system can't clearly identify which fields you're referencing

32:44Double-check that all fields are valid and properly linked to the correct data in your base

32:56We want our database not just to auto-qualify leads intelligently, but also to generate a descriptive message about each lead that we can share with our sales team

33:00So, we'll use the AI assistant again to create a field

33:04that generates this message based on the lead's information

33:08After double-checking that this new prompt looks good, we can save it and move on to the final field

33:14We'll add a date field called "contacted on" that will store the date when we contacted the lead through our automated email

33:21In the Make workflow, we'll add the date to the field from Make at the very end of our workflow

33:26Finally, we'll clean up this base by renaming the sheet to "lead contacts" and set up each record or row to be called a lead

33:32Now that we have all the necessary Airtable fields that match our form fields, we can connect Tally to Airtable via Tally's Airtable integration

33:42Just name the connection, select the database and table you're syncing to

33:51and map each of the tally fields to their respective data fields in Airtable

33:58After saving this connection, we'll see a confirmation that the integration was successful

34:05Now, let's test the connection by filling out the form with some dummy data, making sure to set the budget to $10,000 or higher

34:12When we submit, we should see the new lead record populate in our Airtable database

34:18And voila, it's showing up perfectly

34:24Since the budget is over $10,000, it's automatically marked as qualified, and we've got an AI-generated message ready to send to our sales team via Make

34:30With our lead form synced up to our database, we're ready to start building out the automation workflow

34:34This is what we're about to build out

34:39We'll have a module that watches our Airtable database for new leads

34:43And when it finds one, it sends them an email via the Gmail module, then updates that same lead's Airtable row with the time we contacted them

34:46It also formats and sends a message into a Slack channel

34:49If you're not familiar with Slack, it's a professional group chat with channels dedicated to specific topics like marketing

34:53With this plan in mind, let's head over to make.com

34:57Remember, this is our workflow builder, the assembly line where we'll be constructing our automation

35:01You can get started for free or log in if you already have an account

35:05Once inside, you'll see your dashboard, which displays info about your workflows, which are called scenarios

35:08in Make

35:12You'll see how busy they've been and how much data they've used

35:16This helps you monitor your Make plan usage, which is particularly important if you're on a free plan with usage limits

35:21You can also see if any of your scenarios require attention due to things like bugs and errors

35:27The scenario tab is where you'll spend most of your time, and you can organize your scenarios into folders, like you see here

35:32Before we start creating our own, I want to bring your attention to the fact that you have a bunch of templates to get started from and adapt to your own use cases

35:39And over time, you'll be managing the connections here in this tab, which shows you which external apps, like OpenAI and Google, you have connected to from Within Make

35:46With that brief tour out of the way, let's get into it and create a new scenario

35:50We'll start by setting up the trigger

35:54After selecting the Airtable module, we'll configure it to watch records

35:58Since Make doesn't yet know which records to watch, we'll need to establish a connection between Make and our Airtable account

36:03We'll do so with a token because, as you see in this warning, keys are deprecated

36:09So, we just need to create a token and paste it here

36:15To get that token, go to your Airtable account settings, navigate to the developer hub, and create a new token named something descriptive, like "Make token." When configuring the scope, set it to allow both reading and writing records with full database access

36:33For read and write operations, I'm granting access to all current and future bases, though you may want to restrict this depending on your specific needs

36:39Now, click create token and immediately copy and store it somewhere secure

36:46You'll never be able to see the complete token again

36:52Once we paste the token back into Make, our connection to Airtable should be successfully synced up

36:58Now, we just select the base and table we want Make to be watching and set the trigger field to "Created On." The trigger field tells Make which field to monitor for changes in order to determine when a record is new

37:12By setting it to "Created On," Make will only pull records whose timestamp is later than the last time it checked for new records

37:18That way, it only acts on newly added leads and doesn't rerun on old ones

37:22As for the label field, we'll set it to the company

37:26This field is just for display purposes inside Make's scenario logs

37:30It helps you identify the records that are being pulled in, but it doesn't change how the automation works

37:37The formula field lets you write an Airtable-style formula that filters records before they're passed into your automation

37:41Make only processes records when this formula evaluates to true

37:45So, if a lead's qualification field is equal to qualified, they'll be pushed through to the next step of the automation

37:49If they're not qualified, they don't pass this step

37:55If you ever need help writing these filters, you can ask an LLM like ChatGPT or even have a chat with Make's built-in AI

37:59Once we hit save, we'll choose to start from now on

38:03That way, Make only looks at new leads created after this point and skips anything already sitting in Airtable

38:08If we hit the run button, it should successfully find the newly created qualified lead and display that record's details

38:13Once you run this scenario, any qualified leads that were found will not be found again on rerun due to this created on field

38:19You'll have to add a new lead each time you want to test this scenario

38:25Again, the automation is filtering for only new leads

38:31Since we want to send qualified leads an email to schedule a call and notify our sales team about this lead via Slack, we'll need to set up two actions

38:35This is where a router comes in

38:38It allows our scenario to branch into these two separate tasks simultaneously

38:42Without a router, setting up tasks sequentially means if the email step fails, the Slack step won't run at all

38:46We want to avoid these waterfall effects where one failure blocks other actions

38:51Using a router prevents this issue while making our scenario easier to troubleshoot and expand over time

38:55On the first route, we'll add the Gmail module and select the send an email action, which requires us to set up a connection to our Gmail

39:03If you're using a non-personal email like mike@edge.ai, this setup is very simple

39:12You just log into your Gmail account here, but if you need to use a personal Gmail, one that actually ends in gmail.com, the process is more involved

39:21So, I'm going to ask you to be patient because there are quite a few steps involved to connect a personal Gmail account here

39:26If you're just watching and not building along yet, feel free to jump past this section

39:30Same goes for those of you who are using a non-aggmail.com email

39:33But if you do need to connect your personal Gmail account, here's what that looks like

39:37As you can see, if we pop open these advanced settings, this requires two key pieces of information: a client ID and a client secret

39:42These act as the key that allows Make to unlock access to your Gmail account

39:49Make provides instructions for how to generate these, which you can find by clicking on this guide link

39:53At the time of this recording, it links to the help center

39:57From here, click into apps documentation, then click on communication, and scroll down to Gmail

40:00If you're wondering why Make didn't just link us to this page, so am I

40:04From here, we'll click on create a custom OAuth client

40:09And now we need to log into the Google Cloud Platform

40:14Once you log into Google Cloud with the Google account you want to send emails from, you'll click select project at the top left

40:19From there, click new project, then give the project a name like Make and hit create

40:24Once it's created, a notification will appear in the top right corner

40:30Click select project to open your new project

40:34Now that we're Inside, let's enable the Gmail API

40:37Go to APIs and services and click enable APIs and services

40:41In the search bar, type Gmail and select the Gmail API from the results

40:47Then click enable

40:52Next, we need to tell Google who is requesting access and what kind of data is being requested

40:56So, we'll click on Oorth consent screen and hit get started

40:59To fill out the app information, we need to give the app its name

41:03So, to keep things consistent, let's call it Make, like we did for the project name earlier

41:07We also need to tell it which email we want to give these new abilities to

41:11Now, select external for the audience type and next

41:15Under contact information, enter an email for Google to notify you about this project

41:19Hit next

41:23Then agree to the terms, continue, and hit create

41:26We now need to give Make permission to interact with Gmail on your behalf

41:30So, head into the data access tab and click add or remove scopes

41:37We're adding Gmail API scopes

41:44So, search for Gmail and then select the following scopes: both scopes to read, compose, and send emails, manage drafts and send, view your emails and settings, view your metadata, add emails to your mailbox, send email on your behalf, see and edit labels

41:48With all those labels selected, hit update

41:53Then, scroll down and make sure to save these scopes

41:56Next, let's configure the branding settings

42:00Scroll down to authorize domains and add both make.com and integromat.com, which is the old name Make used to

42:04be called

42:08Then save

42:12After that, head to the audience section and click "Add users," where you'll add your Gmail address and hit save

42:16Now it's finally time to create the actual credentials that Make will use

42:21Go to the client section and click "Create client." For the application type, choose "Web application" and name it "Make." Scroll down to "Authorized redirect URIs," click "Add URIs," and paste the exact redirect URI provided by Make

42:32You can find this in their Gmail integration tutorial page that I showed you earlier

42:44Click "Create," and you'll be given your special client ID and client secret

42:51You will copy both of these and paste them into the fields in Make's Gmail module

42:56Now we can click "Sign in with Google." This sign-in window will appear

43:00Select your Gmail account, grant the requested permissions, and hit continue

43:06Once that's done, your Gmail account should be successfully connected to Make

43:11I know that was a lot, and I wish it was simpler too, but the good news is we can now start sending emails from that Gmail account

43:15So, let's now create the email template

43:19We'll set up a subject line using the lead's name from their Airtable record and whatever engaging text you want to add in here

43:23For the content of the email itself, we can address them by name and say, "We received the request about their company and would love to discuss their goals on a call they can book via our scheduling link." For this, we will be using a handy tool called Calendly

43:32If you're not familiar, Calendly is a scheduling tool that lets people book meetings with you

43:42You connect it to your calendar, set your availability, add conferencing tools like Zoom or Google Meet, then create event types like an introductory call and share a link for people to book these meetings with you

43:51So, just set up a new account if you don't have one, or log in, and we'll create a new event type and call it "Intro Call." This event will have a 30-minute duration, and the location will be Google Meet

44:02Keep in mind you may have to connect a conferencing tool if you're using something like Zoom

44:06Now, we can set our availability for this intro call event

44:10I already have mine set up, but to do that, you just head to the availability tab and go to calendar settings

44:15Here you can see I already have a couple of calendars synced up, but to add a new one, click "Connect to calendar account" and select your provider, such as Google

44:21Then, just choose the account you want to sync and log in

44:26Again, I've already set this up, so I'll close out of this and head back to the event

44:30For each event, we can set the availability for that event type

44:35I may want to change the time I'm free on Friday, either a specific day or every Friday

44:39When I apply these changes, that will update the availability for just this event type and does not apply to other events I may have set up in Calendly

44:45Down in "More options," I can do things like add an event description where I can Tell the person booking that I'm excited for our chat

44:52Once we hit save changes, the event is ready to share

44:58So, let's copy this link and head back into Make and paste it into the body of the email we're sending to our lead

45:02Finally, we of course need to add the recipient of this email

45:07So, we'll fill that in with our lead's email address

45:10With that set up, we can move on to our other route below

45:14Ultimately, we're going to be posting a message to a Slack channel about our new lead

45:17But if you don't use Slack and don't want to go through the steps of connecting another external tool, you could sub this out for another Gmail module where we send an email to our sales team letting them know that we have a new qualified lead and give them the lead's name and other relevant info

45:25Then set the recipient email to whichever test email here

45:32But since I want to show you how to use a bunch of popular tools, let's look at setting this up to post to Slack

45:40We'll choose the Slack app and select the create a message action

45:45If you already have a Slack organization, you can simply connect Make to that module

45:50Now, if you don't, let's quickly walk through creating a new one

45:55You'll head to and sign in with a new account, then click create a workspace

45:58Give it a name

46:02Here, I'm just adding the name of our mock agency that we're qualifying leads for

46:05Then just run through these steps to confirm your name

46:08Skip adding new members for now and start with the free version

46:11Now we're in our new Slack organization

46:14As you can see, there are channels here for different topics and direct messages down here

46:17We'll add a new channel called marketing because this is where we'll be posting our Slack message into for the entire sales team of our imaginary agency to see

46:22With these ready to go, we can head back to Make and connect the Slack module to our Slack by allowing access

46:35We'll tell the module where to post the message by selecting from a list of our public channels, specifying the marketing channel we just created

46:40Now, what should it post to this channel? It should post the AI message from our Airtable lead, so we'll add that in here

46:45If we run the scenario, it will work, but the message will look messy because it's technically a collection, which just means it includes extra stuff that we don't want or need to display here

46:51We can solve this by inserting a formatter module just before we post to Slack

46:57We'll select a text passer, which will do a pattern match using a regular expression to pull just the clean message text out of it

47:03While this might look complicated, think of it like a smart highlighter that scans the text and grabs only the part we care about, the message's value itself and not the messy metadata

47:14If you ever need to use a regular expression or regex in the future, just ask an LLM to draft one for your use case

47:19Now, we tell our text passer which text to pass: the AI message

47:26With that Formatter taken care of, we can head back into the Slack app and tell it to create its message based off that freshly passed text instead of the original messy version

47:38As a final step, we want to circle back to Airtable and update our lead record with information about when we auto-contacted them

47:44After the Gmail module, we'll add an Airtable module and use the update a record action

47:50We'll configure it to return to the same lead base and contacts table, targeting the ID of the record that just pushed through this scenario

47:55We'll set the contacted on field to the current date and time by using the "now" expression, which simply tells Make to insert the exact moment the automation runs

48:01If we run the scenario and head back into Airtable, we'll see the date was successfully added to the contacted on field, giving our sales team context about when the lead was auto-emailed

48:14Our scenario is all set up and working great, but up until now, we've only been running it manually by clicking the run once button

48:20By toggling on the schedule, we can configure our scenario to run on autopilot at regular intervals, such as every 15 minutes or on a specific day of the week or month

48:31You can even set a custom schedule using advanced scheduling, using time ranges with start and end dates if you only want it to run during a certain window

48:36Once you're confident it's working, just flip that schedule toggle on, and your automation will run in the background while you Focus on more important things

48:42Of course, you'll want to frequently save the scenario, and if you ever need to revert to a previous version, you can revert to that version from here

48:53Scenario inputs are useful for more advanced use cases, like when one scenario's output becomes another scenario's input, but that's beyond the scope of this basic build

48:59You've also got your scenario settings, a place for notes, an auto aligner if your workspace gets a little messy, and even a little animation that explains the workflow

49:16Finally, there's a quick reference to every app and module used in your scenario, helpful for getting a bird's eye view of your automation

49:19And so, that's build one explained, just a very basic AI

49:23qualification based out of Airtable

49:26But to give you an idea of where we're going with this, in the next build, build two, we're going to be adding in a voice agent here

49:29You may have heard about voice agents before, but they are a really, really exciting uh area of the AI space right now

49:32You have two main types: you have inbound and outbound

49:36And uh, inbound is when you can set up a phone number and people can call

49:40When people call that number, then they get to talk to the AI directly

49:44Outbound voice agents is what we're going to be building here, where we can initiate a call using our automation here, uh, to send a call out to someone

49:50And say my phone starts ringing and I can pick it up, and I'm talking to the AI that we've created

49:56Here, so this is really, really cool stuff and super powerful

50:02But the reason we're doing this is because, as you will have seen on the form that we set up, we have quite a limited amount of information that we're collecting from the business, and this is for good reason

50:08You don't want to put too much information here, or it will decrease the number of people who fill it out

50:14So, sort of having a lean form, and then if we initially qualify them here, in the second build, we're going to expand it so that we can actually, once they are qualified, as we've explained here, the AI and Airtable is going to determine preliminarily if they are qualified, then we will use our voice agent to actually call the person and ask for more information

50:21And we'll walk through a script, basically, and ask them, "Hey, tell me a bit about your business and your needs

50:29What are you hoping to get out of us?" Da, da, da, da

50:36Basically, collecting a bunch more information that can then be used for even greater and more accurate qualification

50:42So, here we have our Vappy voice agent, which is going to call them, and then we're going to get the data of that call, the transcription of that call, and Vappy is actually going to be able to analyze it for us to determine if it was a successful qualification or not

50:50And then we have to build the automation to handle a few different cases because, of course, not everyone's going to pick up the phone

50:58So, here we create a route that handles if they answered the phone and Then, based off the information, were they interested or were they not interested? And if they didn't answer, we have some other things that we can do to handle it here and update the Airtable and things like that

51:05So, it's essentially build two is adding on top of what we've already built on build one, where we have just a basic qualification and sort of send them an email to book in a call or to let the sales team know

51:17Here, we're trying to do even deeper qualification and making sure that our sales team really isn't getting on any calls they shouldn't be by sending out a voice agent to collect more information for us to do an AI pre-qualification for this business's lead

51:29So, let's take this automation to the next level by adding AI voice calls to qualify leads even more effectively

51:34We've already built a strong foundation, a system that identifies qualified leads, follows up via email, and notifies your team

51:40This alone puts you ahead of the curve

51:46But what if we could make the system even more responsive, more conversational, more human, even? That's where an AI voice agent comes in

51:51By weaving it into our workflow, we can automatically call leads, gauge their interest through real conversation, and tailor our follow-up based on their responses, all without lifting a finger

51:56This is where automation becomes more than a task runner

51:59It becomes a teammate

52:02It's the closest thing we have to a human conversation at scale

52:05And when When it comes to leads, timing and tone matter

52:08Research shows that responding to leads immediately increases success rates by 7 to 9x

52:12In this next section, we'll integrate VP, a popular AI voice agent service, into our workflow

52:16First, we'll set up our voice agent

52:19Then, we'll configure Make to have it call our leads

52:22Finally, we'll enhance its effectiveness by feeding it custom research about each lead, enabling more targeted pitches

52:26So, what exactly is an AI-powered voice agent? You can think of them like a version of Siri or Alexa, but one that's specifically designed to have natural phone conversations with people

52:31Depending on your needs, it can either make calls for you or answer calls

52:37These agents can do amazing things like follow up with potential customers, schedule appointments, answer common questions, collect feedback, or conduct surveys

52:43There are several platforms that offer AI voice agents like 11 Labs, great for highly realistic voices, and Vappy, known for being fast and affordable for our automation

52:49We'll be using Vappy because it's beginner-friendly, cost-effective, and integrates well with other tools

52:56If you haven't already created an account, go ahead and do that first

53:02Once inside, we'll go to the assistance tab and click create assistant

53:06This starts the process of configuring our assistant

53:10You can start from a template like a lead qualification specialist, but we'll create our own

53:14from scratch and name it Ben

53:19When choosing which provider and model to use, you'll want to balance ability with speed and cost

53:25So, keep the price in mind and the time it takes to actually respond, which we call latency, which you can see next to the model options

53:31For now, we'll go with the cheapest and fastest option, which is GPT4.1 Mini at the time of this recording

53:37The most crucial element is the prompt, which defines your agent's behavior and objectives during the call

53:41First, we specify the opening greeting message that the agent will use when calling someone

53:45We'll open up the call asking if it's a good time to talk about the lead's business needs

53:49The actual prompt is much more detailed, and I'll paste in one I wrote earlier

53:56You can find this prompt and everything else you'll need to follow along in the first link in the video description

54:01Let's take a look at what it includes

54:06As you can see, we start off by defining its identity and role: a voice assistant representing Edge AI, an AI automation agency

54:11Then, we specify its goal: to pitch our services and determine whether the lead would like to receive a proposal

54:19We then set its tone and behavior: a knowledgeable rep who is curious but not pushy, and who uses casual, natural language with words like "uh" and "mhm." This section helps humanize your assistant

54:32Finally, we outline the structure of the call that it should replicate

54:36The conversation flow starts with introducing our AI

54:40services, then moves to understanding the prospect's needs through targeted questions

54:44After acknowledging their responses, we pivot to offering a proposal

54:47If pricing comes up, we defer to the proposal for details

54:51The call ends either by confirming they'll send the proposal over email or with a polite goodbye if they decline

54:56It's best to outline the steps as clear bullet points like this, but keep them focused

55:00Too many steps can overwhelm the AI assistant

55:04In our prompt, we included context about the company the assistant is representing

55:08For our needs, this is sufficient

55:13But if our call was more involved, like a customer support agent who is receiving hundreds of nuanced calls, we could add files into It's knowledge base that it can reference, like all of our policies and procedures

55:18But keep in mind, this will increase the response latency since the assistant will need to make round trips to these files as it generates its responses

55:23So, if you can get away without adding supplemental files, your agent will be more performant

55:28Our assistant is almost ready to start making calls on our behalf

55:32But before we publish it, let's add some extra configuration

55:35As we scroll down, we'll see that we can tweak the transcriber settings, which we'll leave alone for now

55:39We can also select different voices depending on the personality we want our agent to have

55:44For our agent, we'll go with Vap's Elliot voice, but feel free to try out different options to feel out which one is best for your use case

55:49You can also add background noise to the call

55:55Adding ambient sound makes conversations feel more natural and helps mask any brief delays that occur while the agent generates responses instead of awkward silence

56:01Callers will hear realistic background sounds

56:06Next, you'll see the tools section, which unlocks powerful ways for your agent to take action during a call, like sending data to your CRM, triggering external workflows, or running custom logic

56:12This is where Vappy really shines for more advanced automations

56:16However, since it's beyond the scope of this tutorial, we'll leave it untouched for now

56:20What we will be using is the call summary

56:24Vappy automatically transcribes the call, and the prompt inside here tells it how to summarize the call based on that transcript

56:30If we open it up, we'll see there's already a built-in prompt that tells the assistant how to create its call summary

56:35While this default prompt works decently, we can make it even more valuable for our use case by customizing it to capture additional details

56:40Here, I'm pasting in a new prompt telling it to summarize the call in a couple of sentences with details that will help out with creating a proposal later on

56:52Since we'll add this call summary to our lead's Airtable record, capturing detailed insights here is valuable

56:56We also want to tell Vappy how to judge if a call was successful or not

57:00There's already a decent default prompt here, but we'll customize it for our needs by telling it to judge success solely on whether the lead wants to receive a proposal

57:04We'll evaluate success with a pass/fail, which simply gives us a true or false value that we can use in our automation workflow

57:09While there are additional advanced options here, the final step we're concerned about is the voicemail detection

57:16Let's make sure we toggle that on with VP as the provider

57:22This is helpful for our Make scenario since we need to accurately track whether the call was actually answered or if it just went to voicemail

57:28We're now ready to hit publish and test our newly created voice assistant

57:31Hey, it's Ben

57:34From Edji

57:36Is now a good time to talk about your business needs? Yes, it is

57:40Great

57:43I'm following up on your submission because we build custom AI agents and automations for companies like yours, anything from customer-facing bots to internal workflow optimization

57:46I'd love to understand a bit more about what led you, uh, to reach out

57:52What sort of processes or tasks are you looking to automate? I'm looking to implement custom AI agents to facilitate learning on an e-learning platform

57:59That sounds really interesting

58:05Um, so you're looking, um, to enhance, uh, the learning experience on your e-learning platform with AI agents

58:12Are there any specific challenges or bottlenecks you're facing right now that you hope these agents could help with? Uh, yeah, just streamlining the learning of the content library on my platform

58:17Got it

58:21So, you're looking to streamline how users access and learn from your content library

58:26That makes a lot of sense

58:29Thanks for sharing that

58:33Would it be helpful if I sent a quick proposal your way showing how we could support your goals? Yeah, that'd be great

58:36Perfect

58:38I'll send that to the email we have on file

58:41Thanks again for your time and I look forward to helping you with your project

58:43Great

58:44Thanks

58:45Bye

58:47You're welcome

58:48Have a great day

58:49Bye

58:51Great

58:53Our assistant is working as intended

58:55It's now the voice of our lead outreach, standing by, ready to make calls on our behalf

58:57Before integrating this

58:59assistant inside of Make

59:01Let's walk through the new path a lead will take through our extended scenario

59:03We left off here, but we're going to extend this for the trigger

59:05Nothing changes here

59:08A new Air Table record marked qualified still kicks things off

59:11Then our voice agent will call the lead using the number from their record

59:14We'll add a short pause to wait for the conversation to finish before we analyze what happened

59:17We grab the call record from VAP, then we check if the call was answered

59:20Answered, great

59:23We log the call summary and mark the lead as interested or not in Air Table

59:26No answer, no problem

59:31We fall back to emailing them a link to schedule a call and alert our sales team

59:36Since we're going to be logging Call summaries and interest level about our leads, we'll just need to head to our lead base in Airtable and add those

59:40We'll add a long text field called summary, a checkbox for interested, and while we're at it, let's add a new date for when a proposal was sent on, since in the final phase of this buildout, we'll be generating and sending proposals to these interested leads

59:54Back over in Make, we're ready to extend the lead qualifier scenario that we built earlier

59:59To keep things clean, let's just clone what we built and extend from there

01:00:04Name it lead qualifier plus voice agent, and now we're ready to continue building

01:00:09The beginning steps remain the same where we watch for new leads

01:00:13Then we'll add the VP module to create

01:00:17an outbound phone call

01:00:20We will need to set up the connection to our V P I account, which means we'll head back into that dashboard, click on API keys, then copy your private key

01:00:24If you don't see one in there, just go ahead and add a new one

01:00:28Give it a relevant name

01:00:32Decide if you want to restrict it to only work on certain sites, or if you only want it to work with specific assistants, then create the private token

01:00:35You'll see it pop up here, then just copy it

01:00:41But make sure to save this somewhere safe since you won't be able to view it again

01:00:44Pasting the key into the V P I module should set up our connection

01:00:46Then we can configure our call

01:00:49We'll just fill in these fields, giving it the assistant's ID, which you copy from the top of the Vappy Assistant page

01:00:52We provide the assistant with the lead's phone number pulled from their Airtable record

01:00:58But what number is our assistant calling from? If we head back into Vappy and click on the phone numbers tab, we can create a new free phone number with Vappy, specifying the area code to call from

01:01:09Note that at the time of this recording, only US area codes are supported by Vappy

01:01:15Since we're building this assistant for learning purposes, we can simply use a US area code like 223

01:01:23However, if you plan to deploy an assistant for production use and you or your client are located outside the US, you'll need to import a number from something like Twilio or Vonage

01:01:29Okay, once that number is created, we can copy its ID, not the number itself, and paste it into the Make.varpy module

01:01:36And with that, our voice agent is set up and ready to make calls triggered by our Make scenario

01:01:40Once the call is sent, we need to wait a bit before we check what happened

01:01:43Calls take time to connect, ring, and potentially have a conversation

01:01:47If we try to fetch the result too quickly, we could just get an empty response or an error

01:01:50So, let's add a short pause

01:01:53Insert a tools sleep module

01:01:56Set the delay to 300 seconds

01:01:58This little breather, 5 minutes exactly, gives Vappy time to do its thing before we peek in to see how it went

01:02:01To ensure things are working so far, let's add a new lead to our Airtable base

01:02:07We could add them via the form, but it's quicker just to duplicate an existing lead in order to create a new one

01:02:12Now, we'll head back and make and run the scenario to test that it's all working

01:02:17Hey, it's Ben from Edge AI

01:02:22Is now a good time to talk about your business? Yeah, it is

01:02:25Great

01:02:28I'm following up on your submission about exploring AI solutions

01:02:31We build custom AI agents and automations for companies like yours, anything from customer-facing bots to internal workflow optimization

01:02:33I'd love to understand a bit more about what led you to reach out

01:02:40What sort of processes or tasks are you looking to automate? Yeah, so I'm just interested in, um, seeing how we can build out some maybe AI-powered workflows to help the operations in my company

01:02:45That sounds interesting

01:02:50AI

01:02:55Powered workflows can really streamline operations

01:03:00Are there any specific bottlenecks or manual tasks you're hoping to reduce? Hoping to help my, uh, learning management system run more smoothly

01:03:06Got it

01:03:13Optimizing your learning management system can definitely enhance efficiency and user experience

01:03:19Uh, thanks for sharing that

01:03:25Um, would it be helpful if I sent a quick proposal your way showing how we could support your goals? Yeah, definitely

01:03:28Perfect

01:03:31I'll send that to the email we have on file

01:03:34Thanks again, and I look forward to your feedback

01:03:36Thank you

01:03:38You're welcome

01:03:40Have a great day

01:03:41Now comes the part where the automation becomes observant

01:03:43We're not just automating calls, we're building a system

01:03:47that pays attention to what happened

01:03:52Did someone pick up? Did the assistant get the job done? Was the lead interested? To answer those questions, we need to ask VBY for the results of a specific call

01:03:57And to do that, we'll use an HTTP module to make a request for that call record

01:04:03To better understand this module's function, let's explore what an HTTP request is and how it fits into the broader workings of the internet and how APIs fit into all of this

01:04:08I know it sounds complicated, but let's break it down with a simple analogy

01:04:14Remember earlier we learned how an automation workflow is like a factory's assembly line, where each module is like a machine performing a step in the process? Well, factories don't operate in isolation

01:04:20Sometimes your factory needs supplies, information, or services from outside its own walls

01:04:26A real factory might call a supplier to order more raw materials, ask a logistics company where a shipment is, verify parts, meet quality standards with lab testing, or request a maintenance crew to check the temperature of a remote machine

01:04:39Simply put, a factory coordinates with external partners to handle tasks outside its own expertise

01:04:44Just like real-world suppliers don't take factory orders shouted over a fence, external services need a structured way to receive requests

01:04:52That's what an API, or application programming interface, is

01:04:59In our factory analogy, the API is like the official order form that your external partners use to process requests, which you would fill out to order some special machine parts to use within your factory

01:05:07Online services like Vappy, Airtable, or Slack all offer APIs that follow the same principle

01:05:11They give outside entities like Make.com a structured way to send and receive information

01:05:16APIs give us a clear, consistent way to ask for something and get a predictable, reliable response

01:05:20There are several types of HTTP requests that serve different purposes

01:05:24So, you could be saying, "Get me this thing

01:05:27Post or add this new thing

01:05:31Put this info where it belongs

01:05:35Replace the whole thing

01:05:39Patch just this one part of the info, but don't replace the whole thing

01:05:43Delete this thing." In our case, since we're about to be making an HTTP GET request inside of Make, we're essentially saying, "Get me this call summary

01:05:48Here's what I want, and here's who I am

01:05:53I've got the proper permission to access what I'm requesting." While platforms like Make.com and n8n provide a visual interface for building workflows, under the hood, they're actually making API calls to connect with these external tools

01:05:59So even though you're working with visual blocks, these modules use the same underlying language that developers use to connect services across the web

01:06:05Yes, this is no-code development, but that doesn't mean code isn't running

01:06:08It's just happening behind the scenes

01:06:11That was quite the detour, but an important one

01:06:14one because it gives you a firm grasp on how things work on a deeper level

01:06:17Now that you understand what an HTTP request is and how it fits into the big picture, let's set this module up to go get the record for the call that was just made

01:06:24We'll set the method to get

01:06:30But where are we getting something from? Well, we're going to make a request to VP's API to get the call that just happened

01:06:36If we check out the VP documentation, we can see that we need to send our request to this URL, where the last part of the URL is the ID of the call we're fetching

01:06:42So let's copy that URL and paste it into the HTTP module, adding on the call ID from the vari module's output in the header section

01:06:54Here's where we add instructions, like putting a label on a package by putting authorization in the name field

01:06:59This just means we're saying we have the authorization to get this info, and the proof is the value of the header itself

01:07:05Another way to think of that proof is that we have a key to unlock this special box that contains the information we're requesting

01:07:11That key is the API key that we generate from VPY

01:07:17So, in the value field, we'll type "bearer", then paste that key next to it

01:07:23This roughly translates to the person who possesses or bears this key has permission to access what they are requesting

01:07:26Finally, we'll say yes to passing the response

01:07:30This means the module will break apart the response into structured fields that we can easily use later in the scenario

01:07:34Let's make Sure, this is working by running this module only

01:07:39Here at the bottom, it's asking for the call ID that we want to get, which we can just grab off of the last time the VAP module made a call

01:07:45Placing that call's ID here and hitting save will now cause this HTTP GET request to fire off, and we quickly see that it was a success

01:07:52We now have access to all of this data from our call, including the summary, which, as you recall, is the result of that prompt we added into VP to summarize the call for a sales team

01:07:59We also have access to the analysis, which tells us if the call was successful

01:08:06This is perfect since we'll use both pieces later in the scenario to update the lead's Airtable record with their call summary and interest level

01:08:11So now that we're monitoring the call results, let's start implementing those next steps

01:08:15First, we want to determine whether the call was answered

01:08:20So, we'll set up a router to create paths for both answered and unanswered calls

01:08:26When someone answers the call and engages with your voice assistant, it's a valuable interaction that your sales team needs to know about

01:08:29Let's set up a filter to check if someone answered the call

01:08:33On the first route, we'll add a filter with a condition that checks for calls where the data do the ended reason equals customer ended call

01:08:36Among all the data points available, this is our most reliable indicator that the call was answered and didn't go to voicemail

01:08:50On the second route, we'll do the opposite and set the condition to filter for cases where data ended reason does not equal customer ended call

01:08:56On the answered route, we want to know if the lead was interested in being sent a proposal or not

01:09:01So we'll add another router that splits into two paths based on the call analysis, specifically the success evaluation

01:09:06Remember earlier when we told Varie to evaluate if the call was a success based on whether the lead wanted a proposal or not? That evaluation is contained in this data here

01:09:18Since this data is simply true or false, we'll check whether the analysis is equal to true success or false failure on each route

01:09:25For both routes, we want to update the lead's record with the call summary and note whether they We're interested in a proposal

01:09:29So on each route, we'll add an Airtable update a record module

01:09:33On the interested route, we'll target the lead contacts based by this lead's ID and update the contacted on field to

01:09:37Now add the call summary and check yes on interested

01:09:50We'll do the same for the not interested route, but check no for interested

01:09:55Now, our sales rep can instantly see when the lead was contacted and what transpired during the call

01:10:01The system automatically documents each interaction, just as a human rep would take notes after speaking with the prospect

01:10:07By the way, in case you're curious, this process technically performs a PUT request under the hood, where it puts or updates something about the record

01:10:11without replacing it all together

01:10:15Of course, not all of our VP calls will be answered

01:10:18This happens, people are busy or they screen unknown numbers

01:10:21That's why we build in a backup

01:10:24On the not-answered route, we'll keep the steps from our initial build where we send that lead an email to schedule a call, and we let our sales team know about them

01:10:29With this all locked in place, let's run the scenario to make sure it's working

01:10:34Hey, it's Ben from Edge AI

01:10:38Is now a good time to quickly talk about your business needs? Yes, it is

01:10:41Great

01:10:45Thank you

01:10:48I'd love to understand a bit more what led you to reach out to us

01:10:52Are there specific processes or tasks you're looking to automate? Yeah, looking to, uh, implement AI agents

01:10:57That's exciting

01:11:02Implementing AI agents can really streamline operations

01:11:07Um, are there particular tasks or workflows at your company that you find especially time-consuming or manual, which you're hoping to improve with automation? Yeah, just hoping to, um, have the agents trained on the learning material so that they can help my students

01:11:10That makes a lot of sense

01:11:13Training AI agents to assist your students could really enhance their learning experience

01:11:15Thanks for sharing that

01:11:18Would it be helpful if I sent a quick proposal your way showing how we could support you in developing those AI agents? Yeah, that would be perfect

01:11:22Excellent

01:11:26I'll send the proposal to the email we have on file

01:11:29Thanks again

01:11:31We've done a lot

01:11:33Let's zoom out for a second to recap

01:11:36With our current scenario, we now have a system that detects qualified leads, places an AI-powered voice call with no manual effort, waits, listens, and reacts depending on whether someone answered and whether they were interested or not, logging the outcome accordingly

01:11:43As of now, the voice assistant works, but it's not as capable as it could be

01:11:51Without knowing our lead's name or anything about their company and needs, the agent's ability to pitch is pretty limited

01:11:59Our next step is to enhance our scenario by researching our lead with OpenAI and passing those insights to our Vappy Assistant, allowing it to personalize each call

01:12:03Essentially, we're going to have a search

01:12:07feature that is going to not only just use the voice agent for, uh, doing the research and getting more information

01:12:11We're going to use OpenAI's, uh, search models

01:12:16So, when people fill out that form we made, then we're going to use OpenAI to research the internet for that lead and get some information on that

01:12:21Then, we're going to send a call to them again using Vappy

01:12:25This time, it's going to be personalized with the information that we got from that web search

01:12:29So it's really, hey, we know this about you, but what else? We're looking for this information on you

01:12:35You can really get a, a, a complete picture of who this person is before we even booked them in for a call with our sales team

01:12:40So with the VIP module, we're currently using, Unfortunately, we're not able to feed anything into it, at least not at the time of this recording, based on the VIP module's current setup

01:12:46But we can solve for this by switching out the VP module with a more custom approach using an HTTP module

01:12:51So, let's drag it out of the workflow and unlink it

01:12:57And since we'll be borrowing some of the values from it soon, inside a new HTTP make a request module

01:13:06Since we're making a manual request out to the Vappy API, we need to specify the URL, just like we did in our existing HTTP module

01:13:10So, we can go ahead and copy that URL from the get module

01:13:14Since we're simply placing a Vappy call and not retrieving an existing one, we won't need the calls ID

01:13:18So, we'll leave that off, and we'll change the method type to post

01:13:24The header remains the same, but we need to add a second item where the name is content type

01:13:33Value is application/json

01:13:37Content type is like labeling the envelope you're sending

01:13:41Application/json means inside this request, the data is structured like a JSON object

01:13:45It's like writing English or Spanish on the outside of a letter so the recipient knows what language to expect when reading it

01:13:53Continuing down the module, we'll then set body type to raw, which means we're manually writing out the data we want to send to V.P.I

01:13:58And we set content type to application/json, which again tells V.P.I

01:14:03to expect data formatted as JSON

01:14:08And I know many of you don't know what JSON is, but it's less intimidating than You might think

01:14:12It's really just a pair, the key and the value, just like in a spreadsheet where you have the keys like phones, name, and email

01:14:19Then you have the values, the actual data that goes with each key

01:14:22It's an easy-to-read way to structure and share data

01:14:26In JSON, everything sits inside curly brackets

01:14:29This is called an object

01:14:33Both the keys and values need to be in quotes with commas separating each key-value pair

01:14:36Don't worry if you're not a JSON expert

01:14:39Many free online tools can help you check if your JSON formatting is correct

01:14:42So back in Make, down in the body of our HTTP call out to Vappy, we're going to add some JSON to save some time

01:14:49We'll grab some values from the VPY module we were using earlier, including the assistant ID, which we'll paste into the JSON

01:14:54And we'll also grab the VPY phone number ID off that old VP module and paste, reuse it in our new HTTP module

01:14:59We're just doing it a bit more manually

01:15:03The main difference here is in this assistant override section

01:15:09As it sounds, we are overriding the assistant within custom variables

01:15:14These are essentially placeholders that will be replaced by the lead's name, company, and the research we perform for each of them

01:15:20This way, when we say, "Hey, Vapy, call this lead," we're also saying, "And here's info about them to use on the call." Now that we're going to be sending these variables into the assistant, we need to head back over to the Vappy dashboard and tell our assistant

01:15:26Ben to be expecting that information and instruct them on how to use it

01:15:32In the first message, we can add the first name variable so our assistant can greet our lead by name

01:15:38In the updated prompt, we'll inform Ben that he will receive custom data via variables such as the lead's first name, company, and company research, and to use these details to personalize everything on the call with the goal of pitching more effectively

01:15:50With our assistant ready to receive all that custom info, we just need to perform research on our lead, and for that, we'll be using OpenAI

01:15:54Let's add an OpenAI

01:15:58Create a chat completion module in line just before we make the Vappy call

01:16:02You'll need to set up the connection with your OpenAI account

01:16:06and make sure you get an OpenAI API key and also have some credits to use for this

01:16:12To do this, you can log into your account at platform.openai.com, log in, and click on API keys

01:16:17Then create a new one, making sure to copy and save it in a safe place

01:16:21Then you'll click over to billing and add some credits, making sure you have an active credit card set up

01:16:25With that connection set up, we'll select the model

01:16:29Since we're doing research, I'm choosing GPT-4o mini search preview

01:16:33By the time you watch this, there may be other options

01:16:36The important thing is to choose a model that can do search

01:16:39In the messages section, we'll set the role to user, which just means this message is coming from a user, you in this case

01:16:42The text content is where we Place the prompt

01:16:48Essentially, we're telling it to serve as a research assistant that uses our leads' information to generate a summary of how an AI automation agency could help them with their needs

01:16:53Let's see how it works by running this module, only giving it an example company name and notes for testing purposes

01:17:01As you can see, it's running and performing research for us

01:17:08But notice how the result is formatted in paragraphs

01:17:15While that might look fine, it actually causes a problem because when we try passing this result into our HTTP module, it needs to follow strict formatting rules

01:17:22Those paragraph breaks can quietly break things behind the scenes and cause the system to reject it since it won't be valid JSON

01:17:28There are a couple ways to fix this

01:17:35We could either demand that ChatGPT gives us our summary in JSON, or we could add a text passer in between the GPT and HTTP modules, which removes those line breaks for us

01:17:41Since there may be other situations when you need to transform data in your future workflows, it's helpful to get some practice passing text

01:17:44So, let's add the text passer replace tool

01:17:48For the pattern, we'll add this regular expression

01:17:52This essentially finds any line breaks, so we can replace them with a new value, which we'll leave blank

01:17:55In other words, instead of the line break, it will be replaced by nothing, aka removed

01:17:59We want global match to be set to yes, so that it finds all line breaks, not just the first

01:18:03one, then no for the rest of the options

01:18:09Finally, we'll select the text we need to pass the result from OpenAI's research

01:18:15With this reformatting in place, we can now reference that clean text inside the company research field of our HTTP body

01:18:19Finally, we'll say yes to pass the response and close out this module

01:18:23Notice how we still have this red error icon on the second HTTP module

01:18:28It's broken because it's trying to reference the call ID from the original VP module that no longer exists because we deleted that module

01:18:35Instead, it needs to reference the call ID from our new HTTP module, which manually makes that VP call

01:18:42Since we haven't yet run that new VP replacement module, we'll run it in isolation, feeding it a phone number and whatever info just to get it to run

01:18:48Once it runs, we can now access and reference the ID field from it for future run-throughs of this workflow

01:18:54We're now ready for the big payoff

01:19:00Make sure you add a new lead to your Airtable with a valid company it can research

01:19:06Let's run the scenario to make sure everything is working properly

01:19:10Hey Mark, it's Ben from Edjai

01:19:15Is now a good time to talk about your business needs? Yeah, sure is

01:19:17Awesome

01:19:20I'm following up on the form you submitted

01:19:23We build custom AI agents and automations for companies like View Mastery, anything from customer-facing bots to, uh, internal workflow optimization

01:19:26I'd love to understand a bit more about what led you to reach out

01:19:32What sort of processes or tasks are you looking to automate? I'm looking to implement AI agents to facilitate the learning journey on my e-learning platform

01:19:38That sounds like a great initiative

01:19:46Enhancing the learning journey for your students can really make a difference

01:19:53Are there any specific bottlenecks or manual tasks you're hoping to reduce with these AI agents? Just hoping to increase the effectiveness of our content by supplementing it with these AI agents

01:19:58Got it

01:20:03So, you're looking to enhance the effectiveness of your content by providing real-time support to your students

01:20:07That's a smart approach, especially with the extensive library you have at View Mastery

01:20:10Thanks for sharing that

01:20:13Would it be helpful? If I sent a quick proposal your way showing how we could support your goals? Yeah, that would be perfect

01:20:16Perfect

01:20:18I'll send that to the email we have on file

01:20:21Thanks again, Mark

01:20:23All right

01:20:25Thanks

01:20:27Exciting

01:20:30Our scenario is working and our voice assistant is now empowered to perform dynamic pitches based on our lead's unique information

01:20:32We're almost there

01:20:35Finally, within build 3, we take this about as far as we can within a beginner tutorial like this

01:20:38Um, and this is a really, really powerful thing once you've added in these extra features

01:20:41So, after the call again, we're going to analyze that and deal with if they answered or didn't answer

01:20:50And long story short, if they answered and they said that they were

01:20:59interested and said, "Hey, yes, can you please send me a proposal?" Then we're going to take all of this research that we've done and all the information that we got from the phone call in order to generate them a custom proposal and saying, "Hey, look, this is what we want to kick off with you." Because you need to make a proposal in order to start any kind of services, or most kinds of services, but we can automate the generation of a proposal, which can take hours and hours and hours for businesses

01:21:08And we can use all of this information we collected, and they've said, "Yes, hey, can you send it over?" And then we use an application called PandaDoc, and we can create a template of a document for our agency, in this case, and it's going to use AI in this

01:21:19case we're going to use a ChatGPT, uh, node here on Make, and it's going to take all of this information and write a personalized proposal on how we would kick things off with them, of what we're proposing in terms of the scope of work for them, like, we will do this, this, it sounds like you need this, we can do this, this is roughly how much it's going to cost, etc

01:21:36And then using PandaDoc, we can send that as an e-sign link so that they're ready to sign, and we get notifications about if they've viewed it, if they've signed it, etc

01:21:41And so by the time you've done this, we've automated everything from the initial point of contact where the lead said that they're interested in our services, to learning more about them, to determining if they're qualified for our offer, uh, to sending them a custom proposal and ultimately for them signing the doc through PandaDoc, and they're ready to kick things off with us

01:21:49So that is an explanation of, of build three and what we're really trying to go here

01:21:56I hope this has been helpful to clarify things for you, um, because this is really, really powerful if you can wrap your head around it

01:22:04So please stick with it

01:22:12Once a lead has expressed interest, it's the perfect moment to harness that momentum and transform it into something concrete, a tailored business proposal

01:22:17Why wait for someone on your team to do this manually when we already have all the context we need? With the help of OpenAI and PandaDoc, we can generate, send, and log a custom

01:22:23proposal without anyone lifting a finger

01:22:30So, in the final section of this course, we'll be tacking on a proposal generator to the end of our workflow

01:22:36We'll use OpenAI to create the custom text to plug into a proposal generator

01:22:40We're going to be using PandaDoc as our tool for creating and sending proposals

01:22:44It allows you to create templates with placeholders that can be filled in dynamically from your automation workflows

01:22:48Here's how to create and configure your template in PandaDoc

01:22:51Log into the PandaDoc dashboard

01:22:54Just create an account if you don't yet have one

01:22:57Then go to templates and click plus template

01:23:01For sake of ease, we can select an existing template to remix, such as one of these business proposal or advertising sales proposal templates

01:23:07I'm going to use a template I already created here

01:23:12Within a Panda Doc template, you are able to drop in tokens, which are basically placeholders that can be replaced with actual values, such as your client's company name

01:23:18In this case, you can set up this template however you'd like, but as you can see, I've set mine up like this with a client introduction section, addressing them by name

01:23:24In the goals and plan section, I've left room to insert information about my lead's goals and the services I'll recommend, and a plan for how I'll implement things

01:23:28So you can see how it works

01:23:33We'll create those as variables

01:23:38Over here in the sidebar, we'll add proposal.goals will be a paragraph

01:23:42or two summarizing the client's top priorities

01:23:49Proposal.services will be a bulleted list of the recommended services

01:23:55Proposal.implementation will be a concise execution plan to deliver the above

01:24:01In the pricing section, I've already added placeholders here: proposal pricing, and for a breakdown of services and costs, and proposal.total, the full estimated project total

01:24:07Down in the agreement section, we're requesting signature and including the lead's info

01:24:13Once everything is in place, name it something relevant and save it because you'll soon be using this template inside your Make's Panda Doc module

01:24:19Optionally, you could spend some time styling this template with a logo, brand colors, etc

01:24:25Remember, this document will be client-facing, so make it look and feel as professional as the service you're offering

01:24:31With your PandaDoc template ready and tokenized correctly with placeholders, we're ready to include it in the final sequence of our Make scenario

01:24:36We'll add the PandaDoc create a document module, set up a connection with our PandaDoc account, name the document based on the company we're sending it to, and select the proposal template we created earlier

01:24:47We'll fill in these values, giving the module the lead's email to send this to and include all of the necessary info about our client, like the company name and the client's first and last name

01:24:59For all these proposal tokens, we'll be generating

01:25:02These values with AI in a moment

01:25:06For now, we'll scroll down and say yes to send a document because we want to email this Panda doc to our lead

01:25:10Fill in the subject line using their name and company, write a short message, then hit save

01:25:15Next, we'll use OpenAI, create a chat completion module to help us write a clear, convincing proposal

01:25:22We'll select a quick and efficient GPT model, and in the prompt, we feed it instructions about its role as a sales expert with context about the services our mock company offers, like AI automation and agent-based systems, information about the client, including the company research we did earlier in the workflow, and the summary of the call our voice assistant had with them

01:25:46Then we clarify its task to identify the most relevant services we can offer them, and we demand the output to be in JSON format so we can make easy use of it in the modules after this

01:25:57If we go ahead and run this module, only passing in some dummy data for the call summary and company research, we'll see it efficiently generates this relevant info organized as JSON, like we requested

01:26:08We're almost ready to plug these values into the Panda doc module, but we first need to add a pass JSON module to prep the message content output from OpenAI, breaking it up into discrete values that are available as variables we can inject into our proposal document in the next step

01:26:25To plug these proposal values into their slots in the Panda do module, We first need the JSON module to run

01:26:32While we could run our entire scenario, there's a quicker way

01:26:38Go into our OpenAI module, grab the expected JSON format, and paste it as dummy data into the JSON module to test it

01:26:44Perfect

01:26:50Now, we can see it's passing correctly, and we can now go into our Panda Doc module and plug those variables into their corresponding token slots

01:26:56Finally, we want to bring things full circle by updating the lead's Airtable record so that our sales team can see when the proposal was sent

01:27:02So in the proposal sent on field, we'll add a timestamp with now

01:27:08This keeps everything tidy

01:27:14So when someone on your team looks at a lead, they know a lead was created, they were qualified, they were called, including A call summary, they were interested, a proposal was sent

01:27:18No one has to chase a status update

01:27:22It's all there in one glance automatically

01:27:26Let's do a final run of this scenario to make sure all of the moving pieces are working correctly

01:27:30Hey Brad, it's Ben from Edge AI

01:27:34Is now a good time to quickly talk about your business needs? Yeah, it is

01:27:36Great

01:27:38Thanks

01:27:40I came across some info about View Mastery

01:27:42It sounds like you're really focused on helping developers learn VDJ's efficiently

01:27:44We build custom AI agents and automations for companies like yours

01:27:49Anything from customer-facing bots to internal workflow optimization

01:27:53I'd love to understand a bit more about what led you to reach out

01:27:57Are there specific processes or tasks you're looking to automate? Yeah, I'm looking to implement AI agents for learning who are trained on the content library of my learning platform

01:28:03Uh, that makes a lot of sense

01:28:10Creating AI agents that can assist learners by leveraging your content library sounds like a great way to enhance engagement

01:28:16Are there particular bottlenecks or manual tasks you're hoping to reduce with these AI agents? Yeah, just hoping for uh, the students to be able to comprehend and apply the concepts more effectively with the agents

01:28:23That's a smart approach

01:28:30Empowering students to better understand and apply concepts with AI support can really boost their learning experience

01:28:36Thanks for sharing that

01:28:43Would it be helpful if I sent a quick proposal your way showing how we could support new mastery with tailored AI solutions? Yes, please go ahead and do that

01:28:45Perfect

01:28:48I'll send the proposal to the email we have on file

01:28:51Thanks again, Brad

01:28:54Thank you

01:28:56You're welcome, Brad

01:28:59Thanks for your time today

01:29:01If you have any questions later or want to discuss further, just reach out

01:29:03Have a great day

01:29:05The workflow seemed to have worked as planned

01:29:08Inside Airtable, we can see that the proposal sent on date was added

01:29:10Now, let's check the email that we told PandaDoc to send the proposal to

01:29:16Heading into that email, we can see that it worked perfectly

01:29:22Our proposal doc arrived, which the client can open up to go view their proposal, which we can verify has been properly drafted, detailing the client's specific needs and our plans to help them

01:29:28From here, the client can sign the document, date it, and finish it out

01:29:34An added benefit of PandaDoc is that we don't need to create additional automation steps in Make.com to track when leads view or sign proposals

01:29:40PandaDoc handles this automatically by sending notification emails to our email whenever a lead views or completes a proposal

01:29:46With this final stretch, you've created a full system that not only identifies and qualifies leads, it translates interest into action

01:29:52Of course, there are many other steps you could add to this scenario

01:29:58For example, the delay we added after the call takes place works in most cases, but if the call exceeds 5 minutes, the system would incorrectly mark it as not answered, even if it was successful

01:30:03The foolproof solution would be to implement a webhook that listens for the call to end, but that's outside the scope of this beginner build

01:30:16You could even add a whole extension to this workflow where you detect when a lead signs the proposal and then onboard them with an automated client orientation workflow

01:30:21I encourage you to get creative and add on to it to learn and challenge yourself

01:30:27For now, I want to share some troubleshooting tips to keep in mind as you go off on your own and build your own workflows

01:30:33[Music] As you take your next steps and start building your own AI-powered automations, I I want to be completely transparent

01:30:39You will encounter issues

01:30:44Platforms will change, tutorials may become outdated, and unexpected problems arise

01:30:48This isn't a flaw in the system; it's a natural part of working in a rapidly evolving field

01:30:52The truth is, even experienced developers spend a significant portion of their time troubleshooting

01:30:58I can't count how many times I found myself yelling at my screen because some seemingly simple thing wouldn't work

01:31:03It's part of the process for everyone

01:31:07There's an old saying, "Give a man a fish and you feed him for a day

01:31:11Teach a man to fish and you feed him for a lifetime." This sums up our approach to technical education

01:31:17If you are spoonfed every solution, you'll end up just Copying existing systems and won't be prepared for real-world challenges, and you won't develop ways to differentiate yourself either

01:31:22So, think of technical problem-solving as a muscle

01:31:28Right now, it might be underdeveloped, and using it feels uncomfortable

01:31:32That's normal

01:31:36But with consistent exercise, tackling problems, finding solutions, learning from mistakes, this muscle will grow stronger

01:31:39It's a gradual process that develops through experience

01:31:42Each problem you solve builds your expertise, making future challenges less daunting

01:31:46While you can't rush this journey, you can fully embrace it

01:31:52When you feel that sense of being out of your depth, try to recognize it not as failure, but as growth

01:31:54You're in uncharted waters

01:31:57You're pushing your limits and expanding your capabilities

01:32:00The most valuable learning happens precisely in these moments of struggle

01:32:03So, with that growth mindset, let's cover some tools you can use for troubleshooting

01:32:09You probably won't be surprised that I encourage you to leverage AI as you develop your skills

01:32:15If you run into errors in your workflow, by heading over to ChatGPT or a similar LLM, you can lean on its ability to support you in solving the issues you encounter

01:32:21The trick here is to describe your issue in detail

01:32:27Remember to give enough context so the AI can grasp what you're building, the specific step you're on, and the expected outcome versus the problem you're experiencing

01:32:30experiencing

01:32:34Include screenshots, error codes, and let it search for the latest information

01:32:38There will be times your issues are a little more complicated

01:32:43For complex problems, you can even try the deep research mode to get comprehensive information on specific platforms or issues

01:32:48Sometimes the first suggested solution won't be the right one, but as you engage in back and forth dialogue, as you see me doing here, where I am giving it more info, the AI gains more clarity about your issue and can better narrow down potential solutions

01:32:57And if you truly want to learn, don't just do what it says without curiosity

01:33:06Ask it to help you understand why the issue happened and why the new solution ultimately worked

01:33:14If you are hitting a wall, it's possible that others have already hit that same wall and climbed over it

01:33:20So, by doing a traditional Google search, you can look for existing threads or community posts about similar issues

01:33:24Many problems you'll encounter have already been solved by others

01:33:28Of course, YouTube is another great resource

01:33:32Search for recent tutorials that show updated interfaces and workflows or that highlight key details that could help resolve your issue

01:33:37We now have access to tools like Google AI Studio that can watch your screen and provide real-time support as you work

01:33:44Think of this as an experienced guide peering over your shoulder and helping you step by step

01:33:50This eliminates the need to manually type out your problem and provide screenshots to ChatGPT, since you can give the tool permission to observe what's on your screen and guide you through solutions using voice assistance

01:34:01Take a look at how powerful this is as it helps diagnose what's causing this error

01:34:07I'm getting an error on this HTTP module where I'm trying to make a post request out to the VAPI API

01:34:13Any idea where I should start looking for a solution to this error? I see the workflow you've created and that you are receiving an error when trying to make a post request to the VAPI API

01:34:19Are there any error messages that you can share? It's a 400 bad request error

01:34:25Do you see the information here in red? Okay, I see that it's a 400 bad request error

01:34:31The message indicates there's an issue with the JSON formatting of your request body

01:34:37It seems like there's an unexpected character, either an expected or after an array element in JSON at position 1167, line 12, column 51

01:34:47Would you like me to help you review the JSON structure in your request to identify any syntax errors or missing commas or brackets? Yes

01:35:00Can you notice anything in here that is wrong? Looking at the JSON, it seems like the error might be in the company research field, where you have an array containing a single element, and that element seems to be an expression

01:35:08If you're trying to pass a single string there, try removing the curly bracket

01:35:16Also, can you double-check that all your keys and values are properly enclosed in quotes? Formatted as strings? Learning to read and apply documentation is a critical skill

01:35:20Each platform has detailed guides that are regularly updated

01:35:25Often, you'll find information there that can help solve your issue

01:35:29If it feels overly technical, you can circle back to asking something like ChatGPT to help you understand the documentation and how it applies to your specific issue

01:35:34Finally, there are plenty of online communities, like the ones me and my team run, related to the platforms you're using

01:35:41Join Discord servers or other forums, search for similar issues, or even ask questions directly

01:35:46You'll be surprised by how helpful and supportive these communities can be

01:35:52If your goal is to build real automations, For real clients, things won't always go according to plan

01:35:56Platforms will change and requirements will shift

01:35:59The ability to adapt, troubleshoot, and find solutions is what separates successful builders from those who give up early

01:36:03The most successful people in this field aren't those who never encounter problems

01:36:09They're the ones who persist through difficulties, who see obstacles as puzzles to be solved rather than roadblocks to progress

01:36:16So, when you hit that inevitable moment where something isn't working, and you feel stuck, remember this is normal

01:36:19Take a breath

01:36:23Step away if needed

01:36:26Then come back and work through your troubleshooting toolkit

01:36:29Each time you solve a problem, you're not just fixing that specific issue

01:36:32You're becoming better at solving all future problems

01:36:35This resilience and problem-solving ability will be just as valuable to your success as any technical skill you learn

01:36:41So, embrace the journey of building your technical skills

01:36:48In the next and final section of this course, I'll show you how to sell your newly built systems to real-world clients

01:36:52Now that you understand how AI automations work and can build them for yourself, let's talk about actually making money with these skills

01:36:57But first, let me destroy a huge misconception that many people have

01:37:01You don't need to build the next ChatGPT or create some revolutionary AI startup to make some money in the AI space

01:37:06The real opportunity is much simpler, helping businesses to understand and implement AI automations like what you've just learned

01:37:12This is how I monetize my AI automation skills, and it has been the most explosive growth I've ever experienced in my career

01:37:20The good news is, if you've made it this far in the video, you're much closer to being able to tap into this starving market for AI automation services than you think

01:37:25But don't take my word for it

01:37:31Let's hear from some of the world's most famous and successful businessmen

01:37:37If I was 25 years old today in 2024, what would I do? What's a good sector to get involved in? What business would I get involved in? I think everything is looking at AI now in a different way, and I think AI Growth is going to be exponential

01:37:42So, anything to do with AI

01:37:48Now, what could that be? In the simplest form, it's helping people use the technology

01:37:54There's going to be a massive amount of people wanting to use it that don't know how to, and they're willing to pay to solve that pain point

01:37:58So, is that consulting? Not really

01:38:03It's implementation and execution

01:38:07And so, helping a business do that transfer into a world where they're controlling their data and getting information from it

01:38:11Now, the majority of businesses in America, for example, are between 5 and 500 employees

01:38:15So, they're small businesses

01:38:17They create 62% of the jobs

01:38:20They want to use AI

01:38:22You should help them solve for that, and they'll pay you

01:38:25Mark Cuban is saying The same thing as well

01:38:28That the biggest opportunity right now is helping small to medium-sized businesses who don't understand AI and automation yet, but desperately need it to survive

01:38:30And they're right

01:38:33Here's why

01:38:36According to recent data, there are 1.7 million businesses in the US alone, making between $500,000 and $10 million per year

01:38:40These are small businesses, which make up 62% of all jobs in the USA

01:38:45These businesses know that they need AI automation to stay competitive, but they don't have the time to learn it themselves

01:38:49And there's basically no one there to help them at all

01:38:55All of the big consulting firms are looking at other big businesses, and no one is serving this small business market who still need AI

01:39:00automations just as much as anyone else

01:39:06So basically, almost all small businesses are starving for AI automation services, like education services, in order to help them to understand what AI and automation is and why they need them

01:39:11Then there's consulting services, which help them to identify where AI automation can help them the most

01:39:18And finally, there is actual implementation services to help them build and maintain their AI automation systems

01:39:23Right now, based on data I've collected in my community, for every person offering AI automation services, there are over 1,100 businesses in the USA alone that need help

01:39:29One to 1,100

01:39:35The market is completely untapped and will be for a very long time

01:39:40And that's where You come in, which is helping these hardworking small business owners to understand and implement AI automations so that they can keep up and survive through this AI revolution, just like you

01:39:44We've seen this exact same pattern happen when the internet came out

01:39:48The companies that helped businesses to adapt to the web made fortunes, as did the companies that they helped

01:39:53I personally spotted this opportunity in early 2023 and started Morningside AI, my AI automation agency

01:39:58And since then, I've generated over $5 million selling AI products and services

01:40:03And as a company, we're only just getting started

01:40:09And the best part is that, as we've proved in this video already, that you don't need to be a technical genius to understand AI and even to build your own AI automations

01:40:14You just need to be one step ahead of the businesses that you're going to help

01:40:20Let me show you the three specific ways that you can start making money with your AI automation skills

01:40:24So, there are basically three services that you can provide to help businesses with AI automation

01:40:28First, there's education

01:40:32This is teaching businesses about AI automation, running your own workshops or presentations, or training their teams and creating courses

01:40:38Businesses are desperate for someone who can explain this stuff in simple terms to you, just like I've done for you in this video, what the hell AI is, what automation is, and what it can do for them

01:40:49And after watching, This video and a few others that I've made on this channel, you'll know more than enough to start educating businesses and helping them to sort of move from where you were at the start of this video to where you're going to be at the end of it

01:40:55I'll be covering which videos those are in a moment

01:40:59And secondly, you have consulting services

01:41:03And this is where you analyze a business's operations and show them where AI automations can help them save time or make extra money

01:41:06You're essentially being their AI automation strategist

01:41:10For example, you could recommend a lead qualification workflow like the one you just made to help a struggling sales department

01:41:13And third is implementation

01:41:17This is where you actually build and Deploy AI automation solutions for businesses

01:41:20Or better yet, like my agency, you can do all three of these

01:41:24You can do education, consulting, and implementation

01:41:27But you don't have to do it all at once

01:41:30It took us like over two years to get here, so there's no rush

01:41:34And believe it or not, there are people with only a few months of experience in the AI automation space selling all of these kinds of services right now: education, consulting, and implementation

01:41:37And the demand from businesses is increasing insanely fast right now because they're all switching on and realizing they need to do something about this right now

01:41:43But here's the thing, you still have one problem, which is that you still don't really know

01:41:47enough

01:41:51You're close, but you're not quite there

01:41:55The way to make money in the AI automation space, or with any services really, is to create what's called a knowledge gap between yourself and the people that you're trying to help

01:42:01Your knowledge gap is your money maker

01:42:07Businesses will pay you in proportion to how much more you know about AI automations, workflows, and their business applications than they do

01:42:12So now, while this video has taught you a lot, your knowledge gap is still fairly small, but we can fix that

01:42:18Let me break down exactly what you need to do to extend your knowledge gap so that you can start monetizing this skill

01:42:23This video is step one, as long as you've been taking notes and followed all of the tutorials

01:42:29by building the automations alongside me, you're already far ahead of most people who have no idea about how to build AI automations

01:42:34Step two is building even more experience with AI automation so that you are more familiar with the platforms and better understand different ways that they are being used to help businesses

01:42:38I've only given you a taster here

01:42:42This is foundational knowledge, the point of this video

01:42:46But to do this and extend your knowledge gap, you can take my free course on Skool, where you'll build another five to ten automations

01:42:50And the link to join will be in the description below this video, and this will further expand your knowledge gap without paying a dime

01:42:56Once you've done that, you'll have What I call foundational knowledge

01:43:03So you understand the core AI concepts, you can build basic solutions yourself, and you know what's possible for businesses right now

01:43:08And then comes the big decision: do you want to go deeper technically, or do you want to start monetizing what you already know? As we've already covered, building and implementing AI automations is only one of the services that you can sell

01:43:20Naturally, the technical skills needed to make money in implementation, actually building AI automation systems, are far greater than just having a foundation

01:43:26You know, so you need to be a lot more skilled in terms of experience and being hands-on with the technology to deliver high-quality services for Your clients

01:43:33However, with a good foundation, you're basically ready to start having a crack at selling AI automation, education, or consulting

01:43:45So, this decision of whether you go to education and consulting or actually building it depends on what you're really interested in

01:43:48I'll use myself as an example

01:43:52I've always loved making things, from like block houses when I was a kid to like brewing beer with my my granddad, to tinkering with engines

01:43:56So when I hit this foundational level in early 2023 with my skills, I naturally kind of just dove deeper into the technical side

01:44:02I kept building more and more complex AI automations, which led me to starting Morningside AI, where we now build AI solutions for clients

01:44:08But Here's the thing, a lot of people aren't like me, and chances are you aren't either

01:44:14They don't get much of a buzz out of the building side of things

01:44:19And because of this, many of you are going to be better at teaching and actually working with people to help them understand and get value out of this technology than actually building stuff

01:44:26But that doesn't mean that you can't make money in the space

01:44:32For you, using the foundational knowledge that you'll have after you finish that free course to actually sell AI automation educational consulting makes way more sense

01:44:38So the key is being honest about your strengths and your interests and setting real expectations on how technical you want to get in your career by picking

01:44:42whether you want to sell educational consulting or development services

01:44:47You have a hard stop on how much you need to learn before you start taking action

01:44:50So this essentially prevents you from getting stuck in an endless learning phase

01:44:54I see it all the time where people just keep, oh, I don't know enough

01:44:57I need to keep learning, and they're forcing themselves to do something they're not really good at or they don't want to do, and they're procrastinating when they could be out there making money

01:45:03So, in summary, your options from here are, if you love building and want to learn more, then just keep going

01:45:07Keep following that interest and that energy

01:45:11Watch my free course tutorials in the description on my free school

01:45:14And then after you've completed all of those, go on to build your own projects and then ones for friends and family

01:45:18Try solving your own problem or the people around you, solving their problems with AI workflow automation

01:45:21And within two to three months of doing that, you'll be ready to start trying to sell implementation to the people around you properly

01:45:27However, if by now you haven't fallen in love with the building process, then it's probably best that you just finish off your foundation by doing the builds in my free course and then get started on monetizing

01:45:34Like, you don't need to keep forcing yourself to learn more and more and more and more

01:45:40You already know enough because you have a knowledge gap between yourself and your clients, and you can start to help them by monetizing that knowledge gap

01:45:45So, once you're clear on what type of AI automation business owner you are going to be, getting your first few clients is actually pretty straightforward

01:45:51And there are two main ways of doing this

01:45:56The first is through what are called warm connections, and this is by far the easiest way to start

01:46:00Instead of expecting strangers to trust you with your automation expertise, you can start with people who already know you and already trust you

01:46:04What you're going to be doing is basically making a big list of all the people you know, all of the connections and friends that you have, and acquaintances even, and reaching out to them systematically to say, Hey, I'm doing this AI automation thing

01:46:16Would you be interested in having a chat to see how we could help you or your business? And it's just consistently starting those conversations with these people in your network

01:46:22And then eventually, one of those doors is going to open and become your first client

01:46:26I've covered this exact process many times here on the channel

01:46:30So on the Skool post for this video, I'm going to add all of my complete guides for warm outreach, including resources directly from my AAA accelerator program that will help you to fast-track your first few clients

01:46:34The second way is what I call the community content flywheel

01:46:38So this is how you build long-term momentum with getting clients for your business

01:46:42Firstly, you need to get inside my free community on Skool and then immediately start creating content about what you're learning

01:46:46So this could be, uh, making YouTube tutorials about building automations, it can be LinkedIn posts about workflow automation tips and tricks, or whatever platform you prefer

01:46:52But here's the key, is that you need to share this content back into the community

01:46:57And we have over 160,000 members in my free Skool with the biggest AI business community in the world

01:47:03And that gives you an instant audience of people who are interested in the same things to help you get traction with your content as fast as possible

01:47:09So let me give you a perfect example of this working in action

01:47:15We Have a guy called Rory Ridges, a young guy from the UK, and he joined my free community and followed this exact process

01:47:21He took the free course in the community, he learned the basics, and started posting simple tutorials on make.com and relevance AI, and literally just started sharing the automation workflows that he had learned from my videos

01:47:28Like, he wasn't trying to reinvent the wheel

01:47:34He was just saying, "Oh, I learned this cool thing, I'm going to make a video on it." But every time that he made a tutorial or a video, he would share it back into the community

01:47:38The community would watch it, give him feedback, and many of them would go and subscribe to his channel and become regular viewers

01:47:43So, this not only helped him To grow his channel faster, but it started to position him as an automation expert to his potential clients

01:47:47So, now his YouTube channel brings him in enough leads to support his growing AI automation agency

01:47:53He's basically started the same flywheel that took me from zero subscribers and zero with AI to on track to making $10 million this year and over 500,000 subscribers in just two years

01:48:04So, essentially, the community gives you an audience, the content gives you credibility, and together they bring you clients consistently

01:48:09So, on my free Skool, there's going to be a post for this video, and I'm going to leave all of the links to my complete guide for creating content and generating leads, just like Rory and I have done

01:48:14I've done a video on it, a ton of resources

01:48:20You can find that all on the free school

01:48:26What's really important to notice with both of these methods is that they start with giving value first

01:48:31Whether it's helping your warm connections to understand and implement AI automation for free, or sharing your workflow automation knowledge for free through content, you have to start giving before you get

01:48:37Now, I know all this businessy stuff may feel a little bit overwhelming or out of reach for some of you, but you will seriously be amazed at what baby steps add up to in this AI automation space

01:48:42You've already taken the first step by watching and following through on this video

01:48:46So, congratulations

01:48:50All you need to do now is keep This momentum going

01:48:54And the next step for all of you is pretty clear now

01:48:57You need to jump in my free community

01:49:00Go in there and drop an introduction post

01:49:03Let everyone know who you are, what you'd like to do with your AI automation career, and then start working through my free course material

01:49:06It's there for a reason

01:49:09And I've poured everything that I've learned about AI automations and building AI automation businesses into videos like these, and they're all in a nice sequence for you to work through on Skool

01:49:13Each time you complete a video, you can click the little checkbox and keep stacking those small wins and keep that momentum going until you get to where you want to go

01:49:19And all of the resources I've mentioned in This last chapter, the selling part of this video, will be on a Skool post for this video

01:49:25Within Skool, if you go to the YouTube resources tab, then it should be right there

01:49:31And don't forget to check all of those resources out there

01:49:37And of course, if you've made it this far, could you please do me a big favor and just leave a like on this video? You can drop a comment below, tell me what you liked the most or what you'd like to see next

01:49:43And click the share button and send it to any loved ones, family, or friends, or anyone so that they can start learning these valuable automation skills for the future as well

01:49:49So, all of these actions just help my videos like these reach more people in the YouTube algorithm, and I'd really appreciate it, 'cause I put a lot of work into these for you

01:49:54And of course, subscribe to the channel for more content like this, helping you understand AI automations, how to build them, and more importantly, how to build businesses and make money around this incredible opportunity that is AI

01:50:07If you want to check out my 4-hour guide on how to build AI agents, I've got that up here

01:50:09It's just like this one, but on AI agents

01:50:11Got a ton of great feedback from it

01:50:13So, if you want to keep learning, that's a great place to go

01:50:16But aside from that, guys, thank you so much for watching

01:50:18That's all for the video, and I'll see you in the next.