# How to Build & Sell AI Agent Workforces as a Beginner | FULL COURSE

## Метаданные

- **Канал:** Liam Ottley
- **YouTube:** https://www.youtube.com/watch?v=pTTvyQDK_tk
- **Дата:** 28.10.2025
- **Длительность:** 1:09:37
- **Просмотры:** 59,599

## Описание

📚 Get all the resources and prompts for this course in my Skool Classroom: https://bit.ly/48GLQOk
Build your own AI Workforces with Relevance: https://bit.ly/liamottley-relevance
Turn your ideas into presentations with Gamma: https://bit.ly/liamottley-gamma

📈 Become a Wildly Profitable AI Entrepreneur: https://bit.ly/47m5GMl
🤝 Ready to transform your business with AI? Let's talk: https://bit.ly/4qypPYD
📋 Get our FREE 14-day playbook for finding high-impact AI opportunities in any business: https://bit.ly/14-day-playbook-

AI isn’t just replacing jobs — it’s creating AI workforces that replace entire departments with digital teams that run 24/7 without salaries, burnout, or hiring bottlenecks. In this video, you’ll learn how to build AI agents and multi-agent workforces that automate real business processes like booking meetings, preparing presentations, transcribing calls, and assigning tasks, using the Relevance AI platform and powered by integrations with Gamma.app, HubSpot, Google Meet, Trello, and more. I’ll show you an end-to-end build of a personal AI assistant workforce that researches participants, designs presentation decks, manages scheduling, and sends follow-up summaries — all while you sleep. If you want to stay ahead in the $1 trillion AI automation market, monetize automation skills, and become the person companies trust to guide their AI transformation, this is your roadmap to surviving and thriving in the new era of autonomous digital employees.

⏱️ Timestamps:
00:00 - What We’re Covering
01:58 - Chapter 1: Foundations
05:28 - What Is an AI Workforce? 
07:00 - How AI Workforces Actually Work
10:53 - Foundations Recap
11:47 - Chapter 2: Building
11:55 - Relevance AI Orientation 
14:55 - What We’re Building
18:08 - Meeting Booker Agent
27:48 - Participant Finder Agent
31:07 - Orchestrator Agent 
39:39 - Gamma Agent 
47:39 - Lead Locator Agent 
52:42 - Note Taker Agent 
56:54 - Full AI Workforce Demo
59:14 - Publishing to Relevance Marketplace
1:01:12 - Chapter 3: Monetization (Selling workforces)

Proud partners with Relevance.ai and Gamma.app

## Содержание

### [0:00](https://www.youtube.com/watch?v=pTTvyQDK_tk) What We’re Covering

AI isn't just coming for jobs. It's coming for entire departments. Teams that once required dozens of people can now be replaced by something entirely new. An AI workforce. These are digital teams that run all day and all night that never get tired. They never quit. And they never ask for a paycheck. And they're showing up in every department these days from marketing to sales to operations and creative. And at my agency, Morningside AI, we implement AI within some of the world's biggest sports teams and even publicly traded companies. And I've been seeing these kinds of AI workforces just starting to take off now. So, I wanted to make a video like this just to open the door to others to not only survive, but thrive in this new era of work by being able to build AI workforces and not be replaced by them. Because while this shift may sound scary, and most people are naturally worried about what's going to disappear, the real opportunity lies in what's going to be created. Because for the first time in history, you don't need millions and millions of dollars in funding or a giant company to build a workforce. You can create one yourself without writing a single line of code. You can build entire digital teams made up of AI agents that keep working while you sleep. This isn't even far off science fiction. Gartner predicts that 15% of all work decisions will be made by AI agents by 2028. That's up from almost zero today. So, in the next few years, every industry will start to feel this shift. That's why businesses will be seeking people who can guide them through this transformation. People like you if you stay to the end of this video. So, we've got a lot to cover in this video. As you can probably tell, we're going to be starting off with foundations, which is breaking down what an AI workforce actually is, how they work, and the core concepts that you need to understand to be able to build them. And then we'll walk through an entire end-to-end AI workforce build of a personal AI assistant that can book meetings for you, prepare presentations, take notes, and even assign tasks for you as well. And in the third and final chapter, I'll reveal exactly how you can monetize this new skill by selling to businesses who are starving for their own teams of AI employees. If you want to learn more about me and my story, you can see the behind the scenes of building Morningside on my second channel, which is in the description below. But without further ado, let's get into it.

### [1:58](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=118s) Chapter 1: Foundations

So, we're witnessing the birth of a trillion dollar market here. And the good news is that anyone can get a slice of it with a little bit of hard work. Of course, there's a reason OpenAI's founder, Sam Alman, and his friends are betting on this. There's actually a video of him talking about it. I in my little like group chat with my like tech CEO friends, there's this betting pool for the first year that there's a uh a oneperson billion dollar company, which would have been like unimaginable without AI and now will happen. The reason this is even possible now is because of these AI workforces. They're not just a shiny new tool. They'll soon be as essential to a business as having a website. And companies that don't start to adopt them will fall behind fast. And companies who can adopt them quick, they're going to gain an immediate competitive advantage. So over the next 12 to 24 months, as we see demand for these kinds of workforces increase, businesses will be seeking the people like you and I to help build them and manage these workforces. Why are these AI workforcees so lucrative? And why will every business need one, too? Well, an AI workforce doesn't just save money, it changes the way work gets done in a company. Instead of salaries and benefits and vacation time, these digital workers just keep going for a fraction of the cost. So instead of the ups and downs that come when people having good days and bad days or sick days, every task gets delivered at the exact same standard that you built the workforce to do every time. And when things start scaling up in a business, you don't have to go through a long hiring and training process to bring new people on. You can scale the business almost instantly. AI workforces are also really fast. So what might take a human team hours or days to coordinate can be finished in minutes by AI agents working together. And the more they work, the better they get. And so each interaction can become fuel for improvement without the need for expensive training costs like you have with staff. And I get it. All of this probably sounds quite intimidating. Like the idea that whole parts of a business can run themselves might feel unsettling or even impossible to achieve. But the truth is that this shift is already underway and it's happening whether we feel ready for it or not. That's why it's so important to lean into this now to understand what AI agents and work forces are and learn how to use them for your own advantage. Because the people who figure out how to harness it are the ones who will shape the future and not be pushed aside by it. Just think about the kinds of tasks that businesses already pour enormous amounts of time and money into. answering customer questions, keeping records organized, updating schedules, researching information, writing reports, producing content for websites and social media. These are the kind of repetitive and draining tasks that every business wrestles with. And they're the exact kind of work the AI workforces are designed to take care of. Businesses that act first will gain an enormous advantage, and the people who learn to assemble these now will become the trusted experts in this industry that is just beginning. So, it's the perfect time to get into it. And the good news is you don't need to be super technical to build them either. There are now platforms like the one we're going to go through in the build section of this video that allow you to create agents and tools and workforces and give instructions like you would a person. You just describe what you want them to do in plain language and the system will literally build it for you and you can tweak from there for your needs. So your real job is simply learning how to connect these pieces together so that they function like a team. It's kind of like building with Lego where each block is simple on its own, but when you connect them together in the right way, you can create something much more complex. And AI workforces work the same way where you're assembling these digital workers who have access to tools and even other apps to operate together efficiently. By becoming a workforce builder, the opportunities are wide open. You can help companies to spot where these systems fit and build custom solutions for them or even package and sell readymade agents and full workforces direct to companies or in marketplaces. And later in this video, I'll show you exactly how and where to start selling them, even if you're completely brand new to the space. But first, we need a clear grasp on what we're dealing with and why it matters. So, let's understand how AI work forces work.

### [5:28](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=328s) What Is an AI Workforce?

So if a workforce is composed of AI agents, what exactly is an AI agent? So you can think of them as like a digital employee. You can give them a task like look this up or write this message or organize this list and then they take action for you and they do it quickly. They don't get tired and they're always ready. It's one worker with one job and a few tools that allow it to do that job properly. So it's kind of like a specialized digital employee. But no business runs on just one employee. A shop doesn't just survive with one cashier. It needs someone to do the inventory, someone to restock the shelves, someone to handle the finances. Each person in the company has their role and together they keep the place running. And that's exactly what an AI workforce is. It's a team of AI agents, each with its own specialty working together like a department inside a company. Workforce that we're going to be building in this video looks a bit like this. It all kicks off over Slack, which is a business messaging platform where you can send a Slack message, schedule a meeting with anyone in your company, or even external contacts. The workforce then books the event and it can even prepare a presentation for the meeting based on company docs and external research. And then finally, it can take notes during the call and assign tasks when the meeting ends. So together, this workforce acts like a personal assistant ready to help out with the literal click of a button. So this is the shift that's happening right now. We're moving from these single AI assistants or agents that only handle one-off tasks to these collaborative AI workforces that can take care of entire business processes. That's not just helpful, that's ultimately going to be world changing. And if you can learn how to build and sell them, then that's going to be life-changing for you over the next few years. So, now that you know what a workforce is, how are they actually structured?

### [7:00](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=420s) How AI Workforces Actually Work

So, you can visualize an AI workforce like an org chart from a typical company with human employees where there are specific roles, clear reporting structures, and defined workflows between the different positions. And the core principles of human and AI workforces are the same. A workforce runs on three pillars. You have specialization, collaboration, and coordination. So specialization means that each agent has one clear job and gets great at it. For example, you have a researcher that pulls information, a writer that turns that into a useful plan, a designer then prepares a presentation for it, and so on. But we don't want our agents to be working in silos. So you need collaboration where agents can work together by passing tasks and information between each other. Just like a designer might create a logo and then pass it to an animator to animate it. And of course, these work forces need coordination. So, it's our job as the workforce builders to create a clear and predictable system structured to keep everything organized without error. We can even have agents in the workforce that function like a project manager who orchestrates everything, deciding what runs and when, making sure everyone is communicating well and everything is operating smoothly and of course addressing issues when they do happen. Just like a real org chart, AI workforces usually take a few different shapes with agents who are working sequentially and completing tasks in a straightforward line where each agent depends on the last, like an assembly line. You can also have agents that run in parallel, completing the task at the same time, which can cut down on the overall time it takes for work to complete. Like in human organizations, AI workforces can have a hierarchy as well, where assignments flow from the top to the bottom. And there can be an orchestrator agent who functions like the team leader who understands the goals and then breaks a big job into smaller parts, assigning it to these different specialist agents and then pulling the results back into a final result like a project manager would. But what enables these agents to actually work? What gives them the ability to understand, remember, and take action? Well, each agent is powered by a few core components that mirror how real employees work. First off, they have a clear understanding of how to do their job. For a human employee, that would be your job description, but for an agent, it's their prompt. These are the instructions that you give to an agent to define its role and its responsibility. It's the blueprint for how the work needs to be done. But if you just handed a sculptor a sketch of what you needed it to sculpt, but you didn't actually give the actual stone, they wouldn't be able to do anything. So, we often need to give our agents access to resources or materials like a transcript of a call or a customer's order or campaign performance data in order for it to do its job. But of course, if we only gave the sculptor a block of marble but nothing to carve it with, then it would be powerless. Similarly, we can empower agents by giving them access to tools that they can use to execute their duties like a web scraper to perform research on a company or a document converter that turns text into PDFs. These tools can include integrations with external apps like CRM like HubSpot or project management platforms like Notion. This way, your agents can interface with the external world and sync up with other systems in the company. You can also give agents access to a knowledge base, which is essentially a database full of useful knowledge that agents can reference as needed. This could be anything from internal company reports to a list of frequently asked questions that a customer support agent could reference in order to come up with standardized responses to customer questions. In addition to your agent being able to know things, they can also have the ability to remember things, too. So, by giving an agent the power of memory, they can recall what's happened in previous steps or even across time. And this not only helps an agent to do its job better now, but allows them to improve over time if you set it up correctly. So, circling back to collaboration and coordination. When it's time to pass work along from one agent to the other, there are different patterns that keep things smooth. Often, the handoff is clean, like a baton pass, where one agent finishes the task and hands the next agent what it needs, and that next agent takes off running. Other times, an agent might have to clear a couple hurdles first, like making sure the right file is ready before it can hand things over to the next agent who would not be able to do the task if they didn't have that file. And other times, this coordination can go both ways where an orchestrator agent might request work from an agent it oversees. And then that subordinate agent performs a task and hands the results back up to its manager. Then that manager might process things and hand it off to another agent who finishes things off. So with all that out of the way, we are about to build. So let's quickly recap to make sure everything is clear.

### [10:53](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=653s) Foundations Recap

So, while these work forces can get complex, ultimately building them is really about starting with the simplest piece that works. You break down work by specialization, creating unique agents that have a prompt that specifies its role and responsibilities. Then, by providing it with all of the necessary resources, knowledge, and tools, it has what it needs to perform the tasks you've told it to do. Then by connecting these specialized agents into a virtual org chart and making handoffs between teammates clear and predictable, you've built the foundation for collaboration and coordination that can start small and continue to scale. With this essential understanding in place, let's see this in action and build our first AI workforce, starting with our first agent. So to make building your first AI workforce as smooth as possible for you, I have organized all of the prompts and instructions for this workforce over in my free school community. So if you haven't yet, feel free to pause this video now. You can head down to the first link in the description, join my school. It'll take a minute or two for you to get accepted. Then you can go to the classroom section where you'll be able to access everything. All the prompts, tools, links, everything you need to follow along with this build.

### [11:55](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=715s) Relevance AI Orientation

To build our workforce, we'll be using Relevance, who we're happy to be partnering with on this video. Like it says, we can build teams of agents that deliver human quality work. We can even invent our agent with a simple prompt. For example, we could tell relevance that we want an agent to research a person on LinkedIn and Google, then click invent, and it will spin one up for us. We'll take a look at that feature later when we're inside the platform and use it along with other tools to build out our full AI workforce. If you don't already have a relevance account, you can sign up to create one, but I'm going to log into my existing one through Google. Here we're looking at the relevance marketplace. This is an ecosystem of agents, tools, and entire workforces that the builder community can use. Like this image generator agent, for example, which generates images using GPT models. We could clone this into our project and use it for our needs. There are also agents that can be purchased like this Gmail task creation agent. As you can see, we could buy this for 99 and use it straight away inside of our projects. So, how do we actually start to create our own agents? Well, over here on the left, you can see several tabs. There's a tab for agents where we can build or find agents we already built or ones that we've cloned or purchased. We can give our agents access to tools that empower them to perform their responsibilities and give them access to knowledge that provides the context for how to do their job well, such as information about your company, your clients, your industry, and more. Putting that all together, we can form our workforces. And these workforces and the agents within them are empowered by integrations through different APIs. That's just a fancy way of saying that we can sync up with other apps out on the internet and use their functionality. This includes integrations with apps such as Gmail or Google Drive, Google Meet, HubSpot, Slack, or Trello. When we're giving our agents functionality, often we're giving them the ability to use external integrations with other apps. Here you can see all of the agents that I've either built, cloned, or purchased. We can store them in folders to categorize them. And they are also grouped by the workforce they belong to. So, we're about to create our first agent. But before we do that, I want to show you this chat feature, which opens up this new window. What you're looking at here is essentially like a regular LLM chat window, like chat GPT. But the cool thing is you can prompt within here and add your agents or even entire workforces and ask them to run tasks for you. So if I select this gamma presentation designer agent, I can tell it to build me a presentation on selling AI services to small to mediumsiz businesses. And it's able to do that straight from this chat window. Then on the left, we have the chat history that we can revisit. Later in the video, I'll show you exactly how to set up this Gamma Graphic presentation designer, which is super powerful. Before we start building our workforce, I want to orient you to what we're actually building.

### [14:55](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=895s) What We’re Building

So, now let's head into the workforce tab and open up this meeting workforce cuz this is what we're going to be building. At the top here, we have our two triggers. This is how we tell the workforce to start. It'll start based on a message it receives. We can send our workforce messages from within relevance, like through that chat window I just showed you. But we can also trigger it from apps that we use every day for work, like Slack. So, we'll set up a way to interact with this workforce directly through Slack. And what are we telling it to do? Well, we're requesting this workforce to book meetings for us. It all starts off with this orchestrator agent that understands what we're wanting it to do, whom invite, and what's required for that meeting. This orchestrator agent has a few agents that report to it called sub agents. There is one that finds internal participants. These are members of your own team or company. We'll give the agent a knowledge base to find the correct participant. We have another agent that can find external participants. This one will be looking within our integrated HubSpot to find leads uh potential clients of ours and then perform research with LinkedIn and Google on that lead and the company they work for. This ensures we have enough information about who we're meeting with to feel prepared going in. And we also have this gamma graphic presentation designer which will run anytime we request a presentation to be made. Maybe we want to do a pitch to a lead or discuss internal metrics during a company call. This agent can build those presentations for us automatically. If you're not familiar with Gamma, it's an AI powered tool that turns your ideas or documents into beautifully designed presentation ready slides and web pages in seconds. And they now have an API which means we can ask Gamma to create these kinds of assets for us from agents within programs like relevance and from other workflow platforms like make or N8N. Once the presentation is ready, it will let the meeting orchestrator know. Ultimately, the orchestrator's job is to book the meeting. So, it calls this meeting booker agent, which uses Google Meet to schedule a meeting with all of the required participants. And then it sends that meeting link to our notetaker agent who is going to attend the meeting, take notes, transcribe the call, identify any next steps or action items, and then create tasks within a to-do list app. Finally, it will even send an email summary to all of the participants with a link to those tasks. So, as you can see, this is a nice well-rounded workforce that functions almost like a personal assistant, booking meetings with internal or external participants, preparing presentations, and documenting calls with action items for follow-up. So, if you're excited to start building it, let's head over to the agents interface and build our first agent by clicking on the new agent button. Like I mentioned before, we could invent this and describe exactly what we want built. And relevance is going to do its best job at building that for us. Or we could use a guided setup. We could even import an existing agent from a file that someone shared with you. Or we can build it from scratch. Since this is our first agent that we're building, I want to make sure you understand exactly how it's built. So we're going to build this agent from scratch.

### [18:08](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=1088s) Meeting Booker Agent

Now we're inside the agent builder and on the left we can see the prompt. This is where we create the guidelines for how the agent should function. We can give it tools, knowledge, set up how it's triggered, build in some escalations, memory, and variables. We'll touch on some of this in a moment. And when we add any of this, it'll show up on the right hand panel over here. So let's start and give our agent a name. We'll call it Borealis the meeting booker. And below here, we're going to write some instructions. But first, I want to bring your attention to the model section here. So, here is where we select which AI LLM model we're using. As you can see here, we're using a performance optimized model where it just picks the best one for us. We could optimize by cost or select a specific one with chat, GPT, Claude, Gemini, or whatever best suits our needs. Now that we're clear on which model we're using, we can start to write our prompt. Now, there's not necessarily a standard way of structuring these prompts, but the way that I like to do it is I'd like to start out by defining the agents role. So, in this case, I'm telling it you are Borealis and specifying that it is a meeting booker agent. Then, I'll just bold its name so it's more easily scannable for the user. And I also want to get clear on what inputs this agent should be receiving. So in this case, it's going to be receiving information for the participant or participants to invite to a meeting. And it's also going to be receiving the time zone of the participant and I'll tell it that it may also receive an exact date and time to book the meeting. So now we told our agent who it is, what information is going to receive. Now we need to define its responsibility, instructing it on what it's supposed to do and how to do that. So, we're going to tell it your purpose is to schedule meetings and invite each participant. If a specific meeting time is provided, book the meeting at that time. Otherwise, identify a meeting time that logically is most convenient considering the time zones of all participants. Now, I'm going to tell it that when it's communicating with the user who is actually triggering it, refer to times within their time zone. And this word here, time zone, we're actually going to convert into something called a variable. You can think of a variable as a placeholder that fills in with whatever value is present at that time. So, we're going to go to the right hand panel and set up a new variable. It's going to be a text variable. And we'll name the variable time zone. This is for the agent to be able to reference what this is called. And we'll describe it as the time zone of the user who is requesting the meeting. And below here and the input is where we actually put the value that we want the placeholder to be replaced by. So the actual time zone such as EDT or Pacific Standard Time. And here in the green, we set the actual name that the agent is going to be using inside of the prompt to refer to this variable. Now over in the prompt, if we add these double curly braces around that variable name, then that activates the variable. So it's going to be filled in with the value of it, which in this case is EDT. Now, once you are clear on the meeting time, schedule the meeting using a tool in order to add a tool into this prompt. We're going to go into this right-hand panel and open up this tools modal and we'll see we have a bunch of tools to choose from. They have them organized by use case and you can also search for a specific tool. So in this case I'm searching for a scheduling tool and I see that there's this Google Meet scheduling tool that we can add to our prompt here is asking me to fill in the missing tool inputs. In this case it needs me to select which Google Meet account I want to connect to. Now, I've already connected my account, but if you haven't yet, you can click add account and go through this process where relevance AI uses pipedream to connect your Google account. I'll select the account I already have connected and hit continue. And now here on the right tab under tools, you can see I have that Google Meet tool. That means it's ready to use within the prompt. So, I can access that by using forward slash. Then I'll click tools, select Google Meet, and here is added right into the prompt for the agent to use. Finally, I'm going to add some important considerations for my agent. Going to tell it to only invite the participants who are explicitly mentioned and tell it that we do not want to invite anyone else. And just like our agent had an input, I'm also going to give it an output so we can clarify what it should actually return when it's complete. So, we'll say once you've booked the meeting, notify the user and provide the meeting link. And if any errors or issues occur, notify the user. And with that, we basically set up our agent. I'm just going to clean things up and add some dividers here. If I hit hyphen three times, then it'll create these lines so I can create some visual separation between the structure of my prompt. And at the very top here, we can give the agent a description. So, of course, Borealis schedules meetings and invites participants. We'll make sure to save the agent. And this whole time, we've been on the build tab where we've been building the agent. But now we want to go into the run tab where we can run the agent to see how it's actually working. If we wanted to, we could add a little guide to provide instructions for how to use or set up this agent, but this one is super simple. So, we will keep that empty. And to run this, we're going to tell Borealis to book a meeting with someone. And we'll give it an email for whatever time. Let's say Friday at 100 p. m. Then we'll clarify the participant's time zone is PDT. Now when we run this agent, we'll see the agent working in real time. We can see it booking the meeting and it was a success. It's provided us with the details and the link to the meeting which we can click and join the meeting when we're ready. Within the timeline, we can see the steps that were performed in the background such as using the Google Meet tool. And just to prove this worked, I can go to the calendar that it added to. And here is that event created for us with our new Borealis agent. So, now that we know that it's working like it should, we could go ahead and share this. We can make it publicly available, so anyone could run this agent. They could embed it somewhere, or we could just share a link to it. We could also turn this agent into a chat widget, which we could add to a website somewhere. We could change its styling to fit the branding of the site, add a starting prompt, such as, "Book me a meeting. Add a message placeholder so people know what to actually type into here and how to use it. And set up other configurations like allowing file uploads and toggling off the relevance branding. Another option would be to make this agent into a clonable template so we can share it with other users and they can clone it and adapt it to their needs. But of course, we're building out an entire team of agents. So you'll see later in the video how to publish an entire workforce out into the world. But before we build out our next agent, let's get a better sense for how tools work within relevance. Back around the build tab underneath the tool section, we can see the tools that our agent has access to. In this case, our agent only has access to the Google Meet tool. And what we're looking at here is all of the tool inputs, such as the connected Google account and the calendar ID. Here, we're letting the agent decide which ID to use, but we can set this manually as well. This tool is currently set to run automatically. We could require approval for it to run or have the agent decide. And conveniently, we can edit the tool whether we created it ourself or we cloned it from the tool marketplace. Inside here, we can set up all of the inputs for the tool. We can set them as required or optional. Here, this looks pretty familiar. It has all of the variables that this tool is making use of. And if we wanted to, we could even add additional steps into this tool. Maybe we want to connect it to a CRM like HubSpot. So once it schedules a meeting, it creates a note within HubSpot relating to the person that it scheduled the meeting with. We could go ahead and save the tool or save it as a draft, but because we don't want to change it at all, I'm just going to close out of this. So that's the process of looking under the hood of an existing tool. But of course, we can create our own tools either by default, which means we're creating it from scratch, or we could vibe create it, which is a way for us to invent our own tool with a prompt. So, let's say we want to build a tool that takes in a transcript of a video or a meeting and then produces an engaging post for LinkedIn. Now, once I hit go, it's going to build this tool for me. I'm speeding this up for your convenience, but as you can see, it walks through all of the steps to invent this tool for me in the background. And I configure these inputs such as the transcript, style, audience, and focus. So, if I hit run, it's going to generate that LinkedIn post for me. And if I pop open the output, I see the actual post and just scanning through it is looking pretty good. I could either use this tool as is or continue to use the invent feature to refine this. So let's say I don't need this post style input. I could go into this prompt and tell it I don't need an input for this and just to remove it and it'll go through that process and remove it for me. I could continue to make changes in this way, or I could even switch to the default builder, which brings me to that view that we were looking at before, which is the traditional tool editor, giving me hands-on control over how this tool functions. And if I expand this Python code, you can see that it did all of this for us in the background. We did not have to write a line of Python code. It invented this all for us. Of course, we could continue to add on to here. Maybe once the LinkedIn post is generated, then we actually post it out onto LinkedIn via API. Now, just like an agent has its run tab, the tool has a use tab. So, here we can actually use the tool and we can see a log of all the times that we ran that tool to debug or just to get a better sense for what

### [27:48](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=1668s) Participant Finder Agent

happened. With all that understanding in place, now let's move on to creating our next agent. We're also going to build this one from scratch and we're going to name it Polaris, the participant finder. And it's going to find participants from within a knowledge base, which we will set up in a second. First, we're going to define its role and tell it that you are Polaris, the participant finder agent. Then we'll set up its input and tell it that it's going to receive the name or title of an employee from a company whose directory you have access to as a knowledge base. And we'll give it a responsibility. For each participant, locate their info within the company directory. And this is going to be that knowledge base. In order to add a knowledge base, we'll go over to the right hand panel and click into knowledge. And we can add a knowledge base in a number of ways. So we could either sync up our agent to Google Drive or Notion, add an existing knowledge base that was already added into our relevance account here, or we can simply upload a file. So here I'm adding a CSV file that lives locally on my computer and we can choose how to use that knowledge base. We can either add it all to the prompt which is good for smaller data sets because when you do this it's going to add the entire file and all of its contents directly into the prompt or we can allow the agent to search and this is good for larger data sets. Since the agent will be able to do a ragbased search on the entire knowledge base, but since our company directory is quite small, we're going to add it all directly into the prompt. Once it's uploaded, we'll see over in the prompt that our knowledge base is added into the prompt here in the brackets. And although it doesn't look complete, our agent actually sees it as if it's the entire CSV file. Finally, for the output, we'll specify that it must return the participants full info and to report any errors or issues that it encounters while running. We'll go ahead and save it. Then head to the run tab and test it out. So, we'll say find me my head of content. Again, it can take in a title or a name and search the knowledge base for that participant. And fortunately, we can see that it worked. It found the correct participant, Adam Jar, my head of content. Clicking on this task icon over here, we can see all of the tasks that our agent has run. We can see a detailed view. We can see if there's anything to review, anything that's been escalated or any errors from our tasks. We can see the queue if anything is in process, and then the list of tasks that have run here. To run a new task, we could either schedule a bunch of tasks in bulk, or we could just hit new task. And this allows us to run new tasks in this agent. I could even tell it to find me all members of the content department because again it has access to that company directory which specifies the department that all of these employees work within. So it's able to process really dynamic requests and find participants to match those requests. Finally, if you wanted to search within the tasks that you ran, you could even go and filter for tasks maybe where it's of a certain status. Or you could even filter by a search term and pull up only the tasks that match that term. Great. So now with all of that context in place and with two agents that we've built, we can now head into the workforce tab and start to build out our workforce with these new agents.

### [31:07](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=1867s) Orchestrator Agent

So, we'll go ahead and create a new workforce. We'll give it a name. We'll call it meeting setter. And you can think of this interface much like a canvas that you can drag different elements onto in order to build out your workforce. If I drag on this agent card on the right, I have all the agents that I can choose from. So, I'll select the meeting booking agent. And as you can see, its prompt is available right here in the panel for me to edit as needed. Next, I'll drag on another agent card. And for this one, I'm going to be selecting the participant finder. And if you remember from earlier, we need a way for these agents to collaborate together through a manager or orchestrator agent who can receive meeting requests and then delegate the tasks across this workforce. So, let's save our progress so far and head out of the workforce so that we can go back to the agents tab and create that orchestrator agent, which will build with the invent feature. We could give it a very simple prompt here, but I'm actually going to be pretty thorough because I want to get this right. So, I'm going to tell it to invent an agent called Orion, the orchestrator. And this agent is going to receive inbound messages requesting meetings and sometimes with presentations. This orchestrator needs to interpret the intent of the message, which means the meeting's purpose to require participants and whether a presentation is needed. It then will delegate work to sub agents. Polaris to find the internal team members, Lania to locate and research external leads. We'll build that agent and a couple others soon like Gamma to create the presentations. Borealis to schedule the meetings and Nate to attend, transcribe and assign follow-ups after those meetings conclude. We need the orchestrator to wait for all of the participant data from Polaris and Lania before calling Borealis to book the meeting. And then once the meeting is booked, we want the orchestrator to notify the user in Slack with a meeting link to then continue checking on the gamma agents progress to make sure the presentation is ready. And then when the presentation link is ready, send that to the user and then of course report any errors or issues clearly back to the user. So once we hit start, just like when we invented the tool, it's going to go through this process and build out that entire agent for us. Of course, I've sped this up for your convenience. We'll just hit accept on the suggestions for its name and description. And it's produced this comprehensive prompt for us. And just scanning through it, it's looking pretty good, but we're going to walk through this step by step soon. So, let's just accept it for now. It's asking for a Slack connection because that prompt mentioned it. We'll set that up in a moment. So, now we just need to save the agent and we can use it over in our workforce. So, let's head back to the workforce tab, open up the meeting setter. We'll make some space and then drag an agent card onto the canvas and select the orchestrator. Now, if we zoom into the prompt here, we can start perfecting it for our needs. I see that its role is a meeting coordination AI. I'm going to add the word agent just to be super clear. And it correctly says that it receives inbound meeting requests and orchestrates a team of specialized sub aents. And the instructions here are that it analyzes those meeting requests, coordinates with the sub agents, waits for all the participants, and keeps the user informed and handles any errors. So, it looks like it got everything that we had requested. It also added in this expected input format, but we don't need that. So, I'm going to actually delete that out and exchange it for an example input message specifying that these are messages from someone within a company wanting to meet with a teammate. the full team or people from outside of their company. And then in here, I'll just give a few examples of potential messages like scheduling meetings with a person with an entire department or someone external from the company to pitch them. And I'll add an important note here that for any mentions of pitches, proposals, etc. Gamma should prepare a presentation. Now, as we scroll down here, we see this sub aent coordination workflow. All these steps are good, just like we wanted them to look. I'm just cleaning up the formatting here. The only change I would make here is that we want to clarify that it is Borealis, the meeting booker, that tells the note taker to attend the meeting. It's not the orchestrator himself who does that. And that's because Nate, the notetaker agent we will build later, is actually a next step after Borealis, the meeting booker, meaning Nate is not a sub agent of the orchestrator. We will also remove the Slack tool and just say to use Slack because, as you'll see, since we'll be triggering this from Slack, Orion will already have access to Slack through that trigger. Now, we'll just clean up this formatting so it's easier to read. And because this orchestrator won't have access to our notetaker agent, I'll just delete this step number eight, which talks about the orchestrator being able to control it, which is not true. And here's talking about how it has access to the knowledge bases, but actually its sub agents do. So, we'll fix that. And with that, the prompt is ready. But you'll notice that there's this warning on this tool. That's because we removed the Slack tool from the prompt. So, it's essentially warning us that we have a tool that we're not using. So, we'll just delete that out from the tools tab and go ahead and save the changes to this agent. Now, we can wire this orchestrator up to its sub agent. Starting with Polaris, we'll make sure that the connection type is AI connection, which means it's a sub agent, and give instructions for how it should be used to find internal meeting participants. And then we can set a label here. We'll make sure that it auto runs. We could have the approval required or let the agent decide, but we'll keep it on automatic. Then we'll wire Orion to Borealis, giving instructions for how to use it when the meeting is ready to be booked and set the edge label to book meeting. In order to trigger Orion, we need to wire him up with this message trigger. And we can test this out from the run tab. We'll make sure to save and publish the workforce and then give it a message to book a meeting with my head of content for Friday. And in the timeline here, Orion is working. It's using Polaris to find the participant. is using Borealis to book the meeting with a Google Meet scheduling tool. And voila, it's successfully worked and booked that meeting with the right person. So, our workforce is in a really good spot so far. If we head back to the build section, we can add another way to trigger our workforce from outside of the relevance platform. Specifically, we want to be triggering it from Slack. We already have our Slack connected here. If you did not already, you could just connect it through here. just put in your Slack organization here and go through the connection process. And if you're not familiar with Slack, it's really a collaborative communication environment for teams to use. So, I'll hit continue and then I'll add a keyword here. I'll call it booker. The keyword is really just a word that we use whenever we trigger this. So, that relevance knows which workforce we want to run. Now, I'm just telling it where it can be triggered from my direct messages and all of these channels. and I'll confirm that I understand that I always need to tag at relevance AI within Slack to use this trigger. If I wanted to, I could enable specific working hours for this Slack trigger and therefore for this workforce, but I don't want to limit it to specific hours. Now, I'll just connect up this trigger to Orion, but now be able to save the workforce, then head over into my Slack organization and make sure that I have the relevance tool installed. So, I'll click on apps and make sure I have it installed. If you don't yet have it installed, you'll want to open the marketplace. Search for the relevance tool and then install it from here. But since it's already available within my Slack, I should be able to go into my DM and then say at relevance AI and then book it. That's that keyword that we set up and say book me a meeting with my head of content for let's say Monday morning and now over in relevance. That should be working. It's going to be taking a while, so I'll speed this up for you, but eventually it's going to give you a reply back. If you pop that open, it should say something like the meeting was successfully scheduled and here is the meeting link. Now, if we head back over into relevance and click on the run tab, we can see here is that task which we can tell was triggered by myself from Slack. Now, as I've been alluding to, sometimes our meetings are going to require us to prepare presentations, pitches, proposals, and for that we're going to

### [39:39](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=2379s) Gamma Agent

use Gamma. So, let's head over to the relevance marketplace to get started with that. As you'll see here, if we search for gamma, there are a couple agents that have already been built that we can make use of. We're going to uh select the gamma assistant here and go ahead and clone it. and we'll give it a more specific name for our usage and call it gamma the presentation preparer. Now, when we save it, we'll see that it's asking us to fill in this variable for the gamma API key. I've already done that and I'll show you how to do it in a moment. So, I can hit continue, then head back into the workforce and put it to work within here. So I will drag on a new agent card and select the gamma agent and wire it up as a sub agent to the orchestrator and give it instructions for how to use it where we'll call gamma whenever a presentation is requested. Now we'll change this label to something more informative such as prepare presentation. And now we're set up to request presentations to be made directly from within this workforce. But before we actually do that, I want to orient you to the Gamma platform. We're happy to be a partner of theirs because they provide a powerful way to bring your ideas to life where you can use prompts to create presentations, branded documents, social media content, and even websites. And now with their new API feature, we can automate the creation of this content from places like relevance n make or even your own custom web apps. For example, you could have a system where whenever a blog post is approved for publication, Gamma runs automatically, creating a graphic that is perfectly suited for that post. So, the possibilities are really endless here, and it can save you and your team a bunch of time. Of course, in our workforce, we're specifically interested in creating presentations, and Gamma is capable of creating really any kind of presentation from a pitch deck to something more personal to an internal team update to a keynote speech or whatever kind of slide deck you need created. It's going to do it very fast with little or no effort from you. And you can use AI to refine and polish the presentation until it's ready to present. As you can see in their video here, it all starts with a prompt which you can feed in from the actual Gamma interface or programmatically from whatever workflow or app you're using. Then Gamma is going to generate the entire presentation for you styled in a theme of your choosing or you can create your own theme based on your branding. Once it's ready, you can edit the presentation with AI, changing up the verbiage or the layout itself. And you can drag and drop different elements onto the slides until you're ready to share it publicly and present it out into the world. If you don't yet have an account, you'll want to create one now. But I'm going to log into my existing one cuz I want to show you some presentations I've already generated from the API. Let's open one of these up. And you'll see I have all of these slides. The text is based on internal documents that I gave it access to. And it generated all of the images and design itself based on the prompt. And if I wanted to change things like this image here, I could regenerate some new AI images and change what I'm using within the presentation. So, not only is it quick to generate, but it's quick to iterate as well. And all of my slides here are using the theme Oasis. So, I'm excited to show you how to create these from within the relevance platform. Now, it's important to note that in order to use the API, you do have to have a pro plan within Gamma. But when you consider all the time and energy you'll be saving with a tool like this, it provides a lot of value. So, with that pro plan, you'll be able to go into the settings here and generate an API key to use within the relevance platform or wherever else you might want to make use of Gamma. You'll just make sure that the gamma API tool in the agent has access to that API key which you can set up within the integrations tab of relevance and add that API key inside of here. So now that we're oriented to the power of gamma and have it integrated into our agent, let's get clear on how this agent is functioning. So under the core instructions, you can see this documentation variable. So if I go to the variables tab, we'll see that we're feeding our agent. uh all of this uh documentation that explains how to use the gamma API and it even includes all of the code for an example request. Note here that the theme name is Oasis like I showed you in the gamma platform and the number of cards in the presentation is 10. These are all things that we have control over from the prompt itself. The only thing I'm changing here is I'm going to increase the duration of the delay and the amount of times we're going to pull for the presentation to make sure that our workforce can gain access to it and it doesn't time out too early before the presentation is ready. And since we want to give Gamma access to some internal documents to build presentations from, we're going to add a knowledge base and sync up to Google Drive. We'll just select our connected Google account, specify the drive itself, and whatever document we want to give access to. In this case, it's information about how my agency provides AI transformation partnership to clients. Since that's not a huge file, we will just add it all into the prompt itself. In order for the agent to make proper use of this, we just need to let it know that when it's researching and preparing for the presentation, it should ask itself, does it need access to the AI transformation partnership information? If so, it should reference that knowledge base which is attached to the bottom of this prompt. So, if I scroll down here, there it is. In order to empower even more, we're going to let the agent know that as needed, it can perform Google research to search the meeting attendees, the company topics, etc. and it can use a tool to scrape the content from a website to discover helpful information about the website of the person or company that is building a presentation for it. And with all of that set up, our agent is empowered to prepare a presentation on a bunch of different topics. If anything went wrong, let's say an AWS outage causes gamma to not be functioning temporarily, we can set up what is called an escalation, which means the agent will notify us via a method of our choosing that there are issues that need addressing. So, we can set up our agent to notify us via Slack whenever a task has timed out, for example, or there's an unreoverable error or it's exhausted, it's retries. In any of these scenarios, we can make sure to be notified within our connected Slack account at the destination of our choosing. For example, through a direct message to myself. We could also choose to be notified via email as well. So, we'll go ahead and save this agent and make sure that it's working by heading over to the run tab, saving our changes to the workforce, and asking our Gamma agent to build a presentation on how Morningside AI can be an AI transformation partner to this example company. I'll give it a URL. Now, as soon as I hit go, we can see Orion has called the gamma agent. It's doing its research and planning, which looks pretty thorough. It's thinking through how to structure the presentation and planning how it's going to make use of the gamma API itself. As it's calling that API, it looks like it ran into an error first, but it keeps trying using delays during those attempts. And of course, I'm speeding this up for you. and it eventually found success and it returned this message that the presentation is ready including a summary of what it covers and a link to the presentation itself. So if we click that open we can view what it built for us which is already looking great. If we wanted to we could tweak this and then on the day of open the presentation link and present it live. So, this is a super quick and efficient way to get custom pictures, presentations, and even proposals generated for anyone that you're meeting with. Speaking of which, let's head back into relevance and create our next agent, which is going to be responsible for locating our leads within a connected customer relationship management tool called HubSpot.

### [47:39](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=2859s) Lead Locator Agent

So, let's start building the next agent, the lead locator. This agent is going to help us locate external participants so that we can book meetings with people from outside of our company. These could be people we want to pitch our business to and turn into clients. Our leads are going to live in a tool called HubSpot. So, we'll switch over to that. Now, if you haven't heard of it yet, HubSpot is a customer relationship management platform or a CRM where businesses store all their customer lead information. You can think of it as a central database for everyone that you're doing business with or people that you want to do business with. You'll see leads organized under contacts, companies, deals, tickets, and orders. But we're mostly concerned about our contacts here. This is where the lead's information will be stored, including their name, email, phone, and their company. These fields are actually linked to their full company data, which we can view as a list over in this company's tab. I'm walking you through this because our lead locator agent will search through HubSpot and retrieve the contact information for the leads we want to book meetings with. Now that you understand what exactly we're asking for, let's go back to relevance and start building out that agent who will be asking for these leads. We'll build the agent from scratch. I'm choosing to name this one Lania the lead locator. And we're going to give it a short description to locate external participants from outside of our company. Okay. and we'll come down here to the prompt and define its role, telling it who it is and specifying that it's a sub agent of Orion, our orchestrator agent. Now, we'll tell it what to expect as an input, which will be information about the lead, like their email and the company they work for. And for added context, we'll tell it that this is a participant of a future meeting. As for its responsibility, we'll instruct it to locate the info with HubSpot. We can access tools by typing a forward slash then the kind of tool we're looking for. In this case, HubSpot. We have a few options to choose from. So, we'll select the tool to retrieve contact details from HubSpot. Since this is an external integration, we need to connect to our account so that we can have access to it from within this agent. Now, let's move down a little bit here and continue its instructions, letting our agent know that we want it to perform research on this lead and their company. And then we're going to the next tool. We're going to use LinkedIn. will use this LinkedIn tool to search for info from their personal and company profiles. For more thorough research, we're also going to use Google search. So, we'll add in a Google search tool here as well. This research will be used for things like creating personalized pictures and eventually proposals. Finally, we'll define the agents output and tell it that it must return the lead's complete information and a research summary to its boss, agent, Orion. And of course, it should let us know if there are any errors or issues with locating the lead. Okay. And that's our prompt. By giving it these tools, we've connected it to HubSpot and enabled it to search through both LinkedIn and Google. So, it's pretty powerful with only a few lines of prompt. I'll make sure to save this agent, then go into the run tab to test it out to ensure everything is working. From this run tab, I'll pass in the contact info for a potential lead. In this case, someone in my network that I added into my HubSpot contacts. This way I can make sure this agent is not only finding the correct contact but doing accurate research on them. Once I enter the email you can see it started running. If you're ever wondering if the agent is actually working on the right hand side here you can see the status will update to running and it also shows the tools that it's going to use. So we can see it is definitely working. It's looking into HubSpot. Then it's grabbing info from LinkedIn profile. Now we can see it's searching Google. Looks like the first one failed, but that's okay because it ran multiple searches, which is great to see because that means this agent, like all agents you build in relevance, is able to adapt on the fly. And once it completes, we can scroll up here and see we have the correct contact details from HubSpot. It's grabbed a bunch of details from LinkedIn about this uh lead and his company and structured it out quite well, too. This is cool because our other agents like Gamma will now have access to all of this context as it builds out super custom presentations. For good measure, I'll mark this as complete. Now that it's built and we've confirmed it works, we're ready to add this agent into our workforce. So, we'll head out of the agent and head back to the workforces tab and go into our meeting setter and drag another agent block onto the canvas and choose Lania. We'll connect Orion down to Lania and make sure it's set as an AI connection since this is another sub agent of Orion who will of course call her to locate external participants. Now, I'll just spread them out a little bit here to clean up the canvas. And as a final step, I'll update the label here to find external participants. I'll make sure to save the workspace because we're going to head out of here and go find our next and final agent, the notetaker agent, who

### [52:42](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=3162s) Note Taker Agent

will attend our meetings. As we've seen, the marketplace conveniently has a bunch of existing agents we can repurpose for our needs. So, if we search for a notetaker, we'll see a few options. Nate fits our needs quite well, so we'll select him and go ahead and clone it. Its current prompt is pretty useful, so we don't need to start this one from scratch, and we can reuse some of what is already here. But, we do need to change a few things. And we'll start by clarifying its role is a notetaker agent who attends meetings, transcribes what happens during that meeting and afterwards assigns tasks and sends a meeting summary. As for its input, that will be information about the meeting the agent must attend received from Borealis. The meeting booker agent will tell it that it's responsible for generating summaries of all types of meetings from internal team syncs to client calls and project updates or strategy sessions. Inside of its instructions, the agent is being told to use this send meeting bot tool to record and transcribe the call. And then when the agent receives that transcript, it reads it carefully and writes a summary of that meeting, including things like key discussion points, decisions made, and action items. Then it's able to use this turn transcript into text tool to generate a file of the transcript. And we're telling the agent to refer to the transcript whenever a user asks questions about that meeting. I'll add a bit more to the prompt here so the agent knows to determine the action items from that meeting and then create tasks based on those actions items and create tasks for them over in our to-do list in Trello. If you're not familiar with it, Trello is a visual task management tool. Uh, and it's used to organize personal and professional projects. It's kind of like a digital bulletin board with sticky notes. We find those boards in this tab where we've got out to-do list board here. Opening up that board, you can see that it has lists arranged in columns, and these lists get tasks or cards added into them. You can name the lists whatever you want or add new ones and then drag cards across them as your tasks move through different statuses. Each card can be opened up and contains a bunch of properties you can set up. Each one of our tasks that the notetaker agent creates for us will be a new card, which is added to this to-do list board. So, back in our agents prompt, we're telling it we want to use the Trello tool to create a card on a Trello board. Here, we need to create a Trello connection, and we're just going to link it through to our Trello account. We need to authenticate with Trello. Just scroll down here, and we'll just allow that connection, and then click continue and continue again. We scroll back down and now we can see that's enabled. continue. When it creates the card, it should fill in the following: the card name, its description, and its due date. That's it. Finally, for the output, we're going to tell it to email a summary to all participants using their emails they attended the meeting with and include a link to the Trello board that we just added tasks to. And it will do this using the send Gmail tool from our connected account so it knows how to structure the email. We'll give it a format to follow, which I'll just paste in here. and we'll include a sample email as well. Great. So, we'll save that agent. Lastly, we need to add a trigger. So, we're going to add relevance meeting bot and click setup trigger. And that's been added in. Noteaker agents are a little different and need to be triggered twice. Once to join the meeting, which in this case, the Borealis agent will do, and once when the meeting is finished. In order to trigger it for the second time, you need to add this meeting bot trigger to the agent. Now we can add it to our workforce. So let's head back over there. Inside our workforce, I'll drag on a new agent. Tell it to use Nate the note taker. And for the handoff type, this one should be next step. This means that instead of the orchestrator agent managing this agent, Nate runs automatically once Borealis books the meeting and hands him the meeting link. For good measure, we'll edit the label here and specify that we're sending a meeting link on this handoff. Now, we're good to go. So, we'll save these updates.

### [56:54](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=3414s) Full AI Workforce Demo

Okay, we've built all of the agents and now we can see them working together as a workforce. So, let's jump over to Slack. This is where we're going to trigger the workforce. Call the relevant AI bot. And then our particular trigger also needs this trigger here. So, we're going to say booker. I'm going to say book me a meeting with Adam. And we'll put Adam's email in here. next Tuesday at 10:00 a. m. Eastern Standard Time and create a presentation about how we can be their AI transformation partner and share it as a link in the meeting. Okay. So, we're going to click to send that and straight away it responds. So, we can look at that and view thread. So, we've got that confirmation here that the agent is cooking up a reply. So, let's jump over to relevance AI. We will have a look at the run tab and we can see that has already started here and it's already running. Lania the lead locator is working and then we are getting the LinkedIn details and we're doing the Google search and then book the meeting. Okay, now moving on to creating the presentation. Now that's completed. So let's jump over to Slack again and we'll just look at the reply. So it's created how Morningside AI can be this company's AI transformation partner exactly as we asked it to do. So, it's gone through and created this detailed presentation. Might need a little bit of a review and then edit, but that's certainly a good starting point. Okay. So, let's close that. Now, let's jump over to Google Calendar. And we can see that the appointment here we need to say yes, we are going to attend. So, let's join with Google Meet. Inside Google Meet here, we can see Nate wanting to join. So, I'll admit him. And there he is taking all of the notes that I need. He will write it all down, email it to us, and assign tasks as we will see later. After the meeting, let's head back to relevance. We've seen that complete. We can jump over to Trello, and we can see we've got a couple of tasks here that have been created, and we can jump up to our email. There's a summary with the key points, the decisions made, and then action items and next steps. This was sent to all participants automatically after the meeting ended. So, there you have it. The workforce works flawlessly.

### [59:14](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=3554s) Publishing to Relevance Marketplace

Great. Now that our workforce is complete, we can submit it to the relevance marketplace and look at how we can start to monetize this. So under more actions, we'll click submit to marketplace and select some categories that our workforce relates to, such as sales, research, and operations. Then we'll add a description for the workforce, telling the public that this workforce helps you book meetings with your teammates and contacts and generates custom crafted presentations to use during those calls. Then we'll decide if we want to submit this as a free or paid workforce. I'm going to submit mine as free, but of course you can set yours as paid and start to earn some money. You could allow sharing it as a clonable template or allow republishing, but I'll leave those off for now. Then on the next step, we just select one of our past tasks to be the preview that shows up when this is published. Then once we submit for review, it's going to run through some automated checks that I'm speeding up for you. And once those checks have passed, you can click finish and you should see your builder dashboard where the approval status is hopefully pending. If it was autorejected, you might have to resubmit it with some changes. Clicking this dropown, you'll see all of the agents and tools that this workforce was submitted with. And if we click on the submission itself, we'll get a preview of how this would show up within the relevance marketplace. As a builder, you have your own profile. You can set up a cover photo and add an image of yourself. And in order to receive payments on the platform, you'll just link a Stripe account. You'll click generate Stripe link. If you don't have a Stripe account, you'll want to create one first and then just enter your Stripe email address and continue the process from here. And with that, you've taken the first step of monetizing your new skills as an AI agent workforce builder. There are so many opportunities for making money with these new skills. So, join me in the next and final chapter where we talk about the blueprint for monetization.

### [1:01:12](https://www.youtube.com/watch?v=pTTvyQDK_tk&t=3672s) Chapter 3: Monetization (Selling workforces)

So, we covered a lot of ground on this course. You now understand the massive AI workforce opportunity, a market that's predicted to reach 52. 6 billion in 2030, and my businesses are desperate for these kinds of solutions. More importantly, you've learned how to design and deploy complete AI workforces that operate around the clock, automating, delegating, and executing work that once would require entire teams. But here's the truth. Knowledge without action is worthless. The knowledge gap that you've built through this course is your new competitive edge. It's your path to financial freedom and building the life of your dreams. Because what you now possess isn't just a technical skill. It's a business superpower. And the ability to spot inefficiencies and design intelligent systems that replace manual processes with scalable AI workforces is exactly what businesses these days are dying to pay for. In this monetization section, we'll turn that skill set into income by building a scalable monetization engine around your expertise. So whether you start as a solo freelancer or launch your own AI agency, this is the path forward. The AI workforce monetization model. Your journey to monetization follows a simple progression. Diagnose, design, deliver, and scale. Step one is diagnosing the opportunity. So, every engagement with a business begins with what I call an AI workforce audit. This is a strategic diagnostic where you step into a business and uncover where complete AI workforces can replace their manual workflows. You'll map out how they operate, expose inefficiencies, and show what's possible with a coordinated set of agents. The result is a road map that highlights exactly where automation can deliver a measurable ROI. This instantly positions you as a trusted adviser to the business, and they will pay you thousands of dollars for this clarity and this audit before you even begin implementation and building their workforce. So, I've documented the whole process of how me and my team at Morningside AI do these kinds of AI audits. And I've boiled that down to a free resource that you'll be able to get on my free school community. That's called how to perform your first $10,000 AI audit, which is going to be available for free with the other resources that you found already, which goes step by step through how to perform your first AI audit. And that's available with the other resources in the classroom on school. Step two is design and implement. So, once you've done the audit and the opportunity is mapped, it's time to start building. And this is where your technical and creative skills have to kind of merge to turn that insight into impact for the business. Here you're not just selling features, you are delivering a transformation for them in their specific workflows. So a single chatbot might be worth a few thousand, but a full AI workforce that replaces an entire role or even an entire department justifies much higher value projects and ongoing retainers for you as well. Step three is manage and scale. So deploying the AI workforce is really just the beginning and the real opportunity lies in the management and optimization. the maintaining, improving, and expanding of these systems over time. And this is where the recurring revenue or monthly revenue can begin for you and your business. So you can oversee multiple client workforces, offer ongoing analytics, and evolve their systems as needs change. So as your demand grows, you can scale by hiring other builders underneath you, extending your capacity to deliver while multiplying your impact and income as the founder. This is typically known as an AI automation agency where you have yourself running the business, but other developers and automation experts underneath you and actually doing the work for you. So, that's the model, but how do you put this stuff into motion? It of course starts with landing your first clients. And even if that means doing your first few projects for free in order to build proof, experience, and confidence. So, who are you actually selling to? Well, the businesses that need the AI workforces the most are typically service companies or small businesses drowning in manual processes. You've got contractors buried in coordination, agencies juggling client workflows, consultants overwhelmed by admin. They need 24/7 operations, but can't afford full teams. More often than not, they rely on repeatable multi-step workflows, which are the exact kind of things that AI workforces are designed to automate. So, your ideal clients are businesses with clear and repeatable processes that currently require multiple people to execute. Step one in getting your first clients is warm outreach. So, you of course want to start with people who already know and trust you, and those are found in your existing network. So, go through your contacts, your emails, your LinkedIn, your social connections. And the key here is that you're not selling to them directly. You're asking them for referrals, which essentially lowers the pressure and expands your reach. A simple message could be, "Hey name, I'm building AI workforce systems that automate operations like customer support, scheduling, and project management, and I'm offering a few complimentary workforce assessments in order to build a few case studies. Do you know anyone who might find this valuable right now? " So, this approach works great because it's personal, it's low risk, and it opens doors naturally. It helps you to refine your pitch and build your first stories that prove your expertise. Inside my free school community, you'll find the full landing your first client in 30 days guide, which is complete with the exact tracking template that's used in my AAA accelerator program. And this exact template and system has helped thousands and thousands of people to book their first AI clients. And I mean, my free community itself is a gold mine for getting clients. With over 250,000 members, many of them being business owners and decision makers by engaging authentically and sharing insights and just offering value. It can lead directly to client opportunities within the community. Step two is cold outreach. So once you've landed your first few clients, it's time to expand systematically with my cold email testing framework, which is a process that basically replaces the guesswork with data. My full guide on how to do this is also available for free in the school community in the monetization section of this course. But the strategy roughly goes like this. So you're going to choose four service niches. For example, you've got HVAC, you've got law firms, you've got real estate agencies or consultants. Then you're going to write one clear results driven email per niche. For example, I help HVAC businesses replace their entire scheduling and dispatch process with an AI workforce that runs 24/7 for less than the cost of one employee. Then you send 500 emails per niche and track the open rates, replies, and calls booked. And then after 30 days, you identify which niche and message has performed the best and then you double down on that. And yes, you can even build your own AI workforce to automate this entire process. Within weeks, this framework turns client acquisition into a predictable and measurable system that you can scale. The authority flywheel. So once you're landing clients and getting results, your next step is to turn that execution and results into exposure for yourself. So every build and every win and every insight is a story worth sharing. So documenting your journey on LinkedIn, YouTube or Instagram and mirror those same kinds of posts that you put there inside my school community by posting these updates and sharing lessons and showing your results in motion. It creates a self-reinforcing loop because you're letting all of these people see you and building credibility. You're showing proof, not just promises. It creates feedback loops which help you to refine your message. It opens doors and others start referring clients your way because you're making noise and letting people know you exist. Community engagement and content creation are two sides of the same coin. When it comes to creating content, you don't need perfection. You just need consistent authenticity. So, document what's real. The builds that you're doing, your before and after results. Your growth is an agency. In my opinion, if you're trying to get businesses, the best platforms to go onto are LinkedIn and YouTube. So, over time, the cycle starts to compound where the results you get with your business, they start creating stories that are worth sharing. Those stories that you share attract new clients and then new clients create more results which fuel your reputation and you get better and better. And that's essentially the authority flywheel. It's a system where your work markets itself and your presence compounds into authority. So now your acquisition engine runs on three cylinders. You have warm outreach initially to build that early proof. Your cold outreach which allows you to scale more predictably. Then community and content to establish a lasting authority. So as mentioned the step-by-step guides on putting these exact strategies into action, the warm outreach and cold email are included with the other resources in the monetization section on my school community. So getting the support you need. If you're feeling intimidated or overwhelmed about this new party going down, it's natural to feel that way, of course, because you're building something entirely new. And that's why I created my free school community. It's at this point the largest AI business community in the world with over a quarter million members who are walking the same path with you. So, inside you'll find all of my best resources, plus weekly live Q& A with me where you can ask me questions directly about pricing and implementation, client acquisition, or anything else that you're working through. You'll also be able to connect with thousands of other builders and business owners who are sharing their wins and solving challenges and just generally growing together as a community. Just recently, we had an in-person event in the Sydney Harour, which was incredible. So, there's also options to come out in person to hang out with me and the team. But, if you're ready to dive into this and get results as fast as possible, my AAA accelerator program is there for those who are serious about building an AI business, and they want one-on-one support every step of the way. That's really what the program is made for. So, me and my team will work with you directly to implement these systems and get you up and running as fast as possible. So, we've covered a lot in this video. You now understand how to design and build multi- aent workflows that can replace entire departments for businesses, not just their tasks. The knowledge gap you need to make money is now there. The market demand is proven for these kinds of systems, and the tools are ready. Plus, you've got all the resources you need to take action inside the free school community. So, so the point of this video is that the AI workforce revolution is here. The question isn't whether it's happening, it's whether you'll be the one to lead it. So, your next move determines everything. You can either be replaced by this stuff or be the one out there helping businesses to adopt it. Join the community, get the support you need, and start writing your AI success story.

---
*Источник: https://ekstraktznaniy.ru/video/11753*