Hi everyone, so in this video I'll show you how to build a 20 AI agent team that can manage and automate literally almost any task or workflow across your entire tech stack. This is one of the craziest agent systems I've built up until today and I think these kinds of setups will be the future of AI agents and automations. This agent team has access to all my softwares including all my communication channels, WhatsApp, LinkedIn, email, calendar, Slack and even voice calling. It has access to my project management tools like my CRM, Notion, Google Docs, Google Drive.
It has three research agents to research any lead or topic and it has specialized content agents that can write and publish across my social medias and blog. I can interact with my agent through voice messages on WhatsApp and the real strength of this system is that it can automate complex workflows across multiple softwares with a simple English sentence. It can for example find flight options, add them to Google Docs and send it to someone on WhatsApp. It can call a friend to reschedule lunch and update my calendar with the outcome. It can research new leads that contacted me, add them to my CRM and notify my team on Slack if they are qualified.
It can write and publish blog and LinkedIn posts on the latest AI news and all from just a single request on WhatsApp. And these are just a few examples. The possibilities with this setup are really endless.
And in this video, I'll give you a demo and a full step-by-step breakdown of the setup and the templates will be available in my community. So stick with me because I think it will blow your mind. Now, if you don't know me yet, I'm Ben.
I've been building AI agents for businesses for over a year now. I also run a community where I teach others how to build and sell AI agents. And if you're a business looking to adopt AI into your business, you can also book us in for a free call in the description below.
So I'll first show you a demo. Then I'll give you an overview of the setup for this system. And then I'll give you a detailed step-by-step breakdown so you can learn how to build something like this yourself.
Remember, the template will be available in my community. And... I'm just going to give you a few examples.
Remember, these are just a few examples. The system is capable of a lot more, but I think it will give you a good idea. And another cool thing about this system is we can actually schedule messages of things we want our agent to do every day.
For example, I instruct my agent normally to every morning create me a Google Docs with all messages that came in across all my communication channels. And with that document, then I can start taking action with my agent. But for example purposes, I'll just instruct my agent manually now so you can see how it works.
So I can leave a voice message if I want. So I can say something like, hey, please retrieve all unread messages from all my communication channels. Also, check all my meetings scheduled for this week and put them in a Google Docs and send them back to me. Now, in the background, my...
director agent who I call, which is the one I'm in contact with, is going to delegate these tasks to his sub-agents. So to retrieve these sort of unread messages from communication channels, he has a communication manager who on itself has another six sub-agents. So the communication manager has a sub-agent for WhatsApp, LinkedIn, Slack, all my communication channels. And so basically my director agent will delegate this to the communication manager, will then instruct.
all the other agents to retrieve the unread messages. And then that will be sent to my project manager who has access to Google Docs. We'll then put it in a Google Docs, send that back to the director agent.
We'll then send it back through WhatsApp to me. So we got it back, as you can see. So we get a little bit of a summary here on WhatsApp too.
And at the end, we get the Google Docs. So let me open it up quickly. So you can see we get sort of an overview of all the unread messages from all my channels.
So we have WhatsApp, LinkedIn, Slack, unread emails with a summary and my calendar events for this week. Now, based on this document, I can start taking actions on these things. And my agent, of course, can start taking actions.
So, for example, my mom here asks, when are you coming to Holland? Right. Did you already book?
Right. So you can see actually here is my mom's message. Right. So we can.
tell actually our agent something like this. Hi, please check flights from Sao Paulo to Amsterdam for the 19th of December. Check for the three cheapest options, put them in a Google Docs and send them to my mom on WhatsApp and ask her if these arrival times are good for her.
And then also send the Google Docs back to me. Now, in this case, it's actually using the Google SERP API. to check for Google Flights. And basically, we'll then try and find the three cheapest options.
Again, put it in Google Docs. And then I'll use the WhatsApp agent to actually send it to my mom. And we'll see it actually appear here.
that it will send it to my mom from my WhatsApp. You can see it sent it to my mom now here. Hi, mom. I found three flight options from Sao Paulo to Amsterdam, right?
Arrival at 11, right? And you can see in the Google Docs, we get the flight options too with the prices. So of course, maybe not the best example, right? As I'm already in WhatsApp. but I just, and you can see it, send it back to me.
I think it's a good example to show what the system is capable of. Then we can also take actions on things unrelated to people, of course. I've also connected it with my social media and my website, for example. So we can also say something like, hey, please research the latest trends on AI coding agents, write a blog post and a LinkedIn post. about the latest news on AI coding agents, post the blog post to my website and add the LinkedIn post to my content calendar on Notion, please.
So in this case, it's going to delegate it to the content manager who has specialized agents for writing blog posts and LinkedIn posts. If you've seen my other video, it basically has these fine-tuned post writers that are They can write optimized posts for different social medias. I'll actually show you that it will add a new article. So these are my latest articles. So you'll see that it will add one.
All right, we got it back. The blog post on AI coding agents has been successfully written. Additionally, LinkedIn post draft has been crafted and added to your content calendar.
You can see it posted it. I think it made up the URL because it didn't get it back. Yeah, but here you go. AI coding agents revolutionizing software development with landing capabilities.
AI coding agents enhance software development with seamless integration. Right, and it even added in images, as you can see. So let me check my Notion LinkedIn content calendar. Let me check. coding here ai coding agent revolution ai coding agents are about to change everything here are some of the latest developments lang lang chain's new ai agent can write code to solve tasks and improve itself over time super agi is launching an ai agent and can code entire this is really good actually auto gpt so it gives a list the coding process will be automated and you can see it adds in my my name and my ctas of course we can also take actions on leads which i Normally do, for example, if you have to unread LinkedIn messages, wants to discuss creating agents for SageMatic.
So I can go something like this. Please research and scrape the LinkedIn of Christian Alpo from SageMatic. Add the enriched data and lead to my CRM and send Oscar a Slack message. with info on the lead and the contact email. Just an example, right?
But yeah, you can see it's like you can basically just combine because you have an agent system that has all of these different softwares working together, we can sort of automate these workflows that require multiple steps. And that I think is really the powerful sort of setup for this system. And I really think it's the future because we can basically start automating.
workflows with simple human language all right i've successfully added chris christian to your crm with all enriched details a slack message has been sent to oscar uh you can view the contact details in the google docs it even puts it put it in a google doc with all the the info so let me check slack right this is oscar you can see it comes from relevancy i haskell we have a new lead right with all the information right now let's check contacts um what's his name chris was it up for yeah here we go christian up for right we actually have the lead summary as you can see here company summary company size email etc but you get the idea right Lots more possible. I actually wanted to show you another one because this agent can actually call for me too. So I can tell. my agent call this person. I can literally let my agent call anyone, for example, to reschedule a meeting or an appointment.
And it can then even update my calendar with the outcome of the call, for example. But I think you got a good idea of it. Let me go over the system right now, where I think you get an even better idea of all the possibilities for this system. So as you can see, it's quite a big setup, but it looks more complicated than it is. And I'll break it down step by step.
So you get a very good idea of how this is set up. Now, first of all, I've set up almost the entire system in Relevance AI, and I use Make.com to make some of the integrations we don't have inside of Relevance AI a little bit easier through Make.com. If you're completely new to these platforms, Relevance AI is an AI agent and AI tool builder. And you can also build these really powerful multi-agent systems to really automate quite complex workflows through these agent teams.
And Make.com is a more traditional workflow automation tool with the big advantage of having lots of native integrations. with third-party softwares. Now, if you're completely new to this, this is a little bit more of a complex setup.
I have many other tutorials on my YouTube channel too, on both of these platforms, but I'm going to break it down in a detailed way and step-by-step. So even if you're completely new to this, you'll probably be able to follow this. And I highly recommend to follow it if you're interested in building no-code AI agents and AI agent teams.
So let me get through the system. So first here on the top, we have the triggers. Here we have our director agent, how I call it, and the director agent is the one we are in contact with through WhatsApp.
Then we have our manager agents here. And here we have our sub-agents. And our sub-agents also have tools. And you can see here one manager agent also has three tools.
So in total, these are 20 AI agents and more than 50 tools. And you might be wondering why I use so many AI agents and so many different tools. Now, the main reason is because at the moment, unfortunately, LNMs and AI agents, they're not good yet at doing multiple tasks.
Right. So to get these systems where there are so many possibilities as reliable as possible. Right. We want to reduce down the responsibilities and the tasks for each of these different agents and each of these different AI steps as much as possible to get the system as reliable as possible. So instead of giving lots of responsibilities to one AI agent.
Right. We. want to reduce it down as much as possible so each of our agents has very specific tasks to get the reliability higher so how does this work in practice right so here we have our whatsapp trigger right and of course that whatsapp trigger in this case i send voice messages that goes voice the text and that will be sent to my director agent now i put these here too because that's the interesting thing with this system i think which is if we want to start automating things on a regular basis for example every morning retrieve all my unread messages, et cetera. We can just plan that in with human language, right?
And this is, I think, why I think it's the future is because we can start automating workflows without actually programming in a workflow automation, et cetera. We can literally, with human language, schedule an automation that runs every day, for example. So you could save something like this, right? The one I use, retrieve all unread messages from all my comms channels, and you can do that every morning at 7 a.m., right? That will be sent to my director agent, will then perform that and send it to my WhatsApp or wherever else I want, right?
But you can also do other things, right? Research all new leads that contacted me through LinkedIn, email, add them to my CRM. If they're qualified, send them a message back right away with calendar link, et cetera. So that's, I think, the amazing thing with this system is as soon as you see, you start interacting with this team and you see that you start doing things on a regular basis, then you could just build in a message to schedule every day.
to your agent and you don't even have to manually trigger that anymore right now from that of course it's being sent to our director agent i'm gonna go through this step later um so our director agent already has four main responsibilities which is the first one is breaking down our query then second according to the query he'll have to plan out what he has to do right to which sub agents or manager agents does he have to delegate these tasks then he has to evaluate if what the work that has been done by the manager agents and the sub agents has actually been done correctly and if not send it back right and lastly he has to communicate back with me that's why we gave our director agent access to two tools the first one is send a whatsapp message so he can contact me right and the second one is get the current date sometimes you will need to know what the current date is if i for example ask retrieve messages from the last week something like that right now You might be wondering, why didn't we just give this director agent access to all these 20 agents? Why did we put four manager agents who then control another layer of agents? Again, it's because if we... give our director agent access to 20 AI agents, it's overkill for one AI, for one AI agent, right? It's going to make mistakes.
There's too many responsibilities. You have to plan out and orchestrate a workflow automation across 20 AI agents. That's going to go wrong, right?
So again, we want to limit down the responsibilities as much as possible. And that's why we have these four manager agents, right? And these four manager agents, of course, we have the communication manager agent, right?
Who has all the agents. that control my communication channels, right? So we have the voice agent, the WhatsApp agent, the LinkedIn agent, the email agent, the calendar agent, and the Slack agent.
So what are the responsibilities of my communication manager agent? The first one, again, very similar, orchestration and delegation, right? So he will have to decide which of these sub-agents he has to use.
So in our example, right, retrieve all unread messages from all communication channels. Of course, he would have to use all of these sub-agents. But sometimes it might be only from one channel. Then second, again, he has to make sure that what these sub-agents have done is actually right.
And if not, he can send it back and make sure that they do the right thing. And this is the second advantage of having these multi-layered agent systems is we can have these sort of evaluation steps in there where agents can check what other agents have done and make sure that what they've done is right. And if not, they can actually send it back until the sub-agents actually do it right.
And then lastly, of course, you have to communicate back to the director, right? Now, if you're unsure about this, how does this actually work, the delegation, right? Basically, our director agent just prompts our manager agents on what to do. So for example, if I say, retrieve all my unread messages from all my channels, the executive director will prompt the communication manager to, with something like, hey, please retrieve all unread messages for all Ben's communication channels, right?
And then, for example, put it in a Google Docs. Once the communication manager has done that, right, the director agent will then send that to the project manager who says, please put this in a Google Docs, right? So that's sort of orchestration and delegation.
Then the second agent is the project manager agent, right? Same responsibilities again, which is orchestration and delegation. Again, evaluation, making sure that what these sub-agents have done is correct. And of course, communicate back with the director agent, right?
And here we have the CRM agent, the Google Docs agent, and the Notion agent, right? And. Then we have the research manager agent, right? Same responsibilities again, right? Orchestration and delegation, evaluation, which is especially important for the research manager agent, where sometimes you want to do in-depth research.
This research manager can really double down on these sub-agents to make sure that they do in-depth research. So if they haven't done proper research, he will send it back and make sure they do more, right? And again, communication with the director agent. And the last one is the content manager. And the content manager has one more responsibility.
which is also, he has three tools, which is post to Webflow, post to LinkedIn, and post to Axe. So he can actually post onto my social channels, right? Because why do we do that? Because for example, if our LinkedIn writer agent, right, writes a LinkedIn post, we have another sort of check in place by sending it back to the content manager agent who can check, okay, is everything good?
Does it make sense? Does it match the original query? And then post it to LinkedIn, right?
Now, as you can see, these sub-agents also have tools. And these tools basically allow our agents to interact with softwares or even do more like workflow automation. So in this case, you see our Slack agent has a tool where you can send Slack messages.
You can retrieve Slack messages. We have our calendar agent who can get calendar events, create calendar events, update calendar events and get calendar events. And I'm not going to go through all the tools, but you get the idea.
So each of these agents basically controls like a software inside of my tech stack and can perform actions inside of. inside of these softwares, right? And by having all of these agents with all of these actions in these different softwares, that's how basically we allow these agent systems to automate very complex workflows with human language.
And that's, I think, why this is the future of AI agents, because instead of mapping out a very rigid, logic-based workflow like we're used to in the automation world, right? And probably we'll rely on that for a while still, but once the LLMs get better and more reliable, you can see that AI agents will be able to basically automate a workflow or process without building in this entire sort of logic-based workflow now what i'm actually building in right now which will probably be available in the template too is another extra step because what i'm note what i notice is sometimes because this director agent already has quite a lot of responsibilities and some of these queries can be extremely complex actually right he has to delegate between four or five agents right Make sure that he prompts each agent with the right thing, right? Doesn't prompt an agent with something he can't do, for example.
So sort of that breaking down a query and planning out is actually the hardest part, I think, or the hardest responsibility for this director agent. That's why I tried to build in a GPT-01 model to actually do the planning for our director agent to take that responsibility out of his hand. Because the GPT-01 models are, of course, very good at sort of system two level thinking, right?
Breaking down and planning out, right? So basically I'm building a GPT-01 model because unfortunately we can't use them in AI agents yet. To first look at the query that I gave it, I gave it all the context on the whole system and the GPT-01 planner. basically makes a detailed SOP on exactly what to do with this query for the director agent.
And instead of the director agent then actually having to plan before executing, he can just execute on the SOP and therefore reduce his responsibilities and we can get this system more reliable. I'm building this in right now. So the system I showed you in the demo is without this step, but I think I will add that in the template.
Now, again, if you want to look at all the tools and all the agents in detail in your own time, The template will be available in my community. And I'll also make sure to put the link of this overview here in the description below here. Now, let me get you through Relevance AI, where I'll go through step-by-step inside of Relevance AI, how these agents are set up. And I'll get you through some of the tools.
And I'll also show you how to set up these triggers. So here we are on my Relevance AI dashboard. Here we have some of the agents of this agent team. Now, if you're going to clone this template, make sure to first make a Relevance AI account. I think sometimes it gives an error.
if you don't have an account yet. So first make an account. I'll make sure to put the link in the description below too.
And then if you're going to clone my template, you can basically click the link and clone it. And then you'll see these agents appear in your own dashboard. So I'll first break down how this actually looks in the background. So we can basically see what our director agent did with the queries I showed you in my demo. So you get a good idea of how this system actually works sort of in the background, right?
Then I'll show you the setup for the director agent and the four manager agents quickly, and maybe some sub-agents and their tools. And then lastly, I'll also show you how I trigger the system from WhatsApp. I'm going to show you that very quickly because I have a full WhatsApp agents video too. If you're interested in that, make sure to check that one out.
And then lastly, I'll also show you how you can schedule these repetitive messages on a daily basis, for example, to your director agent to automate your workflows. So... Let's go to the director agent. So here we can basically see what happened in the background.
So you can see here how I triggered it. For example, here, hey, please retrieve all unread messages from all my communication channels. Also check all my meetings scheduled for this week and put them in a Google Docs and send them back to me.
Right now, you can see this was done with voice to text, right? Because I sent a voice message, right? That was triggered through make.com, which I'm going to show you in a second. Then in make.com, we went voice to text. And then we send it here.
Now you can see the voice to text isn't perfect, right? Also check all my meetings for scheduled for this week, but it's good enough for our agent to understand, right? And here now we can see actually what our agent did in the background, right?
So you can see it performed four steps in the background. And the first thing it identified is that it has to use the communication manager, right? And here we can actually see what a director agent prompted to our communication manager on what to do, right? So you can see here, retrieve all unread messages from WhatsApp, LinkedIn, Slack, and email.
Also retrieve all scheduled meetings for this week from the calendar, right? Now, this information, it already filled out himself because he has this context on what this communication manager can do inside of the prompt of the director agent, which I'll show you in a second. And here we can see then what our communication manager did, right? Because he then delegated these tasks also to his sub-agents, right?
So you can see he delegated it first to the WhatsApp agent, where he basically instructed him, right, to retrieve the unread messages. um, from WhatsApp, right? The same for LinkedIn, the same for Slack, the same for email and also for the calendar agent, right?
So he gets all of that information back from all these, these sub agents. And then you can see, this is what he sends back to our director agent, right? Here, the retreats on red messages, uh, for this week, WhatsApp, LinkedIn, et cetera, right?
So the director agent receives that back. And of course the director agent then has to, uh, actually make the Google docs, right? So that's why he has to use the project manager, right?
Because the project manager, has a sub agent which is the google docs and google drive agent right who can actually make a google drive so you can see create a google doc with the following details right he sends over all the unread messages right now the project manager delegates that again to the google drives and google docs agent right who has a tool to make a google docs so you can see the google drives agent right got prompted with the same prompt basically right um to and you see he used one tool in the background which is create a google doc tool right and You can see he created the Google Doc and show you this quickly, right? You see all the text and in the response, we got the Google Doc, right? He sends that back to the project manager who then sends it back to our director agent who then of course sends us the WhatsApp with all the information.
So you can see he sent us a quick summary of all the unread messages and of course, the link to the Google Docs with all the messages. So that's sort of how it works in the background, right? So you can see, so the hardest thing for these agents is sort of breaking those queries down and sort of orchestrating which tools and which sub-agents it has to use to perform this task, right? But that's also the power of these agents, right?
We can come with these very dynamic queries and it can just know which sub-agents it has access to and which tools, and then can sort of think through, okay, I first have to use him, then him to actually perform this entire workflow, right? Now... You can see here for the second one, right?
Hi, please check flights from Sao Paulo to Amsterdam for the 19th of December. Check for the three cheapest options, put them in a Google Docs and then send them to my mom on WhatsApp and ask her if these arrival times are good for her. So in this case, it actually first has to do research, right? On the flights, right?
So in this case, you'll see he first uses the research manager agent who in his turn has access to two sub agents. You can see, find the three cheapest flight options from Sao Paulo to Amsterdam, right? include details such as airline departure, arrival times, and prices, right? So you can see what a research manager did.
He delegated it to one of his sub-agents, which is the travel agent. And the travel agent has access to tools to get flights, to get hotels, and things like that. So you can see the travel agent, what he did in the background, right? He used the get flight option, right?
Found the three cheapest options, sent that back to the research manager, who then again sends that back to the director agent. Then he delegated, of course, again, to the project manager agent to create a Google Docs out of it. All right. So you can see we got a document. He delegated, of course, to the Google Docs agent.
And lastly, of course, the WhatsApp has to be sent to my mom. Right. So it's delegated again to the communication manager agent who can send WhatsApps. Right.
So you can see, send the following message to mom on WhatsApp. Hi, mom. I found three flight options from Sao Paulo.
Now, how does he know what number my mom has? You can see here the WhatsApp agent actually has a tool to find the number from. from a name in this case i call my mom in the database mom right but he has a database with names and phone numbers so you can retrieve a phone number from a name right so you can see what he did here right he filled out the name and got back a phone number right so then he used the send whatsapp tool to actually send the whatsapp to my to my mom right again he sends that back to me what he has done i'm sorry to the director agent and he then sends all the information to me i found three flight options right and the document. Right. So that's sort of how it works in the background.
Now, let me show you quickly the setup for this director agent. So here above, we have our agent settings. Right. And here you can see first, we have our agent profile.
Now, the agent profile is not that important in this case. It's more important for if this is a sub agent. Right. So you have the agent name. Right.
And here we have the agent description. Now, why is this important for sub agents? Because basically the agent description will be read by the manager agent to know what this sub agent can do. Right.
So Whenever you have a sub-agent, it's important to fill out this agent description to basically let your manager agent know what this agent can do, right? And then we have another section here, which is the trigger section. We have lots of triggers we can use. You can see we actually have WhatsApp for business too here in Relevant CI.
Now, I didn't use it because with this one, we can't use voice interpretation, Google Docs interpretation, or image interpretation. That's why I set it up through make.com because then we can actually receive those types of messages too. I'm going to show you that later.
So... Here, then, we have the agent instructions, right? The core instructions, which is basically our agent prompt, right? Now, if you're new to this, right, agent prompting is a little bit different than normal prompting.
And I always use my agent prompting tool, which I created myself. It's a perfect know, but it will help you write them a little bit faster, I think, and sometimes a little bit better. And the agent prompting tool is also available in my community. So how's this agent prompt structured?
Basically, first, we have the role, always very important, right, in these agent prompts, right? You're Ben from Sprindle's executive director agent responsible for overseeing and orchestrating the workflow of four manager agents. I give it the names of the manager agents who in turn manage a total of 15 specialized sub-agents.
Then we have the objective, which is sort of the high level overview of what this agent has to do. And you can see his first one is delegation and orchestration. Break down tasks by Ben down into subtasks and assign each subtask to the appropriate manager agents. Make sure you provide clear instructions to your sub-agents, but ensure that the tasks you're assigning to each sub-agent are actually doable by them. Now, this part is actually very important.
The first time I created this system, that's actually where I went wrong a few times. Because if you don't clearly say this, what sometimes can happen is that your director agent is going to prompt a task to a sub-agent, which that sub-agent can actually not do. So for example...
In this example I gave, like if you say, retrieve all unread messages and add it to a Google Docs, it might say to the communication manager agent, retrieve all unread messages and put it in a Google Docs. But of course, the communication manager can't make a Google Docs, right? That's the project manager agent, right? that in that case something could happen where the the communication manager says i can't do that uh sorry and the system breaks right so it's very important that our director agent only prompts our his sub agents with tasks that they can actually perform right that's why i have this right and that's why it's also very important to give a lot of context to this director agent on what all of these sub agents can do right and what they cannot do now the second thing here you can see is quality assurance Verify that the manager agents have executed tasks accurately and delivered outputs that align with the original instructions. If not, provide detailed feedback and requests, revisions until the outcome is satisfactory.
And the third, of course, is reporting to Ben, compile and send all relevant details of completed tasks and outcomes back to Ben via the Send WhatsApp to Ben tool. That's his only tool, including entire messages, content, links and results. Now, here I have an SOP where I basically break down these three tasks in... Even more steps. So it knows exactly how to do this.
So delegation, this quality assurance and the reporting, right? So I just break it down step by step, right? What to do, right? Review the input from Ben and determine if the task involves multiple types of outputs or workflows that require collaboration across different manager agents, right? If so, break down the task into subtasks, et cetera, right?
Same for the quality assurance and the reporting to Ben. And this part then is very important, right? Which is giving that context to this director agent of what these agents can actually do, right? This is one of the most important parts in a system like this with so many agents, right?
It's giving a lot of context on what these other agents can do, right? So you can see, I give it, I instruct it very clearly what they can do, right? Manages communication.
I even describe which sub-agents our communication manager agent has, right? The key tools they have. right and even an example task right now i do that for all the manager agents and then some instructions the instructions are always good to sort of double down on important rules right for example send it use the send whatsapp to ben tool to deliver a deal to and comprehensive report to ben right and then we have some examples right now the queries can be really dynamic in these agent systems especially in an agent system like this so it's hard to come with you know examples input output But it's still good to give an example of how it should approach a certain query. So in this case, you're just giving an example of a query.
And basically, you tell him what he would do or should do in that sort of specific query. So you can see the action steps. Assign the LinkedIn post task to the content manager, et cetera, et cetera. So he knows, sort of gets context on what to do with a certain query.
Now, this is exactly also what my agent prompting tool helps with. This will sort of generate it for you automatically if you fill out some other details. You also have to double check if it actually does it perfectly right. But a lot of times it does and it saves you a lot of time, right? And these examples really do enhance the performance of these agents, right?
So I have a second example here, right? And then again, the note section, this is to double down on important rules. Because again, right, LNMs take instructions given to them in the end and in the beginning of the prompt more into account than instructions in the middle of the prompt, right? So important rules, always put them here.
You can see... I put in another one here because it struggled with that first. The first time I tried this, it is vital to my career. You only prompt your sub agents with tasks that they can actually perform based on their capabilities. Right now we have the flow builder option too.
Right now I didn't use that in this case because the flow builder is more if we have a very specific sort of set of actions our agent has to perform in a specific sequence, then the flow builder is really good to sort of double down on that. Now, in this case, of course, the variety of tasks and sort of orchestration can be very big. So we don't actually want to limit that through the flow builder.
So that's why I didn't use it in this one. Then we have the abilities here. We can label tasks if we want.
It's just for here in the sidebar how it labels tasks. And then we actually have an option of scheduling messages inside of Relevance AI. Now, this is unfortunately a business plan feature.
So I'm only on the team plan. So I also don't have access to this. So I'm going to show you a workaround how we can still schedule messages. without uh without this feature or without having a business plan then we also have to escalate to humans which can be very uh useful especially for like more like chat bots and things like that i i show you an example also in the whatsapp agents video uh can be very useful if you want to escalate it and you can escalate it through slack or through email then we have the tools in this case we only have one tool which is send whatsapp to ben tool of course right to communicate back with me and here we have the sub agent section right and here we have our four sub agents right And here we have some extra settings, right?
The first one is the approval mode. So we can actually decide if we want to let this, or direct the agent, run this communication manager agent automatically, or if you want to have approval required. Now, for some use cases, that can be very useful.
When we send out a really important email or something, we always want to check before it actually sends it. Then we can use these human in a loop steps, basically, with the approval required. In this case, we want a completely automated system. So I put all the...
agents on auto run right and then here we have some extra settings which are also important in these agent systems prompt for how to use right so here again we give it more context on what this sub agent can do right very important for a director agent again to know what this agent can do so here we just double down on that again right so we we we tell it what its responsibilities are what it can do right the key tools it has access to and an example task you right and then we have one more option which is the templates for communication and here we can basically uh decide what prompt our director agent should use when it communicates with the communication manager agent right so we can sort of decide that for them already right so we can say something like in this case right retrieve uh all messages from right and then we can even use uh variables right like this with the double curly brackets and those variables are basically prompts another prompt right a prompt inside of a prompt right So basically this, you will always have to send. And this is what we leave sort of open for our director agent to fill out themselves. And here we can describe to our director agent how we should fill out that variable, right?
So we could say the channels, right? To retrieve info from, right? Or messages from.
Now, in this case, I didn't use the template for communication because you can imagine that if we use a template, of course, we also limit a little bit of the, you know, options of how to communicate with the communication manager. And in this case, there's so many options possible in this system. that we don't really want to put these limitations on the system because it might limit the amount of workflows we can actually automate. So in this case, we didn't use it, but can be very useful if you have a little bit more of a rigid system to get more reliability inside of the system. Then we have the advanced settings.
It's important to always use the best models for these agents. In this case, I used GPT-4.0, but you can also choose other models and cloud. So that's it for the... for the director agent now let me get you through the four manager agents quickly so let me first show you the research manager right so the research manager basically has two sub agents right and i'm going to show you this loads and you can see here in the agent profile the research manager i put a quite a big description because again right this is what our director agent will read right again to really understand what this agent does right so we have uh the core instructions right again role objective right it's quite similar um to the director agent right in terms of his objectives of course because he also is a manager right then we give it some context and his sub-agents right we have the travel agent in this case and the research agent which i'm going to show you the travel agents in a second too and the research agent right and we give it an sop too you And some examples, right?
Very similar structure to the director agent, right? Nothing really special here. You can see we have the travel agent and the research agent and no tools available, right?
Now, important for the research manager agent, you can see also in the core instructions, is to review the work that was submitted to ensure it matches the original task and requirements, right? So these are important sort of tasks for these manager agents that are in between too, right? To make sure that what the sub-agents have done is actually right, right? Because they're sort of in the middle.
between communication between the director and the sub agent and sometimes contacts get lost that's why these these these manager agents this this role is also important for them right so um i will show you quickly uh the travel agent for example um so you can see we have the travel agent so the travel agent actually has access to the google serp api to do searches for google flights and google hotels right So you can see this is a lot more of a simpler prompt, as you can see, because this agent only has access to four tools. It's a get airport code, get IATA airline code, get hotel option, and get flight options. Now, these ones are to get specific codes for specific airlines, which are necessary to use when you call the Google SERP API.
Let me show you a quick example so you can also see how these tools are set up. For the agent instructions here, it's a pretty straightforward one, right? As you can see, objective, your goals, the system in planning is travel by number one, searching for flight options, right?
Using the required airport and airline codes and searching for hotel options, right? And ensuring an efficient use of available tools, right? So pretty straightforward. You see the SOP here with a description of the tools and some examples, right? So if I just give the same example, like, please look for...
flights from Amsterdam to Sao Paulo for let's say the 3rd of January 2025. So as you can see in the background, it first gets the airport codes of both, right? Because these are necessary to do the flight search for. And I noticed if I don't use these in a database, sometimes it actually puts in the wrong code. And then, of course, we can't do the search through the Google SERP API, which I'm going to show you in a second to how that's set up.
So you can see we got it back here. Right here are some flight options. Right now we can, of course, also specify this. We can, for example, ask it for its specific airline.
And then we'll actually also use the airline code. tool right and these tools are basically databases so i can show you quickly right to get the airport code what happens here in the background inside of the tool so you can see if you're completely new to tools right tools are basically um logic based automations right where we have an input field here which we save in a variable and then uh we can do go through steps logic-based steps to automate the process right and of course we can implement these ai um steps in there too Now, in this case, it's a very simple one, only one knowledge search, right? So as you can see, what this is, is basically a knowledge base, right?
Of all the airport codes, right? Where we have destination with the airport code. And basically, it just, our agent, right? Fills in this variable, right?
In this case, the city or country to find the airport codes for, right? So we have the destination. It filled that out with Amsterdam, right?
Now that variable we use for the query of our database, right? And it's going to retrieve the most similar results. right now in this case i use search type keyword because that's the most efficient way to retrieve data for these specific types of searches now let's say you want you have a customer support agent that wants to retrieve an answer for a specific question that's where you probably won't use keyword but uh the the vector right so you can see here vector now uh normally the best uh way to do knowledge retrieval in relevance ai is actually true to advanced knowledge retrieval where we have some extra settings so instead of going either vector or keywords we can actually go hybrid which in my experience works best we can also choose the fields to vectorize right and we can do retrieval post processing which in this case is just a very simple search right we want to go to amsterdam that's directly in the database so we can do this use the search type keywords to get an efficient outcome so you can see if i run this you can see we get amsterdam back right and the code right you and you can see here i the page size here you can basically decide how many uh results you want to retrieve so this case this gets sent back to our agent so it knows the airport codes right uh now in this case we didn't specify an airline but otherwise would use this similar tool to retrieve an airline code right and then it's going to use google serp api to actually find a flight flights right so you can see in this tool right so we have the departure airport code right the arrival airport code right the flight date of course in a specific format right which are again specified in here right if you don't know this agents will actually read these descriptions here to know what to fill out so if you have specific formats etc make sure to mention them here in the description so your agent knows how to fill fill out these fields and what to fill out right then we have the return flight date in this case i didn't say that right and the flight class we can also say right i can't economy class premium business class etc now we have the airline code in this case we didn't specify it right now it's important that you leave those options that are not always necessary or are not always given necessarily by the user uh on on non-required right because otherwise your agent is just going to make something up right in this case uh this one is is not required right so it left it empty right and i also instructed that right leave leave empty if user didn't specify specific airline right amount of people to book for right use one if i'm specified which i do for me because i'm alone uh then uh the two-letter country code of the other uh country the user is visiting these are just sort of necessary to do the api call uh for to the serp api now i used make.com to set up because make.com already has the serp api set up so i can show you that one quickly you so sir there we go find flight options now as you can see we have we have the server api here now if you don't know server api is basically directly from google right and you can set it up here in the server api and you can do actually some really interesting things with the server api as you can see we can actually and start getting data from Google Search API, Google Maps, Google Jobs, all these Google products we can use with the Google Search API, right?
Now, in this case, I used the Google Flights, right? But you can see there's lots of interesting use cases here, Google News, Google Trends, right? So there's lots of interesting use cases with the Google Search API. Now, you can do 100 searches a month for free. And after that, you'd have to pay a month.
a monthly subscription right you also have youtube search api so very interesting use cases there and then you can set it up directly here in uh you get you make your account you get an api key it's pretty easy to do and you add the api key to make here right and then you have the serp api and you can see you can do all these things so how does this work right if you're completely new to this right how do i make my agent sort of send information and retrieve information from this make scenario uh it's pretty easy you uh you can see here right we just use an api step here in relevance right if you're completely new to this i have a full video on how to do this also on my youtube channel so i'll go through it very quickly here so you just click post right you use the webhook that you you get from make so first in these scenarios you create a custom webhook in this case i can't do it because i already have one but you create a custom webhook right so you just look for webhooks create a custom webhook and in one click you basically get a webhook right so you copy that webhook you create in this case here right copy this you go back to relevance in the api call method post right you post um the url in there right and then you can decide what you want to send over to make now in this case i sent over all these variables right so you can just add more here if you want right and here i put in the variables that are agent filled out right so basically make sure that all of this information is separated and sent to make right and then for make we can then use it into the Google SERP API. So as you can see, in this case, I set up a router. So if the airline is not defined, or if the airline is defined, so you can see I have a filter here, airline code is undefined, then it goes here, because otherwise it will give an error.
So in this case, airline not defined one way, and this is back and there and back, basically, and the same here. This is where the airline is defined one way and where the airline is defined back and... there and back. So in the SERP API, you can see all we need is the departure airport code, the arrival airport code, the outbound date, return date, and we map that, the values we get from the webhook. The country, travel class.
We have some more options, but they weren't relevant for me. So that's it. And then Google will search for flights for that specific one. Then we use an array aggregator to bundle all the results. It actually gets lots of results.
So I just choose the option of best flights, right? And then we send that back to Relevant CI with a webhook response, right? So I send back the array, the outcome of the array, right, the bundled. So the outcome of the Google search API, and then we send that back to Relevant CI.
And then of course, we can send that back to our agent. So I can show you a quick example how this would work. You can see we get the flights back and this flight options back. We get lots of flight options back. That will be sent back to our agent.
Now, of course, in my example, my demo, I said, choose the three cheapest ones. So our agent actually reduced it down to the three cheapest ones. And then send it back to the manager agent.
So that's how this one works. And for the hotel options, very similar. It's also with the SERP API. I can show you very quickly.
And I'll just do a search of... SERP find hotels now in this case a lot simpler although we actually had to set this one up a little bit more manual as you can see because we didn't have the google hotels option directly in the google SERP API so a lot more straightforward but yeah similar process right so that's it for the travel agent now let me show you very quickly the general research agent So here we have the research agent. Now the research agent, we have equipped with three tools, right?
We have a Google search. So you can basically do a Google search for any topic, right? You can do a web scraping, right? And he has a LinkedIn scraper.
Now we can add lots more if you want. I have a full scraping agent tutorial also on my YouTube channel if you're interested in scraping other things. In my specific use case, I only need this, but you can also set up social media scrapers, visual scrapers, anything you want here on your research agent or even a... perplexity if you want, things like that.
But it does a pretty good job with only these three because with the LinkedIn scraper. In this case, I'm going to show you through the example, right? Search for my demo, right?
Search for Christian Apfel's LinkedIn, right? Using the Google search tool and then scrape his profile using the LinkedIn scraper tool. Right now, this was already instructed by the research manager agent on which tools to use, right? Because, of course, he has context also on what this agent can do, right?
But you can see we didn't even have a LinkedIn from Christian, right? And he just used the Google search, right? You can see Christian Apfel here even filled in the... the the company name because he had that data point and then linkedin.com he got back the google search results for that and basically found his linkedin profile from those right then he used the linkedin scraper tool right to scrape all of the data from his linkedin as you can see get lots of data right and then he made sort of a summary here are the details right which of course this thing can be used to uh to actually you see email he found two to actually uh update our crm which he did right And even sent a LinkedIn message, I think. But yeah, you can see this Google, this research agent is very important to actually do research on leads, but it can also research topics, right?
And you can make this as fancy as you want. In my other video, I have lots of other scraping tools available, which you can add to this agent too. So that's it for the scraping agent. I can show you very quickly in terms of the core instructions, not rocket science, right? Using search tools, right?
Your goal is to stay spending conducting online research, right? Using the search tools to find relevant information, scrape useful data from websites or LinkedIn profiles, right? Delivering detailed and clear reports to the communication manager.
Right, so pretty straightforward, I think. That's it. Then let me go through the next agent.
I think an interesting one is the communication agent, right? Who has access to all my communication channels. So let me start with the manager agent, right?
So for the manager agent, this manager agent, of course. has six sub-agents as you can see email agent call agent the whatsapp agent the calendar agent the slack agent and the linkedin comms agent right now why did i call this comms because we actually have another linkedin agent who creates content right um so for the core instructions right similar what to the the other manager agents right we're in the middle right has usually have three different responsibilities again delegating the tasks right orchestrating second quality insurance and in this case reporting back to the director agent right again as always give it lots of context on what these sub agents can do right and some examples so let me show you quickly the sub agents which i think can be interesting i'm going to skip over the email and a calendar agent because i actually show those two in my personal assistant agent video right if you're interested in those two they're they're pretty simple right then we have i think an interesting one is the call agent right so you can actually call on my behalf right and it's pretty simple agent actually all he has all we have given him is two tools right which is first of all database of my contacts so it can actually retrieve phone numbers from names right you can see tools right get phone number tool now this one's pretty straightforward unfortunately i can't show you an example uh now because i'm actually recording with my phone but uh if you want to see an example i i show an example of the the call agent or a sales agent that calls people in another video which i'll also make sure to link up here so i'll show you quickly the tools how to set up so you get phone number really easy right again i just have a database and i do a knowledge search right so fills out the name or phone number and gets back the result right so i just use google contacts to download a list of all my my contacts put them in a database if you don't know in random say hi right pretty easy to get to set up a database right here knowledge all right you could just create a table upload a csv right and that's how you create the knowledge base then after you would uh it would will appear here in your knowledge sources so that's how this one works pretty straightforward and then we have to call someone now the nice thing in relevance is you actually have this sort of integrated right making the phone call now i think this is set up through vappy but we don't actually have to be inside of vappy to set it up which is the nice thing here rather than say i and the second nice thing is we can actually personalize the prompt right and that's exactly what we do here right because of course if i say for example reschedule a call uh call my friend right um ask him if we can reschedule lunch for saturday at 1 p.m right then uh every time my query will be different so that's what in here in the inputs fields right what i have is of course the phone number which you'll normally use first to find the phone number you'll fill that out and then depending on my query it will fill out the goal and details for this call Right. Describing as much detail what should be done in this call.
Right. And the first name, of course, of the person to call. Now we use this make phone call. step right where we of course the variables the number right we have the assistant uh system prompt your band uh band's personal assistant helping him call people in his network right here we have a pretty simple prompt and of course we put in the goal right of above here in the objective right so every time i give a different query our our voice agent is going to call uh with a different sort of script and different outcome of course and then he also understands why he's calling right and of course here i make sure that you know you will first greet the user mention that ben from sprundle asked me to reach out to you right now i can optimize this a bit more right if you want to see a more optimized prompt also check out that other video the sales multi-channel sales agent video that's it and then we have one more step here is where we actually retrieve the call details right so basically we got a transcript back we can even get the whole recording back if you want but in this case just get the transcript back because of course if i asked my friend if he could reschedule for saturday at 12 p.m and he said yes then we actually also want to know that of course that that was confirmed and then our agent can send that back that that was confirmed and of course now we can send it to the calendar agent to actually schedule in the meeting all right so that's it for the voice agent then i can show you quickly the linkedin agent i think is interesting or the whatsapp agent so the whatsapp agent is has actually quite a few tools right as you can see we have six tools i'm going to show you why right and i'm going to show you these tools because i think there's lots of interesting use cases and this is for my personal whatsapp as you see you saw right it was sent directly from my own uh whatsapp but yeah again if you're really interested in whatsapp i do have a full whatsapp agent video too uh so basically what we do with these tools here and i'll show you through the example right you can see this is the demo right retrieve all unread whatsapp messages from today and report back with sender names right so what it first does is get the unread whatsapp chats Right now, I'm going to show you that very quickly.
It's basically just an option in the WhatsApp module, right? So we get all chats, right? And basically what you can see in the second step, I get all the chats back, right? And the chats basically means you just get the names of the people, the phone number, and if you have unread messages, basically.
And then I identify. right extract all the json objects from the chats where unread count is more than zero right meaning he'll retrieve back all the messages or all the conversations that have an unread count in it meaning all the unread chats but we can't actually in this step in this specific step the get all chats right we don't get back the the the actual messages inside of the conversation yet right that's why we have a second tool so it's the get unread unread whatsapp messages tool as you can see and basically in the inputs field there as you can see we have the chat id which is also what that first tool brought back right uh it's a chat id and through that chat id we use the get conversation option i think in the whatsapp module to get the conversations right to get the messages back from that specific conversation all right so you can see it filled out the chat id and here we have get all messages from chat you right and then that of course is sent back to our agent again right to get the actual conversations and you can see it uses that for each of the unread chats we have right so it uses a different chat id to retrieve the messages from each of the ones where we have unread messages right and then it can also get the name from a chat id right all right so which is basically a database right and then In the end, you can see it would get the unread messages. So a little bit of a setup, but it works quite well.
So that's it for WhatsApp agent. Of course, you can also send messages, right? As you can see here, right?
Send a WhatsApp message to mom, right? So that message, right, where we have the same, we have the database to actually find the phone number, right, for my mom, right? And then it uses the send WhatsApp tool, right? Where it needs the phone number and the message, right?
And we use that same module, but then the send. send a message option again this is not official whatsapp api right so you can literally do this with your personal whatsapp number so you can see it's getting a start new chat right i usually use this one because then we can use the phone number we can also use the send message in the chat but then we need to then we need the conversation id which would be would have been possible too but uh even if the chat has already started you could still use this one Anyway, that's, it's a little bit more technical, but that's the WhatsApp one. Now for the LinkedIn one, very similar process, right? I can show you, I'll just go through it very quickly. So as you can see, right, we have the same thing, right?
Get unread chats first, right? Then we have get messages from the conversation where we have the unread messages, right? Then we have the send LinkedIn message.
And we have one more here, which is send a LinkedIn invite, right? And in this case, we don't have a phone number, right? But in this case, we need to, for example, send a LinkedIn message or send a LinkedIn invite. We need the LinkedIn URL.
So in this case, we actually let our research agent, right? has the linkedin scraper the google search he will find the linkedin profile before sending a message or an invite on linkedin for example right so here you can actually see it did it right with that christian up for a first found his linkedin profile with the research agent right that was then sent back to the comms manager agent the linkedin profile he reported that to the linkedin comms agent to actually you can see right you instructed him with this and And you can see he used the send LinkedIn message to actually send this message in my demo. I didn't notice, but yes, I did.
So it's good to also build the guardrails in, but it seems to be good. He sent my calendar out. That's what I asked him to. So all good.
So yeah, that's it for the LinkedIn agent. Now for the email and calendar agent, check out my personal assistant if you're interested. Now, let me go through to the project manager agent.
Here we have the project manager. Of course, the project manager, again, is a manager, right? So very similar responsibilities as these other manager agents, right?
Of course, task, delegation, orchestration, quality assurance, and reporting back to the director. And of course, this one has three sub-agents, the HubSpot agent, in this case, for my CRM, right? Notion agent and a Google Drive and Docs agent.
Right now, I'll go over them very quickly. So for the HubSpot agent, right? Here we have the HubSpot agent. uh of course what he can do in this case i i gave him a few tools but we can do a lot more if we want right if you want to expand on this in this case the most common use cases for me are add a contact to hubspot right uh get a hubspot contact right get get information back for my contact right and update a contact inside of my hubspot but you can add lots more sort of actions inside of your hubspot if you want right basically allowing your agent to do any task inside of your hubspot almost so In this case, as you can see here, same example, right? The research agent did all the research on this new lead, right?
Sent that back to the director, who sent it to the project manager, of course, passed this on to the HubSpot agent, who then had the task to add Christian to HubSpot, right? So you can see, add, use the tool, add contact to HubSpot. I'll show you very quickly.
So here we basically gave it lots of input fields. If he can find extra data, et cetera, want to all save that inside of our crm right so you can see we have the email the job title linkedin url lead summary right in this case it doesn't have the company linkedin url so important again right you can see i have these all on non-required why is if that information was not available in the research right then of course uh it would error if it doesn't have that information but here you can see they did find the company size so it filled that out right so it fills out everything it can fill out right and then we just use the HubSpot API call here, which is a built-in module here in relevance, right? All you'd have to do if you use HubSpot is find the endpoint, right?
To find the path, right? Which you can find in the HubSpot documentation, right? So in this case, the path for creating a new contact is this one and the method is post. And then all we use is this, where this is the property name inside of HubSpot, right?
And this is the variable, of course, that our agent fills out. right so even if you don't know how to code this this is really simple right that's it so it'll basically update uh update rcrm and add that contact right and that's what it did so that's it for the for the hubspot of course you can do some other actions right you can also get uh get uh contacts right you can update contacts and if you want you can add lots more capabilities to you to your agent too so that's it then for um let's check the notion agent right So Notion agent, of course, has quite a few tools, actually. He has a tool to get my to-do list, to update my to-do list inside of Notion.
So these are basically databases inside of Notion, right? Get my YouTube content calendar, update my YouTube content calendar, update my LinkedIn content calendar, get my LinkedIn content calendar. And you can also create a Notion page. Right now, Relevance AI doesn't have a native integration with Notion. So in this case, I also use the same setup with make.com, right?
I'm not going to show you all of them in detail on this one. again blueprints will be available too for other make scenarios too in the templates right so that's what you can do you can see right in the background same thing for the demo right it uh the our linkedin content writer agent right wrote the linkedin piece right that was sent to the project manager who then added it to my linkedin content catalog right you can see right and again we use that make.com to send it over to make it easier to update our notion right that's it for the notion agent then we have the google drivers and doc now again no native integration with Google Drives and Google Docs in Relevance AI. Again, I kept this one simple, but you can add a lot more, right? So in this case, you can create a Google Docs, right?
And it will actually save it right away to my drive too, and it can get Google Drive files, right? So as you can see here in the example again, right? Same example. We got all that research information.
It also made a Google Doc, right? As you can see, right? how does that work right same thing right i send it over to uh to make.com to to make the doc right with the api call so pretty straightforward i think and i have one more uh thing here which is html format right to actually make it look sort of decent here as you can see so that's it and then we have the api call where we send it to make or we have the google docs uh module already built in we send that text over there put put in the google docs and the google docs webview link is getting sent back right so that's it last manager agent is going to be their content i'm going to keep this one brief because i also have lots of videos on content agents and i reused some actually so so here we have the content manager and our content manager has four sub agents right and actually this manager agent is different from the others because he actually also has tools right he has the options to actually post directly to linkedin post to Webflow, my website, right?
Blog articles and post to X. Now, why do we give that to the content manager agent? It's because we get that double check, right?
We get that extra check, like I said before, right? Is instead of giving it directly to, let's say the blog writer agent, we actually get the content manager agent to first check if everything's all right, that it matches sort of what we were looking for with the original query. And then he can decide to actually post it, right? We have those three tools.
And now again, I use make.com for most of these to make these integrations easier with these platforms. If you want to know more in detail, I explain it in detail in my repurposing video. A lot of referrals in this video to other videos, but it's because I reused quite a bit. So for the sub-agents, we have... I'm not going to go through them all because I show it also in the repurposing agent video.
And for these content agents, what I think really interesting setup is... giving them specialized fine-tuned models for each of the platforms, right? Because AIs, in my opinion, they struggle the most with replicating a sort of natural tone of voice, especially for these specific platforms like LinkedIn, right?
So I give them fine-tuned models. Now, again, if you want to know more about fine-tuning, I have a full video on it. Also how you fine-tune based on LinkedIn for yourself or for other people.
But you can, of course, do this for all different. content types or or social media right so that's it i can show you the linkedin one too but i do have a full video also on linkedin assistant right so you can see here uh we gave the linkedin assistant a few tools it can actually also do some ideation right so you can find similar posts again if you want to know this in detail this is from the linkedin video right so i can actually find similar posts from people i like in the space right it can query a linkedin database to retrieve specific LinkedIn posts about specific topics, right? And then I have my fine-tuned LinkedIn post writer tool that basically uses my fine-tuned LinkedIn post writer tool that writes it in tone of voice, good tone of voice for LinkedIn.
He writes four variations and then our agent system, right? They can actually choose which one they like best, right? So that's how it works.
Now, lastly, I'm going to show you very quickly how you actually can schedule messages, right? To your... to your director agent so you can actually automate workflows on a repetitive or daily basis and i'll show you very quickly how you can set up that whatsapp trigger so we go back to mate.com that's the workaround right we use make.com to actually trigger this so um so basically all we do is we create a new scenario right and here we can create um an api call to our relevance ai agent right now in this case unfortunately make.com doesn't have a native integration with relevance.ai yet so we have to set up an http call which i'm going to show you very quickly so we we click here on http make a request right there we go make a request, right? And here in the URL, if we go back to our agents, right? We go to API, right?
And here we have an endpoint, right? We're going to copy that endpoint and we go back to make and we paste that in. Then the method is always going to be post in this case, right?
And then we need two headers, right? The first one is going to be content type, right? And you can also, I'll show you later where you can find this. And the value is going to be application application json right now i'm going to show you where you find this here in the sample curl you'll see header one content type right application json i actually put it wrong right and the second header is going to be the authorization right and that's going to be your api key right so i'm not going to show you my api key but you can generate it here by clicking on your api key will be generated you copy that and you paste it in here then you have your header set up then you need to select the body type which is going to be raw right the content type is going to be json right and then we need the request content it's like where what are we going to send right so we go back here and here we have the request body and we're going to copy that i'm going to paste it in now as you can see here in the request body we have the agent id and the agent id basically tells reverend say hi to which agent We want to send this, right? Now, we don't only want to send it to this agent.
We also want to send it to the same conversation. Because if we send it to the same agent, but not to the same conversation, it will start a new chat. And it basically loses all the chat history, right? And sometimes we want our agent, of course, to have chat history, especially in a system like this, right? So we actually also want to add in a conversation ID.
So you can go in here. We can actually copy this part, right? add in a comma right we add in this part agent id and then we change the agent id to conversation id that's it and then you can literally decide here the value right so you could do one two three if you want right and basically this will tell the api call to always send it inside of this conversation right so that's it and then here of course now in the message we can define what we want to send so let's say we want to schedule our agent to every day retrieve the unread messages from all my communication channels.
Then here in the content, this is literally the message we're going to send to our agents. So we can literally go retrieve all unread messages from all my comms channels, right? Put it in a Google doc, right?
Et cetera. But we can say anything here, right? It's like research all the new leads that came in, right?
Add them to my CRM, send a LinkedIn invite to them. um right we can you know do whatever we want really and that's really the power here because once you've set this up right you can literally clone this and put in five different messages to send out every day now once you've done this that's it you have it set up right and all you do here then is you can schedule this right so we're going to save this quickly right and now we can schedule when to run this api call right so we can go at regular intervals for example every day you know at whatever 8 8 40 a.m right this is going to run right so every day it's going to send that message to our agent right and we'll receive the document with all the unread messages inside of uh our whatsapp right so of course again right you can clone this and set up five or six right that's that's i think the power of this now let me show you very quickly the whatsapp setup right now this is going to be a little bit more complicated and if you want to know this in detail right check out my whatsapp agent video where i i show you this setup in in detail right so here we have the integration with the whatsapp business cloud and as you can see it might look a little bit complicated but basically what this does is again this is the api call that i just set up right but to relevant ci and here this is the whatsapp module so basically this whatsapp module gets triggered every time a message is received onto this whatsapp now if you don't have this this is the whatsapp business api If you want to set up the WhatsApp Business API, but you don't know how to do it, I also explain it in one of my other videos, which I'll make sure to link up here. At the end of the video, I'll show you how to set up the WhatsApp Business API.
Now, if you don't want to go through that whole hassle, and you still want to be able to use this system, you can still do it. The only limitation will be that you can't do it with voice messages and documents or images. The way you would do that is you go to your agent here, the triggers, and you click on the premium triggers, right? You do need to be on the team plan, I think, in relevance. But you can click this and you can basically connect your own personal.
WhatsApp to this agent and you can trigger it through text messages from your own WhatsApp. So this is a possibility. If you have and if you want to set up the WhatsApp business API, then you can have this system and here you basically have the router here.
All it does is these are media types. So this download the media types, saves it in Google Drive, right? Then depending on if it's a voice message, it goes speech to text, right?
And then sends it to our agent, right? If it's an image, it goes image. the text or describes the image so our agents understand what has been sent, right?
And here's a document and it will transcribe the document, right? Now, it might not be that useful for this specific setup, but transcribing documents and images from WhatsApp directly, there are a lot of use cases for it. I literally know a startup here in Sao Paulo who just raised a lot of money that sort of has a startup around this, where literally all it does is interprets documents and images, extracts information and outputs it into a database, right? because WhatsApp is used so much, that is actually a really powerful use case for many different businesses.
So a lot of different use cases for this setup, I think. If you want to know it in detail, again, right, the template I'll also put in the community. And if you want to know it in detail, check out my WhatsApp agents video. So that's it for this video.
Thank you so much for sticking with me, if you're still watching. And yeah, I didn't even go through everything yet. But again, if you want to check out everything in detail, really want to replicate it, you can join my community.
if you want to of course i'd love to see you there besides all my templates i also have one-on-one tech help and some other cool things in the community so if you're interested and taking sort of building these systems serious i think you'll like the community if not fine too i will keep making a lot of videos on youtube too anyway if you got any value out of this i highly appreciate a like a comment and subscribe i'd appreciate it a lot and let me know if you have any questions in the comments below Thank you so much and hope to see you in the next one.