Leveraging AI

188 | AI Agents in Action: How to Build a Business-Ready Agent W/out Writing Code with Pooja Jain

• Isar Meitis • Season 1 • Episode 188

Share episode

Everyone’s talking about AI Agents, But few are showing how to actually use it in a way that saves time, uncovers real insights, and drives business decisions.

In this live episode of Leveraging AI, Pooja Jain — founder of PowerUp AI and one of LinkedIn’s rising AI educators — is going to take you step-by-step through the exact process she uses to build custom AI agents. No fluff. No code. Just the “how to” you’ve been missing.

You’ll see a live demo of a real AI agent built in Relevance AI that handles competitive analysis — scanning websites, doing sentiment analysis, pulling customer feedback, and even giving positioning suggestions based on gaps in the market. Yes, it actually does things (not just spits out summaries).

Meet Pooja: A former Procter & Gamble leader, Pooja now trains executives and C-suite leaders across Europe to integrate no-code AI and automation into their businesses. She’s already taught 170+ leaders — how to lead AI initiatives without writing a single line of code. She knows what works (and what doesn’t), and she’s here to show you the difference between tools, automation, and real AI agents.

About Leveraging AI

If you’ve enjoyed or benefited from some of the insights of this episode, leave us a five-star review on your favorite podcast platform, and let us know what you learned, found helpful, or liked most about this show!

Isar Meitis:

Hello, and welcome to another live episode of the Leveraging AI Podcast, the podcast that shares practical, ethical ways to leverage AI to improve efficiency. Go your business and advance your career. This Isar Metis, your host, and we have. Maybe the top exciting topic of AI in 2025, which is agents, which is going to talk about today, and agents are already here and I know a lot of people are hearing about this. It's something that is coming and it's the next stage, and it's the evolvement of LLMs, but agents are already here and multiple people and companies are already generating significant business value by leveraging. Agents across multiple aspects of the business. But for most people and most companies, there's still this elusive concept that people don't understand and definitely do not know how to implement. Now, this gap between the people and the companies who have agents to those who don't is spreading every single day, and it's widening. And you want you, yourself, as a person with capabilities as well as your companies to be on the right side of that gap. Meaning you want to be on that fast bullet train, that accelerating and providing more and more capabilities to your business versus being standing on. The train station and watching that train getting further and further away from you, especially if you know that your competitors might be riding that train, meaning they'll be able to do more and more than you can for less money and then be a lot more competitive than you can now, developing agents sounds like complex, and it sounds very technical and it sounds like only big companies like Microsoft with a lot of people who write code can actually create them. But the reality is there are multiple tools out there today that allow you to write really powerful agents with either no code or low code. Today we're gonna focus on no code at all. So one of the most powerful tools out there that enable to do that is called relevance ai. And our guest today, Puja Jain, is a relevance ai. Expert and she has been developing agents for multiple companies on relevance for a while now across different aspects and different businesses and so on. Now, in addition to the fact that she knows relevance really, really well, she spent years in developing and implementing AI solutions at Proctor and Gamble. So in addition to her recent experience and just building them on relevance, she has enterprise level experience in understanding what is required to actually develop agents that actually work in a business environment. And she knows how to do it in a step-by-step in a tool that anybody can use, which makes her literally the perfect guest to talk about, this topic with us. So this is exactly what we're going to do today. We're going to show you an entire process, beginning to end, how to develop an AI agent, what to think about and how to use relevance in order to do that. But having that knowledge and seeing this will allow you to develop other agents and on other tools because the concepts are exactly the same. Now, as I mentioned, since agents are maybe the most transformational technology we ever created, at least that I know of so far, then. This is a really important topic and hence I'm really, really excited to welcome Puja to the show. Puja, welcome to Leveraging ai.

Pooja Jain:

Thank you so much, Isar, how are you?

Isar Meitis:

I'm doing awesome. I'm really, really excited about, this session. I myself am tinkering with different tools. I'm definitely not close to your level, in doing this, so I'm really excited. I'm sure a lot of people are really excited as well. Our top performing episodes in the past few months are all been around agent development, so I'm sure there's a lot of people who are really curious, about this topic. It's everywhere in the news if you're following an ai, but still, I think most people now get a feel on how to use large language models and image generation. I think 99% of the people don't have a clue how agents work and how to create them. And so I think this is gonna be really fascinating. before we get started, a few, messages. First of all, thank you to everybody who are joining us live. Whether you're joining us on LinkedIn or joining us on Zoom, we really appreciate you being here. I know all of you have other stuff to do on, Thursday at noon, Eastern time. But, feel free to introduce yourself. Tell us what you know, what you don't know about agents, and what you wanna know from this session as well. That will help me, guide the conversation, maybe even more. Tell us where you're from so we know where people are joining from. That's always fun for me to see. There's always people from all over the world, at least on this, on the, LinkedIn side of things. There's always a lot of people from, interesting places. So introduce yourself, make new friends. In addition, one last thing that I will say, is that if you are still watching us live, the next cohort of the AI Business Transformation course starts this coming Monday. So when this becomes a podcast, if you're just listening to this after the fact, you missed that particular cohort, but the cohort starts on May 12th, meaning you still have a few days. This is this coming Monday, this course. Is really transformational for people, for companies, for careers, for complete teams, and we've been teaching it. I've been teaching it for the past two years every. Single month, sometimes twice a month. So hundreds or maybe thousands of business people have been through it and have really changed their businesses with AI based on the information that they've learned. So if you have not started proper implementation of AI in your business, this is an incredible opportunity to get a huge amount of information, both on the tactical side of what tools to use, as well as on the strategic side, on what's the right process to implement AI company wide. If this is interesting to you, I'll drop the link in the chat. If you're listening to this after the fact, then there's gonna be a link in the show notes to tell you when the next cohort is, which will probably be in August. because we in between, we usually teach private courses and we're usually fully booked. that's it. With all of that being said, I will give puja the microphone. I'm really excited to see what you have prepared for us and, get ready everybody to learn how. Simple. It actually is to create agents that are extremely powerful.

Pooja Jain:

Thank you so much, IAR for having me here today. And yeah, super excited to share what I am working on and what I have learned about agents so far. Honestly, speaking agent AI is evolving. It's evolving on a weekly basis now. We are seeing something new every week coming up, so it is even new for me, although I have been working in the automation space for many years now. But yeah, agent AI is something new. And today, what I'm going to show you is first like clarifying a bit. So what are AI agents actually, and how do they differ from say, an automation workflow because that's where I think most of the people are still struggling with. And secondly, showing a live demo in relevance AI about this market research AI agent that I have built, and what is the concept around it? Should we get started?

Isar Meitis:

Yeah, let's dive right in. I'm, I really wanna learn as well.

Pooja Jain:

Perfect. Let me share my screen quickly.

Isar Meitis:

Sure. for those of you who are, listening to this as a podcast, and I know thousands of you are, we will explain everything that we're seeing on the screen so you're not missing anything. But if you do wanna watch what we're doing, you can either switch to watch this on YouTube. So go to our YouTube channel, then multiply AI YouTube channel. There's a link in your show notes, or if you are driving right now or mowing the yard or at the gym wherever you are, when you cannot do this, then you can keep on listening to us and then you can decide later on if you also want to watch the YouTube video.

Pooja Jain:

Great. Okay. So firstly, what exactly is an AI agent? of course, like by now almost everyone is aware of what is Chad GPT? So Where do agents fit in here? So imagine when Chad G PT comes in, even now, to get something beneficial out of Chad G pt. You have to give in a proper prompt. You have to add in your business knowledge, and this becomes a repetitive process, right? And Chad g PT is still a chat bot. So it only talks, it does not execute. And this is why AI agents are really changing, the landscape for the businesses because they can execute. So if you want to understand AI agents in very simple terms, think of them as let's say if chat GPT gets knowledge, so your business specific knowledge, it gets a memory. I mean, a chat g PT has a memory, but really, you know, something that is a memory specific to your business, to your style of working as well as two hands that it can start executing. Actions in your systems. Now, it can be something as simple as writing an email or, managing your calendar, which can be chaotic for a lot of people. it's a big productivity hack If JGBT can start managing your calendar or something as complex as, doing a proper research and then going into your CRM and updating the fields there. So this is what, AI agents are all about, like they can understand, of course, because the underlying power is still LLMs, but in addition to that, they can also execute actions in the systems in your business, ecosystem.

Isar Meitis:

Yeah. I'll add, two, two more things. like when I think on agents versus large language models. So you mentioned, one very important thing, which is the ability to take action. The two other things that agents do that LLMs don't do, one is make their own decisions. So they're more autonomous. They don't have to be, by the way, but they can be more autonomous than just a large language model, meaning you can give them a broader task and they will figure out the steps on their own without you having to define an exact path on how to get there. And the other one is. If you build it correctly, they can be multi-layered, meaning you can have an organization of agents working together, like we have teams of humans. You have a manager, you have somebody writing content, you have an editor, you have an evaluator, you have a designer, or a similar parallel in any other part of the company, the same thing. You can build agents and then they can work collaboratively versus just working on their own, which is what LLMs do. So these are the main differences.

Pooja Jain:

Very good point. ISAR because, and this is also one of the major differentiators when you start thinking about agents from workflow automation. so workflow automations are really like, very static. So let's say if this happens, then they should happen. There is no autonomous behavior there. you have to predefine everything and they execute, which is fantastic for a lot of business processes because not every business process needs, that level of autonomous behavior. However, AI agents, they can select their own tool. They can select as I mentioned, they can select their tools. they can select the next step and so on. So where do you really need AI agents? So AI agents make sense when your process is super complex, involves multiple steps and multiple level of decision making. If this is the case, then you should start thinking about AI agents. Otherwise, if your process is more about, say, repetitive steps, that more or less stay the same. You are good to go with a workflow automation.

Isar Meitis:

Yeah. I always tell people now started calling, Zapier and make like AI agents are like, no. If it's doing just a step by step process, you don't need AI in it or you can bring AI in it into specific steps if you're trying to analyze what surgeon in an email as an example. But the rest is just old school automation that existed for a decade now.

Pooja Jain:

Yeah, absolutely. Oh, by the way, Zapier has also introduced their AI agent builder, which is a no-code as well. I think that most of these workflow automation builders are now also moving towards agent ai. Yeah. Great. And then second point, that is, I just mentioned about this AI agency, so that is exactly what I would be showing today. So my agent is about a market research AI agent, or rather a team of AI agents. And when you start thinking about this. you have to really think of it like a team of, humans that are running this. So let's think of it, there is a manager agent, and manager agent is the one that is coordinating with all the subagents in this team. I, as a human, interacts only with the manager agent. So I only give my, request or my commands or whatever I want to do, only to the manager, agent, manager. Agent then, picks like the next subagent. for example, in this specific use case, so I build this for competitor research, there are several subagents, like industry analyst, competitor tracker, customer sentiment analyzer, social media auditor, and then a reporting agent that is really gathering information from all these subagents, synthesizing it and sharing it with the manager. It If you think about it, it's exactly like how you would work in a team of humans. And that is actually the basics of even when you start setting these up in any platform. So manager agent is really who you should be telling in detail. think of it like a job description or a very detailed SOP that is literally your prompt that manager agent should understand and then the manager agent in return, from based on this prompt, should be able to execute these, or rather pick the right subagent for your task. We will see this in a demo. I think that will make it, more clear.

Isar Meitis:

Yeah.

Pooja Jain:

anything, to add here? Isha.

Isar Meitis:

No, I think it's great. I really think what you said is the important thing, think about what humans you would need and even make it more granular, because in humans, in many cases, there's one human that does several of this. So think about it more on the task level rather than on the human participant level. And because every agent will be doing one task that will enable it to be very good at that particular task. And then the manager agent, and then you can also add layers, like a improver, like somebody that reviews the work and adds Yeah. Comments and so on. there's different layers you can add, but still each agent will be focused on one task and there's will be one or more agents that will help to coordinate the task to make it more effective this time around. As well as moving forward.

Pooja Jain:

Yeah, that's a great explanation. I agree to that because when you look at it, I think in an organization you would not see a team that where one person is just focusing on industry analysis.

Isar Meitis:

Yes. So

Pooja Jain:

it can be equated to, I don't know, a very well funded startup where you have a one person doing one task.

Isar Meitis:

Yeah.

Pooja Jain:

So now let's go into relevance ai and I will start describing you how relevance AI is, but I'm hoping that there's an interesting

Isar Meitis:

question, which I know the answer and we're gonna actually demo that, but it's a good question to ask. The question is, is the human sets up the subagents and not the manager agent spins them up in real time? And the answer is yes. and I think it's a yes, but, so I will let puja answer the rest of it.

Pooja Jain:

Yes. I'll be showing that during the demo, and if it is not answer, happy to take that at the end.

Isar Meitis:

Okay. Perfect.

Pooja Jain:

Okay. So what you are seeing on my system is really the relevance AI interface. It looks a bit messy because I've not really organized my workspace here. but relevance AI is a no code, AI agent builder. And if you go into relevance ai, they have now terms and terms of templates. So when you start going, like you can create a free account if you want to get started, and they have a lot of agent templates, which are fantastic way to start. So if you're just starting out, I think the best way would be take one of these templates and start editing it for your requirement. That is the easiest, right? Then there are a lot of tools, so these are really the integrations that are already present in relevance. So for example, if you want to extract something from LinkedIn, they already have a tool for it. All you have to do is select it, use it in your agent or in your project, and adapt the prompts. Now let's go into this agent that I am working on, which is the co research agent. Okay, so firstly, let's see, maybe I will first run this demo so we see the output and then I will start explaining it one by one. So this competitor, analyst agent, as I explained, is a team of subagents that is doing industry analysis competitor. So it can go onto your competitor's website, track the latest updates. It then goes into, say Trustpilot or any other review website that you have given access to, gets the latest reviews. I have added an additional layer there. So not just get the reviews, because let's say if the competitor is doing well in something, I want to understand why or if there are any gaps. I also want to understand why. So it has an additional layer of sentiment analysis, tracking. I have also trained it to go onto the LinkedIn or any other social media, for example, to gather what is happening at the social media of the competitor. And finally, it synthesizes everything and sends me over on Slack. So let's give it a demo. So let's say I just give, use a demo use case. Okay. I'm a sales head for, AI powered, CRM for SMPs. So I'm simply describing what my company's doing in very simple terms. Nothing like, we do not need a page long prompt for this. And I would like to. Get the competitor insights, say on Pipedrive, because Pipedrive is like the CRM, which is very, like a competitor for me, right? So I would just simply run that, okay. As you can see, I've simply, talked with this manager agent, right? So what you saw on my window was the manager agent. I simply, communicated what I want to do and it has started working in the background. Now, first thing is, it is extracting the industry news for me. so this is another subagent that is running in the background. Now let's open another window so I can show you what is happening, in the background. Okay, so I just, ran this like before the session because sometimes, it is extracting a lot of information. Yeah. It'll take time from the web. It takes time. So let's see what it did. It extracted the industry news, which is specific to pipe drive and which is very specific to the AI initiatives of Pipedrive. Because I specifically said that, I am doing this AI powered CRM.

Isar Meitis:

Yeah.

Pooja Jain:

So it just extracted everything along with, the source. Then, so those of you who are just listening,

Isar Meitis:

there are multiple articles with each and every one with several bullet points and topics and summary, and then there's a final analysis of all of them together.

Pooja Jain:

Yes. So this is one agent that did its job, second agent, which is the Trustpilot Review summarizer. What it did, it went on to Trustpilot, it got the latest rating of Pipedrive. And based on that, it gave me like the key positive points. what is happening there? key pain points, so for example, it find out that based on the reviews that there is a recurring issue, in the limitation of the form of components, particularly regarding constant tracking for subscriptions and so on, pricing transparency and the learning curve. So these are already very good, insights for me. Now, let's go further. It then did a competitor, product benchmarking. So what it did, it went to pipe drive's, website extracted, all the latest CRM features that pipe drive release because that is what is relevant to me. It summarized that, and finally, it summarized everything like, synthesized all this information from different subagents, summarized it and gave me like a report here. for example, the strengths, what are the pain points, current capabilities, and so on. Now, one of the questions that I often get here is, how is it different from, a workflow automation, right? So one thing here is, let's say, if had this been in a workflow automation, but if I want to rerun this process, it would always run everything from start to end. Whereas now, let's say if I am not happy with the, Trustpilot, tracking, for example, I can simply say, I would like to rerun or redo the, sentiment tracking. And what would happen here is because the manager agent here is responsible for choosing or delegating to the subagents, it would identify that only that particular subagent needs to be reactivated now. So it is only using the Trustpilot review, summarizer subagent and not rerunning the whole process. And that basically is the big difference when it comes to workflow automation because had this been like a, Zapier flow or make flow, it would have rerun the whole thing and not just one particular component of it.

Isar Meitis:

Yeah. And this connects beautifully to a question that was in the chat that said, That so far, like when you just started running this, it looks similar to deep research. How is that different? And I think you answered some components, but I wanna dive deeper into that because I think it's important for people to understand. First of all, deep research is an agent. So the biggest difference between deep research and just using chacha PT research search is exactly that concept, that it understands your question and then it says, oh, the person wants to understand this topic. What do I need to do? Which is now an autonomous thing to actually give him the information that he needs. The biggest difference between deep research and this, and there are several different differences. Difference number one is you can in advance define all these subagents and you will know exactly what it will do. Meaning in deep research, you can't control what's. Sources it will go to which one, it's not gonna go to what topics you're interested in and so on. So when you build an agent for a specific topic, like in this particular case doing competitive research, you can build it the way you want it. So think about it like a customized version of deep research. That's basically what it's doing. So that's difference number one. Difference number two is, as Puja said, you can go back and forth with specific components of this because they're standalone agents, which is not possible, or it's possible to an extent, with deep research, but it will still not be as tailored in specific as the specific agent that you develop. And number three, which what you're gonna see in a minute, this will actually go and update your CRM and do other things that obviously deep research will not do. So think about this as a. Multi-layered, multi-level, more customized version of deep research that can also then go and do stuff like write it to you in Slack or update your CRM. Anything you want to add, Puja, because I think it's an important topic for people to understand.

Pooja Jain:

Yeah, I think that summarize it beautifully. another point, human in the loop. Deep research does not have human in the loop, right? You have no control. You cannot really say, okay, there is no concept of asking for permission. I will show you in a second that as a custom AI agent, you can really, train it to ask for permissions in certain areas like where you want it to, not run on its own. Awesome. okay. Yes.

Isar Meitis:

Another question that is also I think very important and then we can continue is, there was a question about hallucinations. Is there a way to know or to reduce or to verify the information that is coming from these research agents?

Pooja Jain:

it is possible to, of course, like you can train your AI agent to ask for the sources. So for example, when I was building this agent, I was really not sure if it is getting the right information from the trustpilot. So I was checking it again and again while building it. I was always verifying, for example, the stars that it shows me here are correct, the reviews are correct or not. And the date, because I wanted to only go one month, get the reviews one month older only. So that is something I was always manually checking. I think this is a very important step. Like you have to be very cautious when you are designing your AI agent again, human in the loop. I think this is one of the most or the ultimate guardrails that can be part of your AI agents. Second, the system prompts, they're the best ways to control your AI agents. I will show you in a second where you can add your system prompts. So whenever you are designing an AI agent system, prompts are really the controllers. That is the information and, the kind of, positive prompts as well as negative prompts that you add in your ai, system prompt. They are the ones that would be controlling everything for you.

Isar Meitis:

Awesome. So I'll add my 2 cents. Yes. When I do deep research on stuff I really care about and I really need to verify the information, I usually run it on three different AI deep research tools. So think about running three different agents to do the research for you. And then I have a fourth process that actually creates a comparison table and checks. If all three have the same information, when all three have the same information, then it's very unlikely they all made up the same stuff. And so that's most likely accurate information. And when there are outliers, when only one of them finds a piece of information, the same fourth agent go and checks that information is correct. So again, now I get a second verification if the information is really there from that particular source and all the outliers are not found, are just being thrown to the trash. And I get a summary of that. So it just depends on how. Buttoned up, you need this information to be right. let's say there's 500 Trustpilot reviews. If 10 of them are made up, 15% are made up, still not a big deal, you're still getting the 500. But if you're looking on something that you're gonna make a very important business decision on, you want it to be a hundred percent accurate and not 90% accurate, and then you can add these additional layers and steps in order to dramatically increase the chances that the information is correct.

Pooja Jain:

Great point. Great. So let me show you the concept of human in the loop, which is absent on, definitely on the workflow automation because there is no way that you can add like a, Human, approval step in there, or even in the LLM chatbots, you give them a question and they answer there is no place to even ask for approval. But here it is the case. So let's say in this demo that I'm running, I am happy with the output that I have got so far. Now I want a summary of it, and I want this on my Slack channel. I have said this AI agent in a way that it does not spam my Slack channel with everything. It always asks for approval. And only when I'm happy with the output. let's see. Okay. I should not be writing please, but I'm used to. I do this,

Isar Meitis:

I do the same thing. By the way, the jury's still out on that. So those of you who don't know this whole discussion, there was a big debate last week, based on a post from several different people, including Sam Altman, on the cost of saying, please, and thank you to these chatbots. And there is inconsistency in the knowledge whether that actually makes the results better. I think the best analysis that I've seen, came out from, brain Dead. it'll come back to me in a minute, but he basically said it depends on the use case. Sometimes it helps and sometimes it doesn't. uhhuh, but I still do this because that's how I'm used to typing. And so I'm just like you.

Pooja Jain:

is this a report from Ethan Molik?

Isar Meitis:

Ethan. Ethan Molik. Yes. Thank you. Ethan Molik.

Pooja Jain:

yeah. I read it as well. It's interesting that there are a few things we cannot get rid of, which is nice as well. yeah, that's fine. They're going to be our teammates, right?

Isar Meitis:

Yeah.

Pooja Jain:

Okay, so I simply asked that, now I'm happy with the output. Now, please send me a summary on the Slack channel and as you can see it called the Slack channel. so it called the relevant account, from the Slack channel. Created a summary, a very nice summary of the key trends, vulnerabilities, pricing, transparency, and so on and so forth. And now, but it did not run on its own because this is, like I have said this pro step specifically for human approval. So only once when I click on approve, it would go to my Slack channel and send all this information. Otherwise it would not. These two steps. this single step actually probably should clarify for most people what is human in the loop first thing and second, how an AI agent differs from, say l and m chat bots, deep research or, even a workflow automation. So I would not say approve, because my Slack channel is full right now. I don't wanna open that, but I hope the concept is clear.

Isar Meitis:

yeah.

Pooja Jain:

Wonderful. I think what will be interesting,

Isar Meitis:

is to dive into what are the instructions that make these agents do it, like the actual creation of the agents. I think that's gonna be, yeah. I think the output are now hopefully clear to people. So let's dive a step deeper and show how they're actually built.

Pooja Jain:

Yeah. So let's go into the build. Great. So first let me Demo a bit about the interface that you are seeing here, and then I will go deeper into it. So what you are seeing right now is really the AI agent a as it should look, and the instructions here, as you can see, they are like super long instructions. These are the system prompts and whenever you are designing an AI agent system. Prompts are the key. Like they are the ones that are controlling everything. As I mentioned, the system prompts are the controller. So make sure first, in your system prompts, for example, to mention what would be the function of this particular AI agent. when I explain it to my audience, I always say, think of it like a very well defined job description. So you have to define what your agent should be doing. What tools does it have access to? So I already defined, you have access to industry news. So basically telling my AI agent, so as an onboarding process, who all are there in your team and when you should be calling them. That comes later. But what are your core function or your core to-dos? when you go on a website, what you should be looking for, then what you should do and what you should not do. So this, what you should not do is super important. So for example, do not assume anything. ask if something is not clear or missing, because a lot of times what I see is, let's say when I did not add this, negative prompt, it was always assuming a lot of information. Which is something I do not want when I am running it for a business process. So now adding this negative prompt made such a huge difference. So this manager agent is now coming back to me asking me what is missing? And you can add a lot of guardrails in there. So for example, if you are designing a customer chatbot, a chatbot that is talking to your customers, you can define specifically like a relevance classifier. So to classify if whatever the customers are asking this chatbot are actually relevant, and, they're not asking for a piece of recipe to, to your, I don't know, CRM chat bot, because that happens. you should be defining all this here. Second the tools. So really what, so just before we

Isar Meitis:

jump to the tools I want Yes. I wanna go back because I think it's very important what you said, Just think about defining in simple English, but in a very well structured way, all the things that you want the agents to do and all the things you do not want the agent to do. And so the more detailed you become, the better and more accurate the output is going to be, I assume. But that's an assumption that you have some kind of a template or some kind of a custom GPT that helps you write these and actually get to all the details.

Pooja Jain:

So I am actually using Entropic console for, okay. Refining my prompts. I should I demo that? How it looks like?

Isar Meitis:

if that one, why not? let's show everybody, let's show everybody the what's happening behind the magician's curtain.

Pooja Jain:

Yeah, so if you're not aware, anthropic console is really, the, what is happening in the background of cloud. Okay? Yeah. You can simply go in there, create an account, it asks for your credit card, but it is very cheap to run. But the benefit here is that it is super good with writing and refining the prompts, specifically those advanced level prompting, like chain of thought prompting or the tree of thought prompting, which is what you need when you are, designing AI agents for, complex business processes, right? So what I do is I write like a basic prompt, everything that I want this agent to do because that's, of course, like ropy cannot understand that I take that prompt. then there is a generate a prompt. You simply go in there, copy paste your prompt, and what it would do is. It would generate a very, like detailed prompt for you. and you can even say, if you want a chain of thought prompting style or three of thought, whatever you want, you can add it here.

Isar Meitis:

Awesome. So this

Pooja Jain:

is the hack.

Isar Meitis:

Yeah. This is a great hack. another thing that helps a lot when you're working on more complex stuff, is I really like using. Canvas in Chachi pt. So you can do this as step one, bring it to Chachi pt, ask you to open it as canvas. And then as you're testing the agent and something doesn't work, or it doesn't act exactly like you want, you can go back to the canvas, highlight that section and say, Hey, I'm using this as an agent, and it's doing this and that behavior. How can I change this segment of the instructions in order to prevent this behavior or to enhance this behavior or to add this functionality? And it will add it right in there in the canvas, which then makes it very easy to copy and paste it back into, whatever tool you're using. So being able to do iterative AI assisted process, I think the best tool that we have right now is Chachi PT Canvas. I agree with you that getting very detailed prompts, console from Claude is fantastic.

Pooja Jain:

it is. So Claude. Any, entropic anyways, is, Doing a wonderful job in, agent AI stuff. They're like the way they're developing them. So they are like this improving an existing prompt. the way they have fine tuned their models is really to cater to the agent ai. So this is like my go-to, portal or go to website when I want to design a system, a very good system from.

Isar Meitis:

Awesome. Cool. So we were just talking about the system from, for the agent, we're about to move to tools and explain what tools are.

Pooja Jain:

Yeah. let's say you have this new person joining your team. You have explained the job, you have explained the role. The next step there is you give this person the access to all the key systems, right? This is exactly what tools is all about. You have to think what your AI agent needs. So for that, the diagram that I described before really helps me out. like when I am starting, I am always thinking, okay, if it has to get, say the sentiment analysis, then it should go to Trustpilot or maybe Capterra or any other of these. Review website. If I want to run a social media analysis, then I have to give it access to LinkedIn. So this is the thought process. then it needs also access to my Slack channel and Adding tool is very simple. All you have to do is add it, click on add a tool. As you can see, they, like relevance and all the agent builders by now have this. But relevance for example, has access to, I don't know, tons of tool. All you have to do is select, add, link that to your account. Some of these tools they are free to use, but some of these tools they would need your API. So that depends really on your process. But yeah, you can do a lot here. as a starter, I think it never happened to me so far that a tool that I needed was not here. So I think this is a very good library of existing tools. and then once you select the tool, the very important step here is you have to define where you want this tool. when do you want this tool to run? So simply, describe this in a, how tool is described to the agent. So how does your agent understand this tool? and then the use case, of course, like there is a possibility here, I think can do it here. No, maybe I'll show it later. Okay. I'm not able to find, but yeah, there is an option here, where I can really, say, okay, can this tool run manually or does this tool need my approval to run? So that is something you can edit within the interface.

Isar Meitis:

Yeah. I'll say something important here. So it's really a two step process, right? Step number one is just connecting a third party tool, right? This could be your CRM, your ERP, your email platform, or something that's not from your company, like doing research on a specific platform and so on. And then the second thing is really explaining to the agent. How to use the tool because the fact you have access to Slack still doesn't mean that you understand what you need to do once you get into Slack. And so these are like the two different layers of creating tools for specific agents. Now, the other thing that you need to remember is depending on exactly what you're trying to do, the tools are reusable. Like you can create a tool that connects to Slack or email or ERP or CRM or whatever. That can be used by multiple agents, but you don't have to, depending on how you define the instructions, you can use it in multiple tools or just in one or however you wanna build this. You can connect to the same piece of software with different definitions of how to use them and then create, quote unquote different tools for the different agents to use.

Pooja Jain:

Yes, that is basically how these tool works. so for example, if you see like this post to Slack, I've just given it a very simple description here. So when the user approves the post, create the comprehensive summary and output of the agent in the Slack channel, that's it. That's what it needs to know. It does not have to be super long. So what needs to be very detailed is system prompts. After that, it has to be very communicative with what you want it to do.

Isar Meitis:

Fantastic. just to explain what I was saying before with this example. In this example, what this tool does is it creates a summary of whatever the input was into a short slack message, in a specific message, in a specific, channel, right? So you can use this across multiple agents, not just j that we use. If what you wanted is to post this thing on Slack, sometimes you want an agent that will respond to things on Slack, and then you'll build a different quote unquote tool. It's still connected to Slack, but the definition of how to use it will be different and it will be a different tool within your relevance environment.

Pooja Jain:

Yeah. So for example, When I, look for Slack, as you can see there is post to Slack. I mean it sees my, but there is an ad emoji reaction. There is even a separate tool for that. Yeah. Or create a new channel, send message to a Slack channel, right? You have different sub tools, let's say for the same Slack. So I think Yeah, that's a great point is platform you're

Isar Meitis:

connecting to. Yeah. For the

Pooja Jain:

same platform. Yes, for same platform. Based on what you want to do, delete messages, get the file so you can do whatever in here.

Isar Meitis:

Yeah.

Pooja Jain:

Okay. I hope this clarifies the concept of tools. So as you can see, yeah, there are different tools by the way, like it is so scalable. So since I'm running this for demo, I did not add a lot of tools. Otherwise it becomes very slow. But let's say if you want to get the funding news about your competitor, you can add a tool here that goes to Crunchbase and start getting the funding news. Same if you want to have another social media. I only added LinkedIn, but if you want to have another social media where you want to track your competitors, you can add that. So it is exactly as is I described, like Lego blocks keep on adding or keep on deleting based on your use case. Moving on, Now knowledge think of it as a brain of your agent. For this particular use case, I have not added any knowledge, but let's say if you are building a customer support AI agent, which you want to be specifically trained on your business, then knowledge plays a big part because what you have to do is make sure that it has access to your business, specific information to your website, I don't know, to your vision, mission company one pagers and so on. And as you can see, you can add knowledge in multiple formats. So PDF website, existing knowledge. The knowledge here is really the rag. So retrieval, augmented generation, that means once you have a query or once the user has a query, the LLM model really goes in there, finds the most relevant, answer, search for it, or generate, retrieves it and then generates a respons for, so that is knowledge for your AI agent. any questions here?

Isar Meitis:

no. I think that's pretty straightforward. I think people are very much understanding of this from just using LLMs, right? It's the same concept or using custom GPTs or any of these tools. It's just adding information that it will make it more specific to you versus just the generic universe.

Pooja Jain:

Yes. And the last part here is triggers. So triggers are, so for example, here I'm triggering the, or I am starting this AI agent by chatting with it. That is one way. But let's say, when you think of automation, maybe you want your AI agent to run every week, or maybe you do not want to come to the relevance AI interface, but rather trigger it via some third party. So then you can use one of these tools and use that directly. Maybe a Telegram channel, WhatsApp, these are premium, so they need really high credits. but yeah, that is a way to also invoke your AI agent. So this is, another part of it.

Isar Meitis:

Yeah, so those of you who are familiar with the Zapier and makes of the world, it's the same concept, right? An email comes in, it's the same concept, configure one agent, an email comes in from a specific topic, starts the agent. A meeting is set by a specific person, starts an agent, a message on Slack from a specific channel like each and every one of these things, the tools we use every single day. let's take our example of a research thing. You just created a new account on the CRM. As soon as it's created, it will trigger, the agents, the original logo. Go do the steps, do the research, do the thing. We'll create a summary for you in the CRM without you having to do anything in between, other than just creating, the new account. So you can think about every one of the systems you use daily as both something it collaborate with, but also as a trigger that will actually initiate the process.

Pooja Jain:

Yeah, that's a very good description now. The final part how it looks really in the AI agent interface, right? as you can see here, if you're aware of the ER and make, you know that er, and make, you have to really, tie down the tools or connect the tools with one another, and it runs in a very specific sequence, right? But here I have just given it the access to tools. they run in no particular order. for example, if my question is in a way that I want only the Trustpilot summary, it'll only run this tool. So there is no particular order. And another thing is, you have the option to actually decide. So whether this tool all runs always, or it requires an approval as I did for Slack, for example. Or you let the agent decide so you can really make a deterministic, always run this. Or you give the autonomy to your AI agent to decide, or you, add human in the loop here. Everything is doable here. So that is, I think, a very, major difference when it comes to, what I observe, when I work with me or with, for example, these AI agent builder, relevance.

Isar Meitis:

Fantastic. Puja, this was an amazing overview for beginners. I think we covered really everything people need to know to get started. Uh, Renee on LinkedIn literally said, I just signed up for a test account. I'm gonna start playing with this. So you got at least one person excited enough, and less scared of building agents to actually take action. That is wonderful. so it's fantastic and I'm sure more people will do it. There was a question earlier that I wanted to wait for the end to answer, but I think It is interesting. There are other tools out there like relevance, right? So I'm trying to see what they mentioned, like Mind Studio Lindy, and there's A bunch of others. I don't know if you just dove into relevance and that's like your universe. No. Or you play with some of the others And do you know, do you have a reason why or preferences why use relevance versus the others or not?

Pooja Jain:

No. No. So I am an AI trainer. I play with all of them. Okay. So why IT tool stack really involves relevance, Lindy and eight n and now also Zapier agents, for example.

Isar Meitis:

Yeah,

Pooja Jain:

why I chose relevance for this particular use case was because there are few benefits of relevance. They are cheap, so it's a$20 subscription every month and you get 10,000 credits, which is good enough to run such kind of use cases. Whereas when it compares to Lindy or Zapier, that is very complex, that is very, expensive to run. So they consume a lot of credits, and I think their monthly subscription is also higher than this. That is one Second is compared to NA 10, NN is very popular right now, but I personally can build a lot of NA 10 workflows. But NA 10 is still a bit more technical. So when I, when it comes to

Isar Meitis:

way more tech, way more

Pooja Jain:

technical, yeah, it is way more technical. So when it comes to training the non-technical, audience, they want something that they can see and intuitively understand. So this is why I find relevance to be slightly better, for non-technical folks. But once you get used to of, these AI agent concept, I mean you can use whatever, and it then is very, efficient in terms of price, in terms of credit consumption. You can literally run n it and for four,$4 per month. So that's the benefit of it.

Isar Meitis:

one small thing about NA 10, since you mentioned that NA 10 is an open source tool, so you can pay them to run it on their platform, which is still cheap, but for very little, you can host it on your own and then You can run it unlimited. Amount, maybe not at the highest speed, but speed is not a big deal here. Like even with what we just did, most of the agents, the speed is not critical. So you can still use a relatively cheap hosting plan, four, five,$6 a month and run as many agents as you want. And yes, instead of getting an answer in five seconds, it'll take 10, 20, 40. Who the hell cares? Like it does the work for me. I don't have to do it. and it costs me four bucks a month. So there's benefits in running NA 10, but I agree with Puja a hundred percent. It's more technical and not as simple to use as relevance as an example. yeah. Puja, if people want to know more about you, work with you, learn from you, I know you're launching a course. what are the best ways to connect with you and do more with you based on the amazing information that you have?

Pooja Jain:

Sure. So if I would love to connect with you guys on LinkedIn. I'm super active there. I always share some practical tips on AI agents and business use cases. Please connect with me. I am launching a course next week. It is called Six Week AI Revenue Accelerator, really focused on small and medium businesses and what we are going to build in these six weeks, starting from the basics to really building AI agents for content creation, lead generations SalesOps and, customer success, and personal productivity. Oh, wow. So end-to-end course. and I'm running it, in partnership with Valeria. I believe some of you who has been on this podcast

Isar Meitis:

as well, so previous guest, fantastic. Puja. Again, thank you so much. This was absolutely amazing. Thanks everybody who joined us. We had multiple people on the Zoom and on LinkedIn, and I think this is the most active chat I've seen in a long time on both platforms. So I didn't ask you all the questions. I chatted with a lot of them and just answer them, but great participation.

Pooja Jain:

Can I go and check the questions? Maybe I can answer some of them, or, do they after? No, I, all

Isar Meitis:

the stuff that I knew how to answer quickly, I didn't answer, but you can also answer them, right? they stay on LinkedIn, so you can just go there and answer the questions. I'll try my best. yeah. so thanks everybody for being with us on the live. If you're not here, you should join us. Like we do this every week, every Thursday. And at noon Eastern. I will remind you, that, our course also starts on Monday. So you have two courses to pick from and to be completely honest, it doesn't matter which one you pick, but take a course, accelerate your AI knowledge so you can do more with AI in your business and for your own career. So pick a course and go do it. It makes a very big difference in your ability to actually do the things that you need to do in a much more effective way. and that's it. Thanks everybody for joining us. Thank you again, Puja. Have an awesome thank you. Rest of your day, everyone.

Pooja Jain:

Thank you so much for having me. Bye-bye.

People on this episode

Head Shot

Isar Meitis

Host