198 | Build a Business-Boosting AI Agent That Books Calls While You Sleep-No Code w/ Carolina Posma

0:00Hello, and welcome to another live episode of the Leveraging AI podcast, the podcast that shares practical, ethical ways to improve efficiency, grow your business, grow your business, and advance your career. This is Isar Maitis, your host, and we have an amazing session for you today. We've been talking a lot about agents, both in previous episodes as well as on the news, like agents, and now everybody's interested in agents. Everybody wants to build agents. Everybody wants to know what agents can do for them. And the reality is most people don't have a clue how to do that, how to get started, which platforms to use, and so on.

0:28And this is exactly what we're going to tackle today. And we're going to demystify the whole concept of creating agents. We're going to show you exactly how to build an agent that you can actually use that will be very useful for probably most companies in the world today, big or small. So what are we going to build? We're going to build an agent that will learn everything about your company just by looking at your website and we'll be able to answer questions on that website to, well, wherever you want to place it. For a demo today, we're going to place that on Instagram. So we're going to build an agent that will be able to answer DMs on Instagram based on information from the website.

0:57You obviously can build it and connect it to any other thing, like place it on your own website and so on. And the cool thing is you'll see that the agentic universe, while this sounds complicated, it actually really easy. And we'll do all of that within the next 30 to 40 minutes, which is incredible when you, again, most people think that it's really hard and really complicated, and you got to have an army of coders to do this. The reality is it's not. And we're going to do this with the help of Carolina Posma, who is our guest today. She is an expert on doing this. She has her own agency helping companies do exactly that.

1:26She is a advisor, like an external promoter of Flowgent, which is one of the most commonly used platforms today to develop agents. And this is the platform we're going to use today to show that to you. Her background is in marketing and in entrepreneurship. She's been in multiple marketing roles across multiple companies, including several of her own. So she understands business, she understands entrepreneurship, and she understands agents, which makes her the perfect guest to share with us her information about this. So I'm really excited about this one. Carolina, welcome to Leveraging AI. In the next few years, AI technology will change our world dramatically.

2:04Whether you are a business executive trying to catapult your business forward, or just somebody who refuses to be left behind and want to advance your career, this is the show for you. I'm your host, Isar Maitis, a serial entrepreneur and an AI enthusiast. You'll hear invaluable practical tips from innovative business leaders, AI practitioners, and some of the brightest AI minds in our world today on how you can leverage AI in ethical ways to advance your career and grow your business.

2:39Thank you so much, Isar, and thank you for this very kind introduction. So what I want to show to you today is indeed how you can build an easy and Instagram AI DM appointment center. So you already mentioned it in your description, Isar, an AI agent that does sales for you on AltePype, right? So that's what we're going to explore today. So indeed, I think about me. So yes. No, I'm saying that's amazing. I think it's very exciting. I just want to, first of all, thank everybody in the audience. The people are joining us live, whether on LinkedIn and or on Zoom. So thank you so much for being here.

3:12If you have, first of all, go ahead and introduce yourself. So where you are, what's your experience with agents. So we have a little idea of who's in the audience. And if you're not in the audience, then know that we do this every single Thursday at noon p.m. Eastern. You can come and join us and then you can ask questions. You can chat with the people in the chat. You can network and so on. Also, I want to mention one last thing. If you want to learn more in depth on how to leverage AI in your business, there are two ways we can help you with that. One is we have the AI Business Transformation course, which we have been teaching for over two years.

3:40The next session opens on the second week of August. It's a four-week course, two hours a week, that will give you an incredible level of understanding in AI and how to apply it in your business, whether you're just a business person or you're in a leadership position in a company. In both cases, it will give you an incredible boost to your understanding of AI. The other thing is we work with companies on custom tailored workshops to help businesses accelerate very quickly into the AI era. We do this either in person or online, depending on the setup of the company. So if you're interested in any of those, just look for the links in the show notes or just connect with me on LinkedIn and ask me whatever you want to ask me.

4:14And now let's dive into agents and let Carolina lead the conversation. Carolina, it's your stage for now. Yes, thank you so much. So let's talk a little bit first about the difference between CheckGPT, AI automations, and AI agents. If you are a frequent listener, you might already know the difference, but I always like to go back to basics to just get everyone on the same page. So I will share a couple of slides first where we will discuss this. So let's get started first a little bit on the difference between CheckGPT, AI automations, and AI agents, because today we're going to talk about AI agents and we're going to create our own AI agents as well.

4:51But as I said before, it's always very useful to get a little bit back to basics on what are we actually talking about. So first, where do we stand now in the world of AI? Many people have already probably seen this leaked note from the Shopify CEO telling us that, telling all his employees that before asking for more headcount and resources, teams must demonstrate why they cannot get what they want done using AI. So this already emphasizes the importance that huge companies lay on understanding AI and using AI and knowing how to get things done using autonomous AI agents, as it's mentioned over here.

5:26Then we have companies such as Gumboop that are only with four persons and that's raising 17 million in dollars. So they're building, as they claim, the first 10 person, 1 billion company. And we have companies looking for AI-first talent only, and you have to automate your job as you go. And even further, there are companies like Firefrog who are currently hiring AI agents. So they're not even looking for people to build AI agents. No, they have job vacancies for AI agents open. And the great news here is that we are still in the very much beginning and the people who adopt this technology right now will win, just like in the previous sense, like internet, smartphone, those are very disruptive, just like AI agents.

6:07And when we're talking about AI agents, the first thing that you need to grasp a little bit is chat-up-y. I am assuming that everyone right here has played around with chat GPT already, has had a conversation already with chat GPT, but a lot of people are calling chat GPT an AI assistant. And this is where I want to get started because in my opinion, chat GPT is just an AI advisor because chat GPT is brilliant to get advice, to brainstorm ideas, to create content that will help you when you're stuck in anything. Chat GPT is your personal advice that you can ask anything. But one of the problems of with JGPT is it can't really do anything.

6:42Yes, if you're very advanced with JGPT, you may be aware of custom GPTs, but in general, JGPT doesn't do anything. Then we get onto automations. And automations was already possible for a very long time. Let's take this super straightforward automation example where you're connecting two different tools. Let's say you have a lead form on your website and people can leave their information over there, first name, last name, and you want to have that edit tool, for example, your CRM such as HubSpot, Pipedrive, or any other CRM, you can do that using tools like Zapier, Make, and N8M tools that were there for years already.

7:20So putting this information from one side to the other side was already possible for years, years, years. But why is there all the hype suddenly about AI automations, or AI automations, let's say? So process automations, as we know, they've completely changed with the introduction of better, cost-friendly and accessible AI. In 2022, the API of GTT 3.5 became available, and suddenly AI wasn't anymore just for the big corporates with huge budgets. No, it was for all of us, for you, me, everyone who is open to play around with AI, even as an individual. And what we were seeing was that AI was getting so much more smarter, and at the same time so much more cheaper.

8:00So it became more and more and more available. And what does AI now allows us to do to do in these process automations? Well, it allows us to interpret information, to summarize information, to turn unstructured information into structured data. So what do I mean by that? Let's say, for example, that you have someone sending in a resume or a CV. It can be sent in a PDF, and that's a huge bulk of unstructured information. The name can be anywhere on the PDF, right? But with AI, it can read that information, and it can take out, for example, oh, this is the first name, this is the last name. It can turn unstructured information into structured data, That's so powerful and can create new content.

8:37So there's so much that you can do with AI right now. And when we take a look at our example, and please interrupt me if you have any questions, but if we are looking at this example from the lead form to name email website to your HubSpot pipeline, suddenly you could start doing stuff with that information. So with introduction of AI, you can summarize the website, for example. You can give some qualification criteria to AI and have to judge if this is a qualified lead. or perhaps you have a sales team that pick up the phone for everyone who is filling in that lead form and the AI or an AI can help you create a call script for that salesperson, right?

9:15So there's so much that you can do with AI. You can interpret information, instruct information into structured data. It's changed the world. So right now we discussed ChatGPT, which is your personal advisor to ask questions, get help. Then we have automations. And the old school automations help you to stop copy-pasting info and doing the same boring tasks. It helps you to connect different softwares and tools with each other. And then since a couple of years, we have AI automations. And that's making your automation smarter with AI, summarizing it, interpreting it. But something new in the last couple of months, a year, happened.

9:52And that is AI agents. And this is even a step further. So let's move on to the AI agents. you can think of AI agents as chat GPT but it doesn't just chat it takes action so you can train an AI agent for example on your company's knowledge and you can plug it into different tools it can book meetings it can update CRM records it can send messages it gets real work done and before we dive into AI agents and how to build it's without if you don't know have any tech knowledge at all because like Isa said you don't need to be able to code no you can really there are software that allow you to just plug and play with AI agents.

10:30There's something that you first need to know where we stand with AI agents right now. And what I'm showing you on the screen right now is the triangle of tenants. And in this triangle of tenants, you see a triangle, it looks a little bit like the social hierarchy, of different levels that employees can have. And level one is the lowest level that's useless. And that's someone, if you tell them what to do, they rarely do it right. If we go one level up, we're talking about task monkeys. for those employees persons you tell them what to do and how to do it and when to do it and it will get done then we have a third level of talent which is problem solver tell them what to do and they figure out the how the fourth level of talent is systems thinker tell them and i do see that the credits actually are missing this is shared by sean puri on twitter the fourth level is systems thinker.

11:21Tell them the problem. They set a system to figure it out, people, plus process. And level five is a superstar. They identify the right problem and get it solved. So where are AI agents? I want to pause you just for one second to add two things. One, to do a quick summary of the great intro you did of the differences between AI and agents and automations. And I think most people are still struggling with that. So I think that was great. The biggest differences between agents and just AI large language models is, like I said, they can take action. The second thing is they can figure out their own steps.

11:48Like if you want to do a multi-step process with AI large language model, you've got to tell it what the steps that it needs to do, even though the reasoning models solved it partially, but only partially. And the agents know kind of how to think for themselves. You give them the goal, they figure out the steps versus you have to take them the steps. And number three is they know how to work collaboratively with other agents. You can build a hierarchy of agents that can talk to one another. When it's LLM, it's just that one LLM. So this is kind of like a quick summary and my two cents to add to that.

12:14On what you just said about the talent, there was a very interesting interview with Sam Altman this past week at the keynote of Snowflake, the big data company. And when he was asked about what he's excited about, that's probably coming in the next year, so the next 12 months, he basically thinks that the biggest thing is that AI will be able to solve really big, really complex business problems that we are either unable to, or it takes us a huge amount of effort to solve just by giving them more compute. So he's basically saying what you're talking about right now, that we're going to go from level two to level four, maybe five, by just giving it access to the right data and just paying for a lot more tokens.

12:52But then it will know what to do. And if you can solve a really big problem for a really big company, that might be worth tens of millions, hundreds of millions, billions, depending on how big the company is. So saying, okay, I'm going to throw$2 million worth of compute at this makes perfect sense in those scenarios. And so just to give you a broader idea where we are, where we're going, this is kind of where we are. And I'll let you continue on where we are right now. Yeah, that's amazing. I don't know. It's sometimes so... It's honestly also a little bit scary because if an AI agent already can go to level four at the Systems Think or level five as superstar, I think that's brilliant when we get there.

13:29But also, I'm so curious on how the world will look like by then on what will change because so much is going to change. But at the moment, I think right now, AI agents are still, most of them are still task monkeys. I do know that some companies are playing around with problem solvers already, but the most AI agents that you, for example, would create in softwares that you see often around, like, for example, and are still task monkeys. You need to tell them what to do, how to do it, and when to do it, and then your AI agent will get it done every single time if you instruct it correct.

14:04So with that in mind, in my experience, there are two big use cases for AI agents right now. AI agents can really well connect with your leads or customers via, you often hear the voice, so via calling, via messages, for example, on Instagram, like we're discussing today, but also in website chats or on WhatsApp, for example. So AI agents are great right now to really get the conversation going with customers and leads, like a sales employee or like a customer support employee. That's one use case. And the other use case is a personal company assistant doing different stuff in the background, more like an automation plus.

14:41For example, doing some research for you every time a lead is coming in or, let's say, creating content for you, doing research on that. So that is another big use case. If you are not technical at all, or at least consider yourself to be a non-technical person, there are three software tools that I can recommend you to get started with AI agents. And these software tools are for your personal company assistants are Zapier. I think they have a really good super user and beginner friendly personal company assistant AI agent builder relay app. I think I really like them in the sense that they have a lot of pre-built AI agents already for you.

15:20So you can just plug and play also for the personal company assistance. And if you are looking for an AI agent builder that allows you to create AI agents that can connect with your leads on Instagram, WhatsApp, on your website, then I highly recommend FlowGens.ai, where I'm also involved as an advisor. So let's take a look at some examples that we can create using an AI agent that can connect with your leads or customers. So like I mentioned, the lead generation on your website, Instagram BM AI agent, but also, for example, customer support for e-commerce stores. Connect your AI agent with your Shopify and have it search for products and have it update order status or request order status when people are asking for it.

15:59Or, for example, an AI coach trained on your course, if you're a consultant or if you're running a course. imagine that people can chat with your AI coach person on WhatsApp or in Slack for example and you are giving your students or clients 24-7 advice or let's say for example customer support or sales on WhatsApp for events I think if you're running a huge conference maybe you can start reaching out to everyone on WhatsApp with the newest updates and if people are have questions about where do I park or who are the keynote speakers or anything like that an AI agent can answer that easily right now.

16:36So just to recap what I showed you here and what I discussed here, we went from Catchy PT, which is a personal advisor, to automations, to AI automations, and we discussed two different types of AI agents, the sales or customer support employee or the personal assistant. Any questions so far? No, I think this is fantastic. I don't see any questions in the audience, people saying that it's interesting and that it's awesome. So I guess you're on the right track.

17:06I see that Neida has the second brain assistant built on make.com. That's amazing. Okay, let's move on then to actually creating our AI agency. I am going to hide. Let me see if I can hide this. Hide video. Yes, because then I can actually see what I'm doing. So if you want to walk through this together with me, you are welcome to do it because, well, I'm going to build this live. Always nervous for the live demo, so I hope everything goes well, but I will show you how to do it. So where we're going to build our, what we're going to build is an Instagram AI agent that can answer any questions on your Instagram DMs.

17:44So let's say that you have a lot of followers on Instagram as a company or you're an influencer, then this is a brilliant use case to try and add an AI agent to it. So where we're to build this is flowchance.ai. That is like flow and agent combined for them without the A in middle, flowchance. And on the flowchance project, you can click on get started for free. And then you can add your email address or click on continue with Google. And then you will get on the page that is the onboarding form. Like every software, there's an onboarding form. And there you can tell what should we call you. Well, Carolina.

18:17We're going to build an AI agent for multiply today. then Confidenceizer will just keep these in one to 10, and we will continue. So next, where did you find us? Referral. What's the use case? Instagram AI agents, but you can, within any use cases, will of course help the team of flowchains to build their software better for you. So, and this is where the magic is going to happen, because what's going to happen right now is if you fill in your website over here, and we're going to do this with ESA's website, if you fill in your website over here, in the background, an AI or the website will be scraped and an AI agent will be trained, so to say.

19:02So it will be added as knowledge and a prompt will be generated on your website. So you don't need to have any text skills for this. You can just fill in your website and automatically it will be trained. So we're building your agent now. And in the same time, you are going to be guided through the app. So I will just quickly go through that. So the credits, dashboards. If you are doing this on your own, you can easily read it. But you have a Chef Manager. You can have different agents. You can connect with different integrations and settings. Now click on Agents and click on Agents Overview. Then you can open it to see your first agent.

19:41But the agent is, at the moment, still being built. And this is your agent's playground. So once the agent is ready, we can play around with the agent and we can chat with it. In the meantime, let's say, look, you can edit to your website. Here to edit your agent. And we will take a look at how to edit your agent. So what we will see in a couple of minutes is the agent, the system prompts being filled in. So for every agent, the system prompts are the instructions that you can explain to the agent on how to behave. So you can really think of it as the introduction or the onboarding guide for any of your employees.

20:16in your onboarding guide, you also tell how someone should behave or what someone should do or what's expected in what cases. And that's the same for the system prompt. So remember that the system prompt is really the heart and the brains as well of your AI agent, because you're telling it its personality, you're telling it the way it should behave, which actions it should take, and all in plain English. So this is really the same as chatting with chat GPT, but then and you're explaining it to your AI agent on how to behave. The next part of every AI agent is that an AI agent should have... Before you continue, just to talk about the system prompt.

20:50And I think you framed it perfectly, right? It's the onboarding and the training of a new employee, right? But it covers more than that, just like you said, because it also covers personality. It also covers how you're going to answer it. Do you want to be brief? Do you want to be detailed? If you are detailed, how detailed do you want to be? What's the format of your answers? Every one of those things, you can customize and define for the agent exactly how to behave and different than the average employee. It's actually going to follow these instructions exactly how you tell them. So if you, my question to you though, Carolina, is does Flowgent or do you have a different resource of all the different topics that should be in a system prompt?

21:28Like what, in order to make sure you're not missing anything important, do they guide you through these different things or do you look for that on YouTube and start there? you will see it in a couple of minutes but Flowchants right now because I filled in the website Flowchants has the system prompt created automatically with AI so they have a team of AI agents in the background that go to your website and create a system prompt automatically so the rough draft of the system prompt is already there which makes it more easy to get started with from there on you can make any changes things that I would include and always and this is something that I'm going to share now as well, is always define the role of the of the AI agent.

22:14So who is he or she or it or I don't know how to define it, but who are they? So is it a personal assistant? Is it a sales employee? Is it an appointment setter? Is it a customer support employee? This already sets the stage first for your AI agent on how it should behave in the rest of the conversation. So the role. Then always define, indeed, you mentioned it already as well, the goal. So what's the goal of the AI agent? For a lead generation AI agent, you want maybe to collect email addresses. Or for a customer support AI agent, the goal is to help the customer as best as possible to solve its problems.

22:53Then I always recommend to include the standard operating procedure, but you can name it a different way. You can name it, for example, you can say it's a task or the standard operating procedure or the workflow or anything like that. But there you define usually on what steps it should take if you want it to take certain steps. So for example, for a lead generation AI agent, sometimes you don't want it to have certain steps and you just want to go with the flow and really follow the conversation. But sometimes you want the AI agent to first ask a couple of questions that are, for example, qualifying and then go with the flow.

23:25And that's all stuff that you can also define as well. Tone of voice, examples. So this is a little hack that I always use, but I love to add examples to the system because it makes it very clear for the AI agent how to behave. But what I usually do for that is screenshot a couple of old conversations that are already done by a human, and then put that in ChatGPT, ask ChatGPT to transcribe those screenshots, and then put it in the agent user set or user structure. And then you already have some conversations that you can add as an example as well to the AI agent. And what AI, of course, does is the whole goal of an LM or AI is to predict your dream outcome based on the information that you are providing.