So you probably know our LLMs right. They come with all these different shapes and sizes and forms. And there's a bunch of different vendors. You have Open AI, you have Hugging Face, you having a Ollama. You have a bunch of different options to tap into this. And what those LLMs do is predict the most likely next token. What happens is if you try to chat with some of these LLMs, you're going to quickly realize that you're going to end up having like a regular prompting experience similar to one you get with ChatGPT, where you kind of got to give feedback to it to make sure that through the interactions between you and this LLM, you get the results that you need. All right, so let's use ChatGPT for a second to see how exactly does that interaction works and why. It could be better if we use it agents. So in this case, let's ask ChatGPT to help us create a marketing copy for crewAI, a platform, for building AI agents. So, in here you can see that as regular ChatGPT is going to start to write it down. What should be this copy? But it turns out to be too long. I don't necessarily want something this long. I want to make sure that it's smaller, something that I maybe use on an Instagram post or whatever it might be. So now I get the chance to provide some feedback and say like, "hey, this is too long. Let's summarize it." So once that you say that, you can see that it starts to get better. But the only reason why we can get not only GPT but in LLM to get a better results is true interaction, right? Is the interation between the user in the LLM and the feedback that you provided it that allow it to kind of correct the wrongs and get a better results. So what you quickly realize here is that through the interactions you can get a better results, but you quickly become a blocker. You got to be in there kind of like answering this questions and interacting with it in order to get good results. It's not a thing you want to do other work. It's just like enhancing you. But AI agents actually can break up that and allow you to do other work while allowing the LLM to operate autonomously. And the reason why we can do that is that because these LLMs were trained in so much text and they understand text, they create a state where they kind of have cognition. And by that, I mean that they can reasonably react. They can choose between A and B and left and right, because they can put words together in a way that makes sense. So when you achieve that state, if you can have the LLM to kind of insert some questions, an agent is born. So the agent is born when you get these LLM to basically into in their thinking process throughout it ask questions and answer the questions itself to the point that it can move on and get better by itself. So once that you get into that stage, it allows you to pass a task into this agent. And throughout this thinking process, this agent can then come up with a better answer. It's not the first answer that it would have given you, but it can then think through and optimize the answer up to the point that satisfies itself and then spits it out. But there is one thing missing here, a big component that makes this agent super powerful, and that's the ability to use tools. Other frameworks might call them SKUs or capabilities, but what they allow you to do is to your agent to interact with the external world. It allows your agent to do more things that don't necessarily would be able to do with itself. It could be calling an API, it could be posting something, it could be gathering a data point, whatever that might be. In these, this is a fully fledged agent. So let's talk real quick about what our multi-agent systems. So multi-agent systems grow on top of the agent behavior that we just described. Where instead of having just one agent, you can now can have multiple of them. So whenever you task an agent with something this agent can also task another agent with another task. And in the end you get one single final answer. But you might be wondering what are the benefits of having that instead of having one single agent? Well, I do name a few, but we're going to dig into that in further lessons. The first thing here is that you can have each agent be customized to do one single thing and do it well. You can have one agent, for example, being a researcher and another agent being a writer. So that allows your agent, that is a researcher to focus on doing one thing and making sure that it finds all the sources that check all the sources that include all the services and your writer just use that in order to create the most amazing material ever. And the other good thing is that because you have multiple agents, you can have them run from different LLMs. So you can have your researcher running on Llama-3, while your writers running on GPT-4. You can also have your own fine-tuned version model powering some of those agents. So you can see how a multi-agent systems can be so much more powerful than single agents, because allows you to get very focused agents that will be able to achieve better results than if they're trying to do everything themselves, while also tapping into this ability to use different models from different sources. And we could keep going even one step further, where you can actually say, "well, now I want to multiple multiple agents," but this is getting to meta. now I want to multiple multiple agents," but this is getting to meta. So I step back for a second and let's first build our first multi-agent systems. For all the examples in this course, we're going to be using a super powerful framework. It's called crewAI and it's open source. It's simple and it's designed for production use cases. It also offers a platform to bring your agents into production. But all the concepts that we are going to discuss here apply to all major frameworks out there. Before we jump into examples, let's talk about what is crewAI? I want to take a solid moment to describe why all of the options that we have out there. We are using crewAI on this course. crewAI is a framework and a platform. And there's a few things that it offers that makes it super easy and super meaningful for us. The first thing is, it breaks all these concepts into very simple structures. So it makes super simple for you to pick up on them. The second one is that it provides a pattern to put these systems together, so you don't need to think about how you're going to string all of this, because it already kind of offers you an opinion on that. The third thing is that it provides many tools and SKUs that are ready to be used, and we are going to use them throughout the course. The fourth one is that it gives you a module to build custom tools or agents. In some of our lessons, we're going to get to build some of those custom tools, and you're going to see how helpful that is. And also as a final touch point, it also offers a platform for bringing these agents into production. So whatever you're building throughout this course, you're going to be able to also deploy in production through the crewAI platform if you choose. So All right. So let's start looking at some of our initial building blocks. In this case, agents, tasks and crews. We're going to be diving into those and building our first multi-agent system at the beginning of our next class. So if you like what you heard so far, if you got excited about any of the examples that you mentioned, I recommend to stick around, because things are only going to get more interesting from here on. Though so much they're going to be able to build with AI agents that I promise that are going to be impressed by the end of this course. It's going to allow you to automate parts of your life, automate parts of your job. And honestly, I like a lot of potential. So I hope you stick around for our next lesson. Where we're going to actually build our first multi-agent systems ourselves. And I'm going to guide you through all the way. So thank you so much and I'll see you in the next class.