Learn to build autonomous AI agents from the ground up. This course combines theoretical principles with practical application using the LangChain framework.
foundations of Agentic AIThe "what" and "why" behind AI agents and the core components that make them work
2 assuntos
The Foundations of Agentic AIWe'll start with the core theoretical concepts and a brief introduction to the tools we'll be using.
5 licoes
What is an AI Agent?Explore the concept of AI agents as autonomous systems
which can perceive their environment, make decisions
and execute actions to achieve specific goals, distinguishing them from standard chatbots.
Core Components of an Agentic SystemThis lesson breaks down the architecture of an AI agent, focusing on the core components that enable it to operate autonomously and accomplish complex tasks.
Introduction to LangChainThis lesson introduces LangChain as a powerful open-source framework for building applications with large language models. We will explore why it is a go-to choice for creating complex agentic systems.
LangChain vs. LangGraphThis lesson clarifies the key differences between the LangChain and LangGraph frameworks, helping you understand when to use each for your projects.
Building a Simple AI AgentThis is a hands-on guide to building your first AI agent. We will put the foundational concepts of LangChain into practice by creating a working agent from scratch, a process that is essential for moving toward more complex projects.
Agent Memory and Advanced ConceptsThis module will explore the capability of memory, which is essential for creating agents that can learn, adapt, and maintain a consistent context over time.
7 licoes
Memory for Agents (Conceptual)This lesson introduces the concept of memory in AI agents, explaining why it's a critical component and distinguishing between different types of memory that enable agents to have long-term awareness.
Building Agents That Never Forget (Semantic Memory)This lesson is a hands-on guide to implementing long-term, or "semantic," memory in your AI agents. You will learn how to use a vector store to give your agent a persistent knowledge base that it can retrieve information from.
Self-Improving Agents (Procedural Memory)This lesson examines procedural memory, a component of an agent's memory that enables it to acquire new skills and adjust its behaviour over time. We will discuss how an agent can remember successful or failed actions and improve its decision-making
Using Vector Stores for Long-Term MemoryThis lesson is a hands-on guide to implementing a vector store to give your agent a persistent knowledge base. You will learn how to set up, populate, and query a vector store, enabling your agent to "remember" facts beyond a single conversation
The Agent's Toolkit (Tool Calling)This lesson explains the critical concept of tool calling, a mechanism that enables an AI agent to go beyond simple text generation and interact with the real world by accessing external data and services.
Introduction to Multi-Agent SystemsThis lesson introduces the concept of a multi-agent system (MAS), where multiple specialized AI agents collaborate to solve complex problems that a single agent would struggle with.
Building A Multi-Agent System with LangGraphThis is a hands-on tutorial that will guide you through building a simple multi-agent system using LangGraph. You will learn to define agents as nodes and connect their actions using a graph to orchestrate their collaboration.
