An Illustrated Guide to AI Agents

Chapter 1. Introduction

A Note for Early Release Readers

With Early Release ebooks, you get books in their earliest form—the author’s raw and unedited content as they write—so you can take advantage of these technologies long before the official release of these titles.

This will be the 1st chapter of the final book. Please note that the GitHub repo will be made active later on.

If you’d like to be actively involved in reviewing and commenting on this draft, please reach out to the editor at [e-mail].

In the mid-2020s, AI agents began reshaping the AI landscape as we knew it. When ChatGPT, at the end of 2022, revolutionized the field of large language models (LLMs), AI agents started taking a major step further and were designed to act with autonomy, pursue goals, and even interact with the world. Rather than just generating text, these agents are capable of solving much more challenging problems using advanced reasoning, memorizing complex interactions, and creating entire codebases.

This shift is monumental and not just an incremental improvement. It redefines how we interact with AI. Where LLMs require significant handholding, AI agents are capable of autonomously deciding which actions to take, when to take them, and even how. It’s this agency that makes them such interesting entities and will be a core focus throughout this book.

This book covers AI agents that rely on LLMs. It’s important to note that there are other types of AI agents in practice that do not ...