An Illustrated Guide to AI Agents

Preface

Something remarkable happened in the years following the broad public usage of large language models (LLMs): they stopped just talking and started doing. Given a goal, a set of tools, and a bit of memory, an LLM can now search the web, write and run code, revise its own plans, and work through problems over many steps with little hand-holding. We call these systems AI agents, and they represent one of the most consequential shifts in how work gets done and how software gets built.

This book provides a comprehensive and highly visual introduction to the world of AI agents, covering both the conceptual foundations and practical applications. We start with the “brain” of today’s most powerful agents, the reasoning LLM, and then build the agent up piece by piece: memory, tools, planning, and reflection. From there we look at how agents behave as systems, how to evaluate them, and how they specialize, whether that means multiple agents collaborating, agents that can see and hear, or the coding agents that have become a staple of modern software development.

An Intuition-First Philosophy

The main goal of this book is to build intuition. The pace of development in AI agents is even more dizzying than that of the LLMs that power them. New frameworks, protocols, and architectures appear weekly, and keeping up can feel like a losing battle. Instead of chasing the latest releases, we focus on the fundamentals of agents, the components and principles that remain strikingly consistent ...