AI Agents - The Definitive Guide
The companion code repository for the book AI Agents: The Definitive Guide, with runnable Jupyter notebooks organized by chapter covering agent architectures, planning and reasoning, memory, evaluation, security and production deployment.
This repository holds the code that accompanies the book AI Agents - The Definitive Guide. Notebooks are organized into folders by chapter, covering the progression from large language models to agents, planning and reactive architectures, multi-agent systems, advanced planning and reasoning techniques such as chain-of-thought, tree-of-thought, ReAct and hierarchical agent teams, and the models that power agents.
Later chapters cover moving a prototype into production: tool contracts and reliable execution, secure execution and tool governance, deployment in real products, foundational and customized evaluation of agentic systems, agent memory, the cost and compute trade-offs of running agents efficiently, and threat modeling for AI agents.
Every notebook can be opened and run directly in Google Colab from a link in the repository.