Featured starting point
AI Agent Book: a study map for agent engineering
Use the open book and its experiments without confusing a reading list with a deployed agent.
Use the open book and its experiments without confusing a reading list with a deployed agent.
Featured starting point
Use the open book and its experiments without confusing a reading list with a deployed agent.
Suggested learning path
01 → 09
Use the open book and its experiments without confusing a reading list with a deployed agent.
Run one documented chapter-1 example and keep its provider and mode visible.
Manage dependencies, external checkouts and model credentials for a learning environment.
Follow messages and tool results through the chapter-1 agent loop.
Inspect the mechanisms behind the book’s first reproducibility lesson.
Avoid turning one sample or a book claim into a general performance number.
Protect keys and files, and distinguish a teaching example from a deployable service.
Choose a learning resource by the evidence you need to produce.
Turn one context lesson into a documented experiment and design decision.