Skip to content
Atlas
Start
Back to AI agent engineering

Module 00 · Base

Foundations

How the course works and what it is pointing at, what the toolchain is and how an exercise is graded, and the completion object every later module reaches into: choices, finish_reason, tool calls and usage.

3 lessons · 2 graded exercises·1.5 hours·beginner·No prerequisites
01

How this course works

12 min
What you end up having built, how an exercise is graded, why the reference solution sits behind a deliberate click, and why nothing here calls a real model.
02

Check your setup

15 min · exercise
What the toolchain is, how an exercise is graded, and how to read a unittest failure. Then an easy exercise whose only job is to break loudly now rather than confusingly in module 4.
03

Reading a completion

25 min · exercise
The object every model call hands back, and why finish_reason rather than the text is the thing your code branches on. Truncation, tool call turns, and what token usage counts.