CourseAgentic AI Engineer: The Complete Course · Module 13: Evaluation · part 72 of 97

Part 72 · Module 13: Evaluation

Module 13: Evaluation

1 min read·13 Oct 2026

What you need first

Module 3: the eight tools, make_failure_safe_tools and call in returns_desk/tools.py.
Module 5: the agent loop and scripted stand-in models.
Module 12: the controls the red-team suite tests (recommended).
Python dictionaries, hashing with hashlib, and running a command from a terminal.

This course is bought on its own, once, and stays readable afterwards, including the parts added to it later.