Lesson 18: Reviewing AI Code and Challenging the Model (Teach This Topic)
This guide supports teaching learners to review AI-generated code and the behaviour of the agent that produced it. It focuses on diffs, requirements, architecture, security, omissions, adversarial questions and honest reporting. No coding tools or live repository are needed: all examples and activities are supplied here. The key principle is that working code and passing tests provide evidence, but do not automatically justify approval.
