Welcome to Unit 2. In Unit 1 you built a mental model of what GenAI is and where it fails. Now you start using it effectively.

In Module 1.1 you learned that all three tools — ChatGPT, Claude, and Gemini — are built on Large Language Models that predict the next word. So if they all work the same way under the hood, why does it matter which one you use?

You have already been using role prompting since Module 2.1 — every time you wrote “You are a senior Python developer…” at the start of a prompt, that was role prompting. This module goes deeper: what exactly makes a role effective, when it genuinely improves output, and — critically — when it can actually hurt the quality of your results.

This is the final module of Unit 2 — and the most practical one. You now have three modules of prompt engineering theory behind you. This module is about what goes wrong when you apply it, and how to fix it fast.