How to Prompt.

You will learn how current Claude models follow instructions, and the five fixes that turn vague prompts into precise ones. End state is a rewritten version of your own worst prompt, tested side by side against the original. After this module you can scope outputs explicitly, cap length and format, use positive instructions and action verbs, and know when to ask for extra reasoning.

1. Understand how newer Claude models follow instructions more literally than older ones
2. Write prompts that name the scope, the format, and the length cap
3. Replace negative instructions with positive ones
4. Use action verbs and concrete success criteria
5. Know when to ask for extra reasoning and extra tool use