The trap with writing prompts is asking for the finished thing. Ask for options instead, then bring your taste to the edit.
Make the output reviewable
Write down what you never want as explicitly as what you do. The exclusions often do more work than the instructions.
- Name the audience and the single goal before you generate
- Compare two outputs instead of trusting one
- Save the prompt that worked so the next person reuses it
Name the failure modes
Write down what you never want as explicitly as what you do. The exclusions often do more work than the instructions.
- Keep one ask per prompt — chaining beats cramming
- Lower the reading level, then check what broke
- Compare two outputs instead of trusting one
Keep a negative list
Treat the first output as a draft, not a verdict. The prompt does the typing; you keep the judgment about what ships.
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.