The trap with support prompts is asking for the finished thing. Ask for options instead, then bring your taste to the edit.
Name the failure modes
Treat the first output as a draft, not a verdict. The prompt does the typing; you keep the judgment about what ships.
- Name the audience and the single goal before you generate
- Have the model flag what it could not cover
- Keep one ask per prompt — chaining beats cramming
Anchor to one reader
Treat the first output as a draft, not a verdict. The prompt does the typing; you keep the judgment about what ships.
- Lower the reading level, then check what broke
- Have the model flag what it could not cover
- Compare two outputs instead of trusting one
Reuse the recipe
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.