You don't need a hundred support prompts. You need five you trust and actually reuse.
Start with the smallest version
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.
- Keep one ask per prompt — chaining beats cramming
- Save the prompt that worked so the next person reuses it
- Name the audience and the single goal before you generate
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.
- Compare two outputs instead of trusting one
- Have the model flag what it could not cover
- Name the audience and the single goal before you generate
Generate options, not answers
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.