The trap with operations prompts is asking for the finished thing. Ask for options instead, then bring your taste to the edit.
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.
- Name the audience and the single goal before you generate
- Save the prompt that worked so the next person reuses it
- Lower the reading level, then check what broke
Anchor to one reader
Write down what you never want as explicitly as what you do. The exclusions often do more work than the instructions.
Reuse the recipe
Lock the parts that never change and leave one slot for the variable. Now every run shares a family resemblance instead of starting from scratch.
- Compare two outputs instead of trusting one
- Have the model flag what it could not cover
- Keep one ask per prompt — chaining beats cramming
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.