Most research time goes to the unglamorous middle — the setup, the second draft, the review. The right prompt quietly takes that part off your plate.
Keep a negative list
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
- Keep one ask per prompt — chaining beats cramming
- Lower the reading level, then check what broke
Make the output reviewable
Treat the first output as a draft, not a verdict. The prompt does the typing; you keep the judgment about what ships.
- Save the prompt that worked so the next person reuses it
- Lower the reading level, then check what broke
- Name the audience and the single goal before you generate
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.