A good research prompt isn't a magic trick. It's a checklist you don't have to remember, run by something that never gets bored.
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
- Keep one ask per prompt — chaining beats cramming
- Lower the reading level, then check what broke
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.
- Save the prompt that worked so the next person reuses it
- Keep one ask per prompt — chaining beats cramming
- Ask for three angles, then cut to the one worth shipping
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.