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.
Start with the smallest version
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
Cut before you polish
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.
- Lower the reading level, then check what broke
- Save the prompt that worked so the next person reuses it
- Compare two outputs instead of trusting one
Write down what you never want as explicitly as what you do. The exclusions often do more work than the instructions.