Most writing time goes to the unglamorous middle — the setup, the second draft, the review. The right prompt quietly takes that part off your plate.
Reuse the recipe
Write down what you never want as explicitly as what you do. The exclusions often do more work than the instructions.
Make the output reviewable
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.
- Have the model flag what it could not cover
- Compare two outputs instead of trusting one
- Name the audience and the single goal before you generate
Name the failure modes
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
- Keep one ask per prompt — chaining beats cramming
- Have the model flag what it could not cover
Treat the first output as a draft, not a verdict. The prompt does the typing; you keep the judgment about what ships.