The trap with data work prompts is asking for the finished thing. Ask for options instead, then bring your taste to the edit.
Start with the smallest version
Write down what you never want as explicitly as what you do. The exclusions often do more work than the instructions.
- Compare two outputs instead of trusting one
- Have the model flag what it could not cover
- Keep one ask per prompt — chaining beats cramming
Anchor to one reader
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.
- Ask for three angles, then cut to the one worth shipping
- Keep one ask per prompt — chaining beats cramming
- Save the prompt that worked so the next person reuses it
Generate options, not answers
Write down what you never want as explicitly as what you do. The exclusions often do more work than the instructions.
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.