You don't need a hundred data work prompts. You need five you trust and actually reuse.
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.
Keep a negative list
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
- Ask for three angles, then cut to the one worth shipping
- Name the audience and the single goal before you generate
Start with the smallest version
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 the reasoning, then the result. When the model shows its steps you can see exactly where to push back.