The trap with research prompts is asking for the finished thing. Ask for options instead, then bring your taste to the edit.
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.
- Have the model flag what it could not cover
- Lower the reading level, then check what broke
- Compare two outputs instead of trusting one
Name the failure modes
Treat the first output as a draft, not a verdict. The prompt does the typing; you keep the judgment about what ships.
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.