The trap with writing prompts is asking for the finished thing. Ask for options instead, then bring your taste to the edit.
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.
Generate options, not answers
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.
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.
- Save the prompt that worked so the next person reuses it
- Ask for three angles, then cut to the one worth shipping
- Lower the reading level, then check what broke
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.