A good support prompt isn't a magic trick. It's a checklist you don't have to remember, run by something that never gets bored.
Make the output reviewable
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
- Keep one ask per prompt — chaining beats cramming
- Have the model flag what it could not cover
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.
- Compare two outputs instead of trusting one
- Have the model flag what it could not cover
- Name the audience and the single goal before you generate
Keep a negative list
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.
- Lower the reading level, then check what broke
- Ask for three angles, then cut to the one worth shipping
- Compare two outputs instead of trusting one
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.