Working With the Machine
Engine Room Article 11: Prompting as Interface Design
The Real Skill: Knowing When to Stop
The most valuable prompting skill isn’t crafting better prompts. It’s recognizing when prompting isn’t the answer.
If you’re on your fifth iteration of a prompt, trying to get reliable behavior for a critical task, that’s a signal. The task might not be well-suited for current LLMs.
The most valuable prompting skill isn’t crafting better prompts. It’s recognizing when prompting isn’t the answer.
I’ve come to think of prompting less as ‘talking to AI’ and more as designing an interface between human intent and machine capability. That framing shifts what good prompting looks like.
What Tends to Work
Format specificity: ‘Return a JSON object with these fields’ eliminates ambiguity about output structure.
Examples over descriptions: Showing what you want often works better than explaining it.
Task decomposition: Breaking complex tasks into steps often improves results.
Constraints Beat Personas
Giving the model a persona (‘You are an expert marketer’) is popular. It works sometimes, but has a failure mode: the model may confidently perform the persona even outside its actual competence.
Constraints often work better than personas. ‘You are an expert’ makes the model confident; constraints help it stay appropriately scoped.
Prompting is interface design between human intent and machine capability. Be specific about format, use examples, decompose complexity - and know when a different approach is needed.
Related: 07-source—engine-room-series