Separate AI's recommendations from the decisions I must own
Sorts an AI answer into what you can accept, what you must check, and what you must decide yourself, with the questions to settle each.
The prompt
I have an AI-generated analysis or recommendation. Help me separate what I can accept from what I must decide myself.
The AI output: [PASTE]
The decision or work it feeds into: [DETAILS]
My role and accountability: [what I am answerable for, to whom]
Stakeholders affected: [WHO]
Go through the output and classify every recommendation, conclusion, or judgment into:
- Accept - routine, low-risk, and easy to verify (e.g. formatting, a summary of my own notes).
- Check, then accept - factual or analytical points I should confirm first. Say how.
- I decide - choices involving trade-offs, priorities, values, people, risk appetite, or commitments on behalf of others. AI can inform these but should not settle them.
Return:
1. A table: Point from the AI output (short quote) | Category | Why | What I need to do.
2. For each "I decide" item: the real choice in one line, the options, what the AI may be missing (context, politics, history, values), and 2-3 questions to settle it.
3. Any place where the AI stated a judgment as if it were fact.
4. A short note I could add when I share the work, making clear which parts are AI-assisted analysis and which are my decisions.
Do not make the decisions for me. Lay them out clearly so I can own them.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Working with AI prompts
What to fill in
- PASTE
- DETAILS
- what I am answerable for, to whom
- WHO
How this prompt is built
This prompt follows the RTF structure (Role, Task, Format). RTF tells the model who to be, what to do and what shape the answer should take. It is the quickest structure that still gives noticeably better results than a bare request.
Related prompts
- Reverse-engineer the prompt behind an outputWorks backwards from text, code, or an image to the prompt that likely produced it.
- List the ways an AI agent could fail and how to prevent eachA failure-mode review for an AI agent: realistic scenarios, how you would notice, the damage, and the safeguard.
- Answer my question, then critique it and argue against itGets an answer, an honest self-critique, the strongest counterargument, and a revised answer you can trust more.
- Turn a one-off AI chat into a reusable prompt pack for my teamExtracts the prompts, fixes, and checks from an AI chat that worked into a step-by-step workflow and prompt pack colleagues can reuse.