Protocol
Write your rationale before asking AI for a recommendation
Give the model something to extend before you give it permission to steer.
When it fits
- You face a complex decision and asking for an AI recommendation first could anchor the rest of your thinking.
When to avoid it
- For unfamiliar domains, your initial rationale may be weak; the exercise preserves ownership but does not make your premises correct.
Why it matters
Write your current options, reasons, constraints and uncertainty before asking AI for help. Then provide that rationale and ask the model to identify missing considerations, tensions or implications. This preserves your decision model as an inspectable object and makes AI support easier to compare with your own thinking.
Steps
- You can identify what the AI added or challenged because your pre-AI rationale still exists.
An example
Before asking AI whether to buy a tool, write the actual workflow, compatibility constraints and exit costs, then ask what you may have missed.
Check your result
You can identify what the AI added or challenged because your pre-AI rationale still exists.
Keep this limit in mind
- For unfamiliar domains, your initial rationale may be weak; the exercise preserves ownership but does not make your premises correct.
Connected ideas
Use beforeAsk AI to extend the reasoning, not only answer it
Evidence and sources
The ExtendAI study found that AI support built on participants' own rationales integrated better into their decision process and produced slightly better outcomes than a recommendation-centric condition in the tested task.
The study involved one complex investment decision task and does not establish that rationale-first AI is always superior.
AI, Help Me Think—but for Myself: Assisting People in Complex Decision-Making by Providing Different Kinds of Cognitive Support · Abstract results