Using AI as Your Plan's Devil's Advocate
Before executing a major decision, ask AI to attack your plan with the strongest possible arguments — not politely agree with it.
Goal
Surface plan weaknesses before execution through structured opposition, instead of settling for the model's default polite agreement.
Steps
-
1
Explain your full plan to AI neutrally, without asking for an opinion yet.
Expected Outcome
Evidence base
School: Decision Making / Structured Dissent
Founders: Irving Janis (Groupthink) · Anthropic Research Team (1972)
Irving Janis's "Groupthink" 1972 recommends a formal devil's-advocate role to break false consensus. Anthropic's research on sycophancy shows models default toward agreement, requiring an explicit opposing prompt.
Keywords
Frequently asked questions
How long does "Using AI as Your Plan's Devil's Advocate" take?
When will I notice the effect of "Using AI as Your Plan's Devil's Advocate"?
Is "Using AI as Your Plan's Devil's Advocate" evidence-based?
Is "Using AI as Your Plan's Devil's Advocate" suitable for beginners?
Subscribe for full access
Subscribe to Plus for full access to this practice and the whole catalogue, or try first — free, no sign-in, no commitment.
7 complete practices (one per domain) are free forever, no sign-in.