Use with ChatGPT Search to get better search results Red-Team My Assumption
My assumption: “[ASSUMPTION]”. Search for the strongest counter-evidence from the last 18 months. Summarize risks if I’m wrong and the lowest-cost test to check.
Co-founder of Prompt Magic and ThinkingDeeply.ai Career Chief Marketing Officer
Build your personal prompt library, save your favorites, and access curated AI prompts created by the community
Access a vast library of high-quality AI prompts for every use case
Save prompts to your personal library and organize them your way
Get started with full access to our core features at no cost
No credit card required • Free forever • Join 10,000+ users
Spot the invisible beliefs holding your idea together. Identify hidden assumptions. Test their strength. Suggest how to validate or challenge them.
Most AI outputs default to the safest, mainstream summary. Deep Truth Mode is a forensic prompt protocol that forces the model to (1) steel-man the mainstream view, (2) steel-man the best dissenting view using primary evidence, (3) generate a third hybrid hypothesis, then (4) aggressively red-team all three and keep only what survives. It is not a truth machine. It is a structured way to reduce consensus autopilot, surface missing data, and produce a clear what-would-change-my-mind test plan.
This prompt helps bridge the gap between intuition and logic when you have a strong gut feeling. It seeks to validate your instinct by finding supporting data, identifying historical patterns, and framing the decision as an asymmetric bet.
Perplexity Max just added Model Council: you ask once, three frontier models answer (ex: Claude Opus 4.6, GPT-5.2, Gemini 3.1 Pro), and a separate synthesizer compares them, shows where they agree vs disagree, then delivers a cleaner final answer. It’s built for anyone who’s tired of running the same prompt in three tabs and manually reconciling contradictions.
Give the model three lenses—investigator → critic → decider. You’ll get answers that are deeper, less biased, and immediately actionable.
This prompt forces you to critically evaluate a plan by having the AI act as a skeptical board member. It aims to expose core assumptions, logical weaknesses, and potential points of complete failure without offering solutions.