Prompts.
Copy. Run in ChatGPT or Claude with one click. Stolen and refined from issues you should be reading.
The Agent Swarm Architect
Designs a multi-agent structure for a real task you are stuck on — with an explicit failure budget, validators kept separate from producers, and a stop rule.
The Provable Claim Auditor
Walks you through one decision you are about to trust AI with, and tells you whether it is the kind of question that can be checked against a rule, or the kind where you are trusting fluency and calling it confidence.
Is This Real?
Interviews you about a suspicious celebrity endorsement, ad, or "exclusive" article, walks you through the actual verification checks, and gives you a real/likely-fake/unconfirmed verdict — not a guess.
Design your AI verification protocol
Personal AI verification protocol designed in 5 questions, calibrated to your work, audience, and worst-case scenario.
The Two-Model Gut Check
An interview-first prompt that pressure-tests any AI answer the way an editor pressure-tests a draft — then hands you a map of exactly where two models disagree and which one to trust.
