Track how a claim changed over time
Tests whether a statement survived newer evidence.
A growing, practical AI prompt library
Find complete prompts for real tasks, understand what each one does, replace the variables and use it immediately.
New: prompts for messy reality
Turn claims, files, screenshots and risky offers into answers you can inspect. These prompts show what AI can and cannot verify.
Copy, paste, smile
These short prompts work in a chat you already use. For personal questions, the AI should say what it actually knows, not pretend it can see your whole life.
Find your starting point
Choose a format, then explore its topics. Every prompt has its own page.
Browse the library
Tests whether a statement survived newer evidence.
Maps quotation chains instead of counting copied articles.
Treats blanks as a research question, not automatic zeros.
Designs a safe join and cardinality audit.
Makes limited tests useful without overstating confidence.
Ranks possible causes before telling a story.
Shows who was reached, who replied and what remains unknown.
Stops misleading percentages before they spread.
Creates fair arguments without false equivalence.
Makes an activity usable without specialist equipment.
Moves from taught example to a structurally different case.
Turns a room into a practical observation lesson.
Uses near-misses to reveal how understanding develops.
Drafts customer communication after something did not work.
Makes what the customer buys and does not buy obvious.
Exposes handoffs, delays and missing ownership.
Defines collaboration scope and protected information.
Maps only verifiable differences and useful gaps.
Creates a low-cost test before building an entire sales funnel.
Separates durable preferences from live operational facts.
Defines source and time budgets with meaningful stop rules.
Defines safe stop and recovery behaviours.
Cuts noisy status chatter while preserving urgent alerts.
Need an AI worker, not one answer?
Define tools, authority, proof, persistence and safe stop conditions.