Sample translated content for drift
Routes meaning problems to fluent reviewers.
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
Routes meaning problems to fluent reviewers.
Flags records for accountable human decisions.
Reports meaningful page differences without editing the site.
Keeps unknown files from becoming trusted instructions.
Makes units, nulls and ownership explicit.
Checks quality without inspecting every record.
Shows how display choices affect interpretation.
Detects impossible paths before conversion analysis.
Uses context and measurement checks before exclusion.
Keeps missing matches visible instead of dropping them.
Balances local insight against re-identification risk.
Finds extreme influence and unsupported population claims.
Shows what changed when labels were consolidated.
Prevents double counting across files.
Checks which files and settings are truly owned.
Prevents order-dependent false confidence.
Finds where text changes encoding.
Ensures preview cannot hide dangerous differences.
Maps mutations to exact stale views.
Treats cell text as untrusted data.
Protects clients from skipped or repeated records.
Inspects inputs before blaming the compiler.
Tests specific error paths for sensitive output.
Finds paths that reach data before authorisation.
Need an AI worker, not one answer?
Define tools, authority, proof, persistence and safe stop conditions.