Turn a vague brief into testable acceptance criteria
Makes scope and success concrete without adding imaginary requirements.
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
Makes scope and success concrete without adding imaginary requirements.
Maps fields, validation and privacy before digitising a form.
Creates a maintenance checklist without guessing a diagnosis from pixels.
Separates spoken decisions from guesses and missing steps.
Rewrites labels and error text without inventing product behaviour.
Turns visual concerns into checks for keyboard, screen reader and responsive use.
Uses a screenshot as a starting clue, not proof of the cause.
Maps data sensitivity and permissions before connecting a service.
Finds sensitive details and suggests a minimal safe sample.
Inspects a message without opening a risky destination by default.
Screens a listing for risks and proposes a safer purchase path.
Helps a jobseeker pause and verify a fee request safely.
Reviews a vacancy or recruiter message while avoiding false accusations.
Compares version markers and approvals before trusting a document.
Organises files, provenance and redactions for a human reviewer.
Explains substantive changes instead of just listing altered words.
Separates decisions, proposals and promises from casual discussion.
Produces a targeted request list instead of another broad research loop.
Surfaces conflicts in versions, figures and promises with precise citations.
Orders events without inventing dates or merging unrelated people.
Gives a short publish/hold verdict with specific verification steps.
Rewrites overconfident claims at the certainty the evidence deserves.
Turns an entrenched argument into testable evidence requirements.
Explains whether apparently conflicting sources actually answer the same question.
Need an AI worker, not one answer?
Define tools, authority, proof, persistence and safe stop conditions.