Explore a tabletop continent without leaving your chair
Makes a guided expedition from three supplied objects.
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 a guided expedition from three supplied objects.
Gives a shelved idea a playful, reversible send-off.
Adds one handmade paper boat to a visible puddle while leaving the person and street on the original photo plate.
Turns a stressful search into a bounded, reversible location checklist.
Describes a verified stop layout and next action without guessing service status.
Tests whether wording and response-option changes make survey results incomparable over time.
Converts marketing wording into measurable conditions and failure criteria.
Extracts inputs, steps and missing details needed to repeat a study.
Tests eligibility and fit with direct evidence and open questions.
Builds specific catalogue queries and a provenance capture sheet.
Finds substantive changes and marks interpretation for expert review.
Defines a non-production restore rehearsal with integrity checks.
Traces call sites, data variants and rollout assumptions first.
Designs exit codes and messages for predictable failure handling.
Maps API changes, lockfile effects and rollback for a package update.
Defines replay order, idempotency and user-facing conflict states.
Generates cases for timezone, daylight and period-edge behaviour.
Specifies identity keys, partial-failure behaviour and tests.
Maps a proposed config diff to environments, defaults and rollback.
Separates exact matches, plausible matches and risky false positives.
Exposes non-comparable areas before producing a trend map.
Creates a transparent themebook with counts and counterexamples.
Breaks forecast performance into meaningful segments and horizons.
Tests randomisation balance, exposure and exclusions independently of results.
Need an AI worker, not one answer?
Define tools, authority, proof, persistence and safe stop conditions.