A tiny crew works around the real me
Stages a task-focused miniature work crew around a real portrait, distinct from a toy parade.
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
Stages a task-focused miniature work crew around a real portrait, distinct from a toy parade.
Designs instructions usable without constant data, apps or account access.
Turns a source into a clear public explainer while preserving dates and caveats.
Finds unintended changes to identity, text, products and important details.
Writes an edit brief with explicit identity and content preservation.
Uses explain-back and targeted corrections instead of another lecture.
Compares prompt versions using the same examples and explicit scoring.
Keeps the task contract stable while respecting different tools and limits.
Designs a useful explorable experience before anyone builds it.
Builds three genuinely different executions instead of repeating a slogan.
Compares draft assets with an approved style guide and shows specific fixes.
Turns existing work into a reusable voice and visual system without cloning others.
Makes essential information usable on a basic phone and slow connection.
Compares key claims across languages before publication.
Produces a plain-language draft plus a native-speaker review list.
Builds convincing copy only from verified product capabilities.
Simulates objections while clearly separating fiction from real research.
Reuses a verified source without repeating the same promotional line.
Creates a measurable campaign using only existing channels and assets.
Cuts cost and errors by reserving model calls for genuinely ambiguous cases.
Creates safe synthetic prompt-injection and false-source drills.
Finds decisions and relationships that need a human owner.
Turns a recorded workflow into a scoped reusable instruction set.
Converts an emotional report into a respectful reproducible test.
Need an AI worker, not one answer?
Define tools, authority, proof, persistence and safe stop conditions.