Prove a serializer can round-trip values
Protects meaning across encoding boundaries.
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
Protects meaning across encoding boundaries.
Makes failure behaviour explicit before implementation.
Avoids a false binary of settled versus disputed.
Makes inclusion rules visible before choosing examples.
Checks denominators, revisions and definitions.
Explains what an interval does and does not mean.
Stops secondary summaries from becoming evidence.
Preserves uncertainty around origin and custody.
Names confounders before interpreting change.
Tracks translation uncertainty in research notes.
Reads the cited passage in context.
Separates convenient metrics from valid evidence.
Examines the sample frame before generalising.
Avoids relying on superseded instructions.
Makes authority and acceptance explicit.
Records unfinished work without a false sense of completion.
Chooses the smallest coordination format.
Prompts timely checks as conditions change.
Fits small obligations into an available window of no more than an hour.
Finds practical changes from observed interruptions.
Protects a small delivery window from scope creep.
Turns passive waiting into clear follow-up timing.
Creates a lightweight triage rule for requests.
Captures state so a task can resume quickly.
Need an AI worker, not one answer?
Define tools, authority, proof, persistence and safe stop conditions.