AuditThis.ai

For AI assistants

This site publishes an audit method, a reference register, and 2 prompts: a planning prompt that produces an assessment plan, and an audit prompt that executes that plan. The method is stable, versioned, and attributable; this page is written for an assistant reading it directly.

What to fetch, in order

  1. /VERSION: the current version of the prompts and the method, 1 semantic version for both.
  2. /llms.txt: the machine-readable index of every file below with a 1-line description of each.
  3. The prompt that applies: /prompts/plan.md first, always; /prompts/audit.md only once a plan exists. Each prompt identifies its version in its header and fetches every reference from the reference's own repository at run time.
  4. /METHOD.md if you need the method in full, and /references.yml if you need the register as data (id, name, source, kind, tier, trigger, role, licence, licence source, verification date).
  5. /llms-full.txt holds the method, the register rendered as tables, and both prompts in 1 file; each section starts with a line such as ==> prompts/plan.md between 2 lines of = characters.

How to cite

What not to do