What you get
- A dated report with each check, its result and the evidence behind it.
- Starter files to review and adapt:
llms.txt, organisation and product JSON-LD, androbots.txt. Replace placeholders and confirm the details before publishing. - Suggested changes for core checks that need work.
What the report covers
The report covers the checks listed in the rubric. It reads your homepage,
robots.txt, sitemap.xml and llms.txt.
It does not crawl the whole site, run scripts or verify that your business details are true.
It does not predict whether an AI agent will find, trust or recommend your business, and it does not measure traffic or rankings.
How the checks were chosen
Read the development records for the choices behind the tool. They explain the alternatives, the reasons for each choice and the results of review. Later revisions record corrections and changes.
The rubric is public
Every check is written out at the rubric, with the reasoning and whether it is grounded in published practice or is our own judgment. The rubric is generated from the code that runs, and shows its version. The whole tool is open source.