ChatShortlistBot
If you found this page in your server logs, someone ran an AI readiness scan against your site using ChatShortlist. Here is exactly what that means.
What it does
When a signed-in visitor submits a URL, our server makes up to four
ordinary GET requests: the page itself, /robots.txt,
/llms.txt and /sitemap.xml. It reads the HTML,
grades it against a fixed rubric, and shows the visitor a report.
What it does not do
- It does not execute JavaScript, submit forms, or log in.
- It does not crawl onwards — only the URL it was given.
- It does not store a copy of your site, only the score and the observations behind it.
- It does not train a model on your content.
Rate
A scan is a handful of requests, triggered by a person waiting for a result. There is no background crawl, no schedule, and no queue building up against your origin. Scans are rate-limited per account.
Blocking it
We honour robots.txt. To refuse the scanner entirely, add this to yours:
User-agent: ChatShortlistBot
Disallow: /Worth knowing before you do: the tool exists to tell site owners when they have accidentally blocked GPTBot, ClaudeBot and PerplexityBot. Blocking us changes nothing about how those crawlers see you — it only stops anyone checking.
Contact
Questions, or a request to stop scanning a particular property: hello@chatshortlist.com. We answer these.