NFW Web Studio
News
// Method

How we calculate the AI score

The AI score measures how ready a site is to be read and cited by AI assistants and AI search. It runs from 0 to 100 and is the weighted mean of ten checks, computed for every working site we audited.

CheckA site passes when
Content in the HTMLpartial credit20its analyzed pages are not rendered by the browser alone. The score is the share of non client-side pages among those whose rendering is known.
llms.txt15the file /llms.txt exists.
robots.txt allows AI15robots.txt exists and does not disallow the whole site to every bot or to a known AI crawler. An Allow that re-opens part of the site is not taken into account.
Structured data15the main page carries JSON-LD structured data.
Sitemap10a sitemap.xml was found.
Title5the main page has a title.
Meta description5the main page has a meta description.
Canonical5the main page declares a canonical URL.
HTTPS5the site is served over HTTPS.
Lighthouse SEOpartial credit5the score is the main page's Lighthouse SEO score, divided by 100.
Total100

The AI crawlers we check for

For the robots.txt check we look at whether the site is closed to every bot, or to any of these:

  • GPTBot
  • OAI-SearchBot
  • ChatGPT-User
  • ClaudeBot
  • Claude-Web
  • anthropic-ai
  • PerplexityBot
  • Google-Extended
  • CCBot
  • Applebot-Extended

When a figure is missing

A check the audit cannot answer is left out for that site, and the remaining weights are rescaled. A site whose page rendering is unknown, for instance, is scored out of 80 rather than given zero: missing data never counts as a failure.

Back to the observatory