diff --git a/web/public/robots.txt b/web/public/robots.txt index e74db4e..d1465b2 100644 --- a/web/public/robots.txt +++ b/web/public/robots.txt @@ -2,4 +2,25 @@ User-agent: * Allow: / +# AI crawlers are blocked at the edge, with a WAF skip for the two surfaces +# built for them: the llms.txt index and the markdown behind every docs page. +# Saying so here spends a crawler's budget on the two paths that answer instead +# of on HTML that will 403. This list is advisory and safe to let drift — the +# WAF is the enforcement, and a crawler missing from it falls back to the group +# above and is stopped at the edge anyway, which is the same answer, just later. +User-agent: GPTBot +User-agent: OAI-SearchBot +User-agent: ChatGPT-User +User-agent: ClaudeBot +User-agent: Claude-User +User-agent: Claude-SearchBot +User-agent: PerplexityBot +User-agent: Perplexity-User +User-agent: meta-externalagent +User-agent: Bytespider +User-agent: CCBot +Disallow: / +Allow: /llms.txt +Allow: /docs/*.md$ + Sitemap: https://reader-md.jnahian.me/sitemap.xml