# This site monitors whether crawlers respect robots.txt.
# The paths listed below as Disallow are honeypots.
# Any request to them is logged as a violation, regardless of
# user-agent. The rest of the site is open to all bots so that
# compliance can actually be measured.
# Results are published at https://goodbot-badbot.com

User-agent: *
Content-Signal: ai-input=yes, ai-train=no, search=yes
Disallow: /do-not-crawl/
Disallow: /private/
Disallow: /honeypot/
Disallow: /training-data-forbidden/
Disallow: /no-ai-allowed/
Disallow: /robots-test/

Sitemap: https://goodbot-badbot.com/sitemap.xml