# Robots.txt for AuditBadger.com
# See https://www.robotstxt.org/robotstxt.html for documentation

User-agent: *
# Content Signals (https://contentsignals.org/) — declares AI usage preferences
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /
Disallow: /session
Disallow: /passwords/
Disallow: /newsletter
Disallow: /p/
# Downloadable copies of pages that already exist in HTML (e.g. the Article 50
# pack PDF), kept from competing with the page they came from.
Disallow: /downloads/
# Tokenized, personal Article 50 record downloads (also X-Robots-Tag: noindex).
Disallow: /eu-ai-act-article-50/download/

# Allow search engines to crawl important pages
Allow: /features/
Allow: /developers/
Allow: /about/
Allow: /contact/
Allow: /blog/
Allow: /by_category/
Allow: /category/

# Agent-readable maps of this site
# https://auditbadger.com/llms.txt      - curated site map for LLMs
# https://auditbadger.com/agents.md     - when to use AuditBadger, and how to call it
# https://auditbadger.com/openapi.json  - OpenAPI 3.1 description of the REST API
# https://auditbadger.com/.well-known/ai-catalog.json - agentic resource catalog (ARD)

# Sitemap location (301s to the S3-hosted file)
Sitemap: https://auditbadger.com/sitemap.xml

# Crawl-delay for polite crawling
Crawl-delay: 1

# User-agent specific rules
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /