# robots.txt for https://qkchealth.com - QKC Health LLC
# American Heart Association Authorized Training Center: CPR, BLS, ACLS and
# First Aid training in Connecticut, Westchester County NY, and New Jersey.
#
# Search engines and AI services are welcome to crawl, index, quote, cite and
# train AI models on this site (Content-Signal below; see the Terms of Service).
# Site summary for AI assistants:
#   https://qkchealth.com/llms.txt       (index of every page, llmstxt.org format)
#   https://qkchealth.com/llms-full.txt  (the full text of every page in Markdown)
# Each page also has a Markdown copy at its URL plus "index.html.md".
#
# Keep the rules in both groups identical. A crawler that matches a named
# group ignores the "*" group (RFC 9309), so a rule added to one group must
# be added to the other. No blank lines inside a group.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Search engines and AI assistants named in their vendors' documentation.
# Google: Googlebot (Search, AI Overviews, AI Mode), Google-Extended (Gemini
# training and grounding), GoogleOther (research crawls)
User-agent: Googlebot
User-agent: Google-Extended
User-agent: GoogleOther
# Microsoft: bingbot (Bing; its index also grounds Copilot)
User-agent: bingbot
# OpenAI: OAI-SearchBot (ChatGPT search), ChatGPT-User (user requests), GPTBot (training)
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: GPTBot
# Anthropic: Claude-SearchBot (search), Claude-User (user requests), ClaudeBot (training)
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: ClaudeBot
# Perplexity: PerplexityBot (search), Perplexity-User (user requests)
User-agent: PerplexityBot
User-agent: Perplexity-User
# Apple: Applebot (Siri, Spotlight, Safari), Applebot-Extended (Apple Intelligence training)
User-agent: Applebot
User-agent: Applebot-Extended
# Meta: meta-webindexer (Meta AI search), meta-externalagent (training),
# meta-externalfetcher (user requests), facebookexternalhit (link previews)
User-agent: meta-webindexer
User-agent: meta-externalagent
User-agent: meta-externalfetcher
User-agent: facebookexternalhit
# Amazon: Amzn-SearchBot (Alexa search), Amzn-User (user requests), Amazonbot
User-agent: Amzn-SearchBot
User-agent: Amzn-User
User-agent: Amazonbot
# DuckDuckGo: DuckDuckBot (search), DuckAssistBot (AI answers)
User-agent: DuckDuckBot
User-agent: DuckAssistBot
# Mistral AI: MistralAI-Index (search), MistralAI-User (user requests), MistralAI-Training
User-agent: MistralAI-Index
User-agent: MistralAI-User
User-agent: MistralAI-Training
# Other search and AI crawlers: You.com, Kagi, Common Crawl, Ai2. (AI2Bot has a
# digit, which RFC 9309 product tokens lack; strict parsers fall back to "*",
# whose rules are the same.)
User-agent: YouBot
User-agent: Kagibot
User-agent: CCBot
User-agent: AI2Bot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

Sitemap: https://qkchealth.com/sitemap.xml