User-agent: *
Allow: /

# Search indexing — allowed
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Applebot
Allow: /

User-agent: DuckDuckBot
Allow: /

# AI citation / grounding / link-preview crawlers — allowed
# (These bots fetch pages to attribute/cite or render previews. They do not
# feed training datasets. Allowing them restores AI Overview eligibility,
# ChatGPT/Perplexity/Grok citations, and Facebook/Instagram link previews.)
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Grok
Allow: /

User-agent: GrokBot
Allow: /

User-agent: xAI-Bot
Allow: /

User-agent: xAI-Grok
Allow: /

User-agent: Grok-DeepSearch
Allow: /

User-agent: DuckAssistBot
Allow: /

# Pure AI training crawlers — blocked
# (These bots scrape content to feed model training corpora. Blocking them
# opts out of training datasets without affecting search or AI citations.)
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

# Data-resale / scraping services — blocked
User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: YouBot
Disallow: /

# SEO and content scrapers — blocked
User-agent: Amazonbot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: YandexBot
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: Sogou
Disallow: /

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