# bzhorizon.ai robots.txt
# AI crawlers: allowed for search and citation purposes

# Standard search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

# AI search and citation crawlers — explicitly allowed
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Applebot-Extended
Allow: /

# Block aggressive training scrapers with no search benefit
User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

# All others
User-agent: *
Disallow: /config
Disallow: /search
Disallow: /account$
Disallow: /account/
Disallow: /commerce/digital-download/
Disallow: /api/
Allow: /api/ui-extensions/
Disallow: /static/
Disallow: /*?format=json
Disallow: /*&format=json
Disallow: /*?format=page-context
Disallow: /*&format=page-context
Disallow: /*?format=main-content
Disallow: /*&format=main-content
Disallow: /*?format=json-pretty
Disallow: /*&format=json-pretty
Disallow: /*?format=ical
Disallow: /*&format=ical

Sitemap: https://www.bzhorizon.ai/sitemap.xml