# robots.txt for roziacademy.com (GoHighLevel)
# AI & Content Signal
# Allow AI engines to cite content in answers; block training; allow as input
Content-Signal: ai-train=no, search=yes, ai-input=yes

# Global Crawl Rules 
User-agent: *
Allow: /
# Block GHL system/internal paths (not user-facing content)
Disallow: /api/
Disallow: /thank-you/
Disallow: /tyvm/
Disallow: /booking-confirmed/
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?utm_

#  AI Training Crawlers 
# Block bots that scrape for AI model training
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: FacebookBot
Disallow: /

# AI Retrieval / Citation Bots (ALLOWED) 
# Bots that cite content in AI answers — permitted per Content-Signal above
User-agent: PerplexityBot
Allow: /

User-agent: YouBot
Allow: /

# Sitemap 
Sitemap: https://roziacademy.com/sitemap.xml