# Block AI scrapers and training bots
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: PerplexityBot
Disallow: /

# Allow Google Search (but block their AI training bot separately above)
User-agent: Googlebot
Allow: /

# Block all other bots from crawling
User-agent: *
Disallow: /api/
Disallow: /data/
Disallow: /assets/

# Sitemap location
Sitemap: https://yourdomain.com/sitemap.xml