# robots.txt for acme.com
# Search engines and AI search can read the site.
# Crawlers that collect training data can't.

# AI search and assistants fetching a page for a user
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
Allow: /
Disallow: /app/
Disallow: /api/

# Crawlers that collect model training data
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: CCBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bytespider
Disallow: /

# Everyone else, including Googlebot and Bingbot
User-agent: *
Allow: /
Disallow: /app/
Disallow: /api/

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