# RyanWilson.Land crawler policy
# Public content and assets are crawlable. Robots rules are not access control.

User-agent: *
Allow: /

# Public, read-only article data needed by the browser.
Allow: /api/blog
Disallow: /api/

# Authentication/private routes and development directories.
Disallow: /admin
Disallow: /sign-in
Disallow: /sign-up
Disallow: /user-portal
Disallow: /profile
Disallow: /server/
Disallow: /node_modules/
Disallow: /_next/
Disallow: /dist/

# Verification files, public images, JS and CSS inherit Allow: /.
Sitemap: https://ryanwilson.land/sitemap.xml

# Block mass AI model training / bulk corpus scraping
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: CCBot
User-agent: Google-Extended
User-agent: anthropic-ai
Disallow: /

# Allow real-time search & citation agents
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: Perplexity-User
User-agent: PerplexityBot
Allow: /
Allow: /api/blog
Disallow: /api/

# Googlebot, Bingbot and social previews use the shared policy above.