# public/robots.txt

# Allow all crawlers
User-agent: *
Allow: /

# Block authentication routes to prevent duplicate content
Disallow: /sign-in/
Disallow: /sign-up/
Disallow: /sign-out/
Disallow: /verify/
Disallow: /reset-password/
Disallow: /account/

# Disallow API routes
Disallow: /api/

# Disallow old test request page
Disallow: /request-a-test

# Explicitly allow major AI / LLM crawlers. Finnrick publishes test data for
# public benefit and wants to be citable by AI engines.
User-agent: GPTBot
Allow: /
Disallow: /api/
Disallow: /account/

User-agent: ChatGPT-User
Allow: /
Disallow: /api/
Disallow: /account/

User-agent: OAI-SearchBot
Allow: /
Disallow: /api/
Disallow: /account/

User-agent: ClaudeBot
Allow: /
Disallow: /api/
Disallow: /account/

User-agent: Claude-Web
Allow: /
Disallow: /api/
Disallow: /account/

User-agent: anthropic-ai
Allow: /
Disallow: /api/
Disallow: /account/

User-agent: PerplexityBot
Allow: /
Disallow: /api/
Disallow: /account/

User-agent: Perplexity-User
Allow: /
Disallow: /api/
Disallow: /account/

User-agent: Google-Extended
Allow: /
Disallow: /api/
Disallow: /account/

User-agent: Applebot-Extended
Allow: /
Disallow: /api/
Disallow: /account/

User-agent: Bytespider
Allow: /
Disallow: /api/
Disallow: /account/

User-agent: CCBot
Allow: /
Disallow: /api/
Disallow: /account/

# Sitemap
Sitemap: https://www.finnrick.com/sitemap.xml

# LLM-friendly site summary (for clients that honor it; proposed standard)
# https://llmstxt.org

# Host
Host: https://www.finnrick.com