User-agent: *
Allow: /
# GEO JSON seeds submitted in sitemap.xml / advertised in llms.txt.
# More-specific Allow wins over Disallow /api/ (Google longest-match;
# listed before Disallow for first-match crawlers). Private API surfaces
# (/api/account, auth, companion, admin, waitlist, uploads) stay blocked.
Allow: /api/breed/*/neighbors.json
Allow: /api/v1/agent/discover.json
Allow: /api/v1/coverage/frames.json
Allow: /api/v1/atoms.json
Allow: /api/v1/papers.json
Allow: /api/v1/breeds.json
Allow: /api/v1/conditions.json
# Keep remaining API + private surfaces out of the index (crawl-budget
# hygiene, not a security boundary).
Disallow: /api/
Disallow: /account
Disallow: /login
Sitemap: https://sniff.world/sitemap.xml

# LLM context files for AI citation
# llms.txt: priority URL index

# GEO-friendly crawlers (training + live retrieval). Each agent group is
# independent of User-agent: * — Allow: / is intentional so citation bots
# can fetch the public genetics surface and the GEO JSON seeds above.
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /