# Crawl policy: retrieval/answer crawlers welcome, training crawlers not.
# Rationale + measurement: docs/backlog/agentic-channel-proposal.md (H-A1).

User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

# --- Answer-engine retrieval + user-initiated fetch: ALLOW ---
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# --- Model training / bulk scrape: DISALLOW (Content-Signal ai-train=no) ---
User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: meta-externalagent
Disallow: /

Sitemap: https://whyismy.org/sitemap.xml