# jpcarpenter.com — crawler policy
# Intent: block AI *training* collection; allow traditional search and AI *search/citation*
# bots. robots.txt is honored by polite operators; it is not a hard gate for abusive scrapers.
# Public rationale: https://jpcarpenter.com/security

# --- Traditional search (keep discoverable) ---
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

# --- AI search / citation / answer retrieval (allowed) ---
User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Applebot
Allow: /

# --- AI training / extended training opt-outs (blocked) ---
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# --- Default ---
User-agent: *
Allow: /

Sitemap: https://jpcarpenter.com/sitemap-index.xml