# Logan Currie — logancurrie.com
# Allow retrieval bots (surface content in AI answers)
# Block training-only bots (don't use content for model training)

# AI usage preferences (Content Signals — IETF draft-romm-aipref-contentsignals)
Content-Signal: search=yes, ai-input=yes, ai-train=no

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

# Retrieval bots — welcome
User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Training-only bots — blocked
User-agent: GPTBot
Disallow: /

# Google-Extended is broader than a training opt-out: per Google's crawler docs
# it also governs grounding in Gemini Apps and Vertex AI Search grounding.
# Blocking it does not affect Google Search indexing or ranking.
# It is one token for both, so allowing grounding also allows Gemini training.
# Kept blocked for now; that tradeoff is Logan's call.
User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: FacebookBot
Disallow: /

Sitemap: https://www.logancurrie.com/sitemap.xml

# a note for anyone reading this by hand instead of parsing it:
# retrieval is welcome, training is not. nothing personal, ClaudeBot.
# the map is /llms.txt. every page has a .md twin.
# one page only exists in markdown. the 404 knows where.