User-agent: *
Allow: /

# -- AI training crawlers --
# These feed model training. Allowing them trades attribution for presence in
# the model's knowledge, which favors name recognition over referral traffic.
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: cohere-ai
Allow: /

# -- AI search and answer-index crawlers --
# These build the indexes that assistants cite from. Highest value for
# referral traffic.
User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: GoogleOther
Allow: /

# -- User-initiated fetches --
# Fire only when a person asks an assistant to read a specific page.
User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Perplexity-User
Allow: /

# -- Content Signals Policy (Cloudflare) --
# search: building a search index
# ai-input: feeding real-time AI answers
# ai-train: training or fine-tuning models
Content-Signal: search=yes, ai-input=yes, ai-train=yes

Sitemap: https://michalak.world/sitemap.xml