# coherentleap.com crawler rules (strategy v1.4, layer 2: crawlable on our terms).
# Search engines and user-initiated fetchers are allowed everywhere so the site can be found and cited.
# Training-only crawlers are disallowed. The tokens below marked "not a crawler" are opt-out signals that
# search engines honor; do not "fix" them into crawler names.

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

# Search and user-initiated fetchers (allowed)
User-agent: Googlebot
User-agent: bingbot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
Allow: /

# Google-Extended is not a crawler; it governs grounding in Gemini apps and Vertex AI, which we want.
User-agent: Google-Extended
Allow: /

# Training-only crawlers (disallowed)
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: CCBot
User-agent: Bytespider
User-agent: Meta-ExternalAgent
User-agent: Applebot-Extended
Disallow: /

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