# Content Signals policy: Thematic content may be indexed and used to
# answer user questions, but may not be used to train generative AI models.
Content-Signal: search=yes, ai-input=yes, ai-train=no

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

# AI search and user-requested retrieval crawlers are explicitly welcomed so
# Thematic can be surfaced and cited in AI answers. Training-oriented crawlers
# are explicitly blocked to match the Content Signals policy above.
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: /

User-agent: Amazonbot
Allow: /

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: *
Allow: /
Disallow: /assets/

# AI-assistant content index: https://getthematic.com/llms.txt
# (a comment, not a directive — robots.txt has no LLM-Content field, and
# emitting one trips validators such as Lighthouse's robots-txt audit.)

Sitemap: https://getthematic.com/sitemap-index.xml
Sitemap: https://getthematic.com/insights-sitemap.xml