# Answerwright — robots.txt
# Policy: allow every crawler that sends traffic or cites a source.
# Decline the bulk training crawlers that take content and return nothing.
# Agent names verified against vendor documentation, August 2026.

# ---------- Traditional search ----------
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Applebot
Allow: /

# ---------- AI search and retrieval: these cite and link back ----------
# OpenAI
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
# Anthropic. Claude-Web and anthropic-ai were retired; these are the live ones.
User-agent: Claude-SearchBot
Allow: /
User-agent: Claude-User
Allow: /
# Perplexity
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
# Others
User-agent: DuckAssistBot
Allow: /
User-agent: YouBot
Allow: /
User-agent: MistralAI-User
Allow: /
User-agent: Amazonbot
Allow: /

# ---------- Bulk training crawlers: declined ----------
# Nothing here affects Google Search, AI Overviews or AI Mode. Those are
# governed by Googlebot access, which is allowed above.
User-agent: GPTBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: meta-externalagent
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: omgili
Disallow: /
User-agent: ImagesiftBot
Disallow: /

# Google-Extended is a usage token, not a crawler. Allowing it keeps this site
# eligible as a grounding source for Gemini.
User-agent: Google-Extended
Allow: /

User-agent: *
Allow: /

Sitemap: https://answerwright.com/sitemap.xml