# https://www.kretsia.com/robots.txt
#
# Kretsia wants to be found and cited, by search engines and by AI answer
# engines alike. Nothing on this marketing site is gated behind a login, so
# there is nothing to disallow: nofollow/noindex on individual pages (the
# blog template specimen, for example) is handled with a <meta name="robots">
# tag on that page, not a Disallow here. A Disallow would stop crawlers from
# ever reading the noindex tag in the first place.
#
# Content-Signal (contentsignals.org) states how the content may be used:
# search index, AI answers (ai-input) and AI training (ai-train) all allowed.

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

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# --- AI crawlers: explicitly allowed -----------------------------------
# Kretsia's SEO strategy depends on being cited in AI answers (ChatGPT,
# Claude, Perplexity, Gemini). Do not block these, and do not let a future
# "block AI scrapers" boilerplate snippet get pasted in here.

# OpenAI: GPTBot trains ChatGPT; ChatGPT-User and OAI-SearchBot fetch a page
# live when a user asks about it.
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic: ClaudeBot trains Claude; Claude-User and Claude-SearchBot fetch
# a page live for a Claude/claude.ai answer.
User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Perplexity: PerplexityBot indexes for search; Perplexity-User fetches live
# for an on-demand answer.
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google's AI training crawler, separate from Googlebot (which is already
# covered by the User-agent: * block above and must stay allowed for search).
User-agent: Google-Extended
Allow: /

# Common Crawl: not an AI company itself, but its corpus feeds many AI labs'
# training sets (including, historically, Perplexity's).
User-agent: CCBot
Allow: /

# Meta: trains Meta AI.
User-agent: meta-externalagent
Allow: /

# Bytespider (ByteDance) is blocked at Cloudflare (WAF custom rule, on the
# agent's recommendation), so it is not listed here. Amazonbot is allowed
# (unblocked 2026-10-21: it feeds Alexa and Amazon's AI answers).