# Presly — robots.txt
# Presly WANTS to be read, indexed, and recommended by search engines AND AI
# answer engines (ChatGPT, Claude, Perplexity, Google AI Overviews/Gemini,
# Copilot, Apple Intelligence, etc.). Every public page is open to them; only
# private application routes are disallowed.
#
# Cloudflare Content Signals (https://contentsignals.org):
#   search   = yes  → appear in search indexes
#   ai-input = yes  → AI answer engines MAY use our content to ground & cite answers
#   ai-train = yes  → may be used for AI training (maximizes exposure/recommendation)

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /dashboard
Disallow: /admin
# Public blog content API — the blog SPA fetches article JSON from here when it
# renders. Crawlers' renderers obey robots.txt, so this MUST be allowed or the
# page renders "Post not found" (a Soft 404). More specific than /api/ below, so
# longest-match lets it through while the rest of /api/ stays blocked.
Allow: /api/blog/
# #189 (A3): the blog sitemap explicitly — belt & braces for parsers that don't
# do longest-match on the /api/blog/ rule above.
Allow: /api/blog/sitemap.xml
Disallow: /api/
Disallow: /login
Disallow: /signup
Disallow: /onboarding
Disallow: /invite/
Disallow: /reset-password
Disallow: /auth/

# ── AI answer & search crawlers — explicitly welcomed ────────────────────────
# (Named so no inherited/edge default can ambiguously block them. Same rules as
#  the wildcard group: full public access, private app routes excluded.)
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Bingbot
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: cohere-ai
User-agent: Amazonbot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
Allow: /
Disallow: /dashboard
Disallow: /admin
# Public blog content API — the blog SPA fetches article JSON from here when it
# renders. Crawlers' renderers obey robots.txt, so this MUST be allowed or the
# page renders "Post not found" (a Soft 404). More specific than /api/ below, so
# longest-match lets it through while the rest of /api/ stays blocked.
Allow: /api/blog/
# #189 (A3): the blog sitemap explicitly — belt & braces for parsers that don't
# do longest-match on the /api/blog/ rule above.
Allow: /api/blog/sitemap.xml
Disallow: /api/
Disallow: /login
Disallow: /signup
Disallow: /onboarding
Disallow: /invite/
Disallow: /reset-password
Disallow: /auth/

Sitemap: https://presly.ai/sitemap.xml