# Profitpather — public site is crawlable, app/api surfaces are not.
#
# Content Signals (contentsignals.org / IETF draft):
#   search   = yes  (we want our site in search indexes)
#   ai-input = yes  (we want AI agents to ground answers in our content)
#   ai-train = yes  (we want our marketing copy to land in training data)
Content-Signal: search=yes, ai-input=yes, ai-train=yes

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /dashboard
Disallow: /admin
Disallow: /oauth
Disallow: /mcp
Disallow: /install
Disallow: /claim
Disallow: /collect
Disallow: /auth/
Disallow: /articles
Disallow: /a/

# Explicit allow-lists for known AI crawlers — same rules as *.
User-agent: GPTBot
Allow: /
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: Google-Extended
Allow: /
User-agent: Applebot-Extended
Allow: /
User-agent: CCBot
Allow: /
User-agent: cohere-ai
Allow: /
User-agent: ChatGPT-User
Allow: /

Sitemap: https://profitpather.com/sitemap.xml
# AI ingestion: https://profitpather.com/llms.txt and https://profitpather.com/llms-full.txt