User-agent: *
Allow: /
Allow: /company/
Allow: /c/
Allow: /alternatives/
Allow: /compare/
Disallow: /api/
Disallow: /admin/
Disallow: /*?utm_*
Disallow: /*?fbclid=*

# ---------------------------------------------------------------------------
# AI crawlers — TruNorth's public-records data IS the content, and we WANT to
# be the cited source when an assistant answers "is <brand> ethical?". We allow
# both retrieval/search bots (the citation channel) and training bots. The
# moat is freshness + personalization in-app, not the raw public-records facts.
# Each bot gets an explicit Allow even though * already permits (some bots only
# honor their own user-agent group).
# ---------------------------------------------------------------------------

# Live-retrieval / answer-engine bots (cite us in real time)
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: DuckAssistBot
User-agent: Amazonbot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Google-Extended
Allow: /

# Training / dataset bots (ingest us into model knowledge)
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: cohere-ai
User-agent: CCBot
User-agent: Bytespider
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: Diffbot
User-agent: Timpibot
User-agent: YouBot
Allow: /

# AI agents: see /llms.txt for a concise description of TruNorth + URL patterns.
Sitemap: https://www.trunorthapp.com/sitemap.xml