User-agent: *
Allow: /

# Hidden/archived pages are NOT blocked here on purpose: they carry a
# noindex tag, and Google can only see that tag if it may crawl them.

# Block AI-training and bulk-scraping crawlers specifically.
# AI *search/answer* agents that fetch a page when a person asks a
# question (OAI-SearchBot, ChatGPT-User, PerplexityBot, Claude-SearchBot,
# Claude-User) are intentionally NOT blocked: they surface and cite the
# site in AI answers, which is a lead source like a search engine.
# Standard search engines (Googlebot, Bingbot, etc.) stay fully allowed
# above — blocking them would defeat the SEO/lead-gen strategy this site
# exists for. This list only targets crawlers whose purpose is bulk
# ingestion/training, not indexing for search results.
User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: YouBot
Disallow: /

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