# Interstate Medicine crawling policy (website 84s, 2026-11-02)
# Search engines and AI answer engines may crawl and cite this site.
# Collecting this site's content to train AI models or build datasets is not permitted.
# Content Use Policy: https://interstatemedicine.com/content-use-policy.html
# (/pro.html is a redirect to /ledger.html and carries its own noindex meta tag; deliberately NOT disallowed here.)

User-agent: *
Allow: /

# Search and answer engines: allowed
User-agent: Googlebot
User-agent: Bingbot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: Applebot
User-agent: YouBot
User-agent: Amazonbot
User-agent: Meta-ExternalFetcher
User-agent: PetalBot
Allow: /

# Google-Extended stays allowed on purpose: blocking it also removes the site from Gemini app answers (owner, 2026-11-02).
User-agent: Google-Extended
Allow: /

# AI training and dataset crawlers: not allowed
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: CCBot
User-agent: Applebot-Extended
User-agent: Meta-ExternalAgent
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Bytespider
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Diffbot
User-agent: Timpibot
User-agent: ImagesiftBot
User-agent: Omgilibot
User-agent: Omgili
User-agent: GoogleOther
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: img2dataset
User-agent: PanguBot
User-agent: Scrapy
Disallow: /

Sitemap: https://interstatemedicine.com/sitemap.xml
# Machine-readable site summary for AI answer engines
# https://interstatemedicine.com/llms.txt
# https://interstatemedicine.com/llms-full.txt