# robots.txt for Magnolia Men's Health
# Last updated: 2026-05-07
# Site: https://www.magnoliamenshealth.com

# All standard search-engine crawlers welcome on every URL
User-agent: *
Allow: /
Disallow: /_migration/
Disallow: /raw-uploads/
Disallow: /.vercel/

# === AI training + answer crawlers (explicitly welcomed for GEO/AEO) ===

# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: OAI-SearchBot
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /

# Google AI Overview (separate from regular Googlebot — must opt in to AI training)
User-agent: Google-Extended
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Common Crawl (training data for many models)
User-agent: CCBot
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /
User-agent: Meta-ExternalFetcher
Allow: /
User-agent: FacebookBot
Allow: /

# Other notable AI crawlers
User-agent: Bytespider
Allow: /
User-agent: Diffbot
Allow: /
User-agent: Cohere-AI
Allow: /
User-agent: Amazonbot
Allow: /
User-agent: YouBot
Allow: /
User-agent: DuckAssistBot
Allow: /

# === Sitemap + LLM index ===
Sitemap: https://www.magnoliamenshealth.com/sitemap.xml

# Pointer to llms.txt for AI agents that look for it
# (not part of the robots.txt spec but increasingly read by AI fetchers)
# https://llmstxt.org/