# robots.txt for garyhendershott.net
# Updated for SEO + AI GEO (Generative Engine Optimization)

# ================================================================
# Traditional Search Engines — full access
# ================================================================
User-agent: *
Allow: /

# Block admin/utility paths
Disallow: /includes/
Disallow: /logs/
Disallow: /webmaster/

# ================================================================
# AI Crawlers — full access for citation and answer quality
# ================================================================

# OpenAI (ChatGPT, search)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Google AI (Gemini, AI Overviews)
User-agent: Google-Extended
Allow: /

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

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

# Microsoft (Bing, Copilot)
User-agent: bingbot
Allow: /

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# Meta AI
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# ================================================================
# Resources
# ================================================================
Sitemap: https://garyhendershott.net/sitemap.xml