# ==============================================
# General Crawlers
# ==============================================
User-agent: *
Allow: /
Allow: /blog/
Allow: /tools/

# Disallow dynamic report pages to prevent crawl waste
# These pages are accessible via direct links and sharing
Disallow: /report/

# ==============================================
# Major Search Engines
# ==============================================
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# ==============================================
# Social Media Bots
# ==============================================
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

# ==============================================
# AI Crawler Agents (CRITICAL FOR AEO)
# ==============================================
# OpenAI Crawlers
User-agent: ChatGPT-User
Allow: /

User-agent: GPTBot
Allow: /

# Google AI
User-agent: Google-Extended
Allow: /

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

User-agent: Claude-Web
Allow: /

User-agent: Anthropic-AI
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# ==============================================
# Sitemap Location
# ==============================================
Sitemap: https://cite-met.com/sitemap.xml