# ===========================================
# People Inc. ROBOTS.TXT
# Corporate Website Access Control
# ===========================================

# ===========================================
# AI TRAINING & CONTENT SCRAPING BOTS - BLOCKED
# ===========================================

# OpenAI Crawlers
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

# Anthropic Crawlers
User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# Google AI Training
User-agent: Google-Extended
Disallow: /

# Common Crawl (used by many AI companies)
User-agent: CCBot
Disallow: /

# Meta/Facebook AI
User-agent: FacebookBot
Disallow: /

# Apple AI Training
User-agent: Applebot-Extended
Disallow: /

# ByteDance/TikTok
User-agent: Bytespider
Disallow: /

# Other AI/ML Services
User-agent: ImagesiftBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Timpibot
Disallow: /

# Additional AI Crawlers
User-agent: ClaudeBot
Disallow: /

User-agent: Cohere-ai
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: Amazonbot
Disallow: /

# AI Crawler Wildcards (for efficiency)
User-agent: *GPT*
Disallow: /

User-agent: *Claude*
Disallow: /

User-agent: *AI*
Disallow: /

# ===========================================
# NEWS & MEDIA CRAWLERS - ALLOWED
# ===========================================

User-agent: Googlebot-News
Disallow: /cdn-cgi/
Disallow: /_nuxt/

# ===========================================
# GENERAL CRAWLERS - ALLOWED WITH RESTRICTIONS
# ===========================================

User-agent: *
# Block technical/system directories
Disallow: /cdn-cgi/
Disallow: /_nuxt/

# ===========================================
# SITEMAP LOCATION
# ===========================================

Sitemap: https://www.people.inc/sitemap.xml