# Default rules for all crawlers
User-agent: *
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /cms/

# =============================================================
# Explicitly allow AI crawlers
# Why: Some crawlers check bot-specific rules first.
# An explicit Allow signals intent — you WANT to be indexed.
# =============================================================

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

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

User-agent: GoogleOther
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# You.com
User-agent: YouBot
Allow: /

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

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

# Microsoft / Bing
User-agent: bingbot
Allow: /

# Meta
User-agent: FacebookBot
Allow: /

# =============================================================
# Host — Primary site
# =============================================================
Host: https://www.hii.com

# =============================================================
# Sitemap — Full crawlable URL structure
# =============================================================
Sitemap: https://www.hii.com/sitemap.xml

# =============================================================
# llms.txt — Token-efficient index of top level content
# =============================================================
llms.txt: https://www.hii.com/llms.txt