# llms.txt for https://www.industrialescaperooms.com/
# Purpose: Control access/use of site content by AI crawlers and model trainers.
# Last updated: 2025-10-02

# --- Contact & Policy ---
Owner: Industrial Escape Rooms
Contact: info@industrialescaperooms.com
Policy: Content is provided for human visitors. Use for AI/ML training, dataset creation, or embedding databases is NOT permitted unless we grant explicit written permission.

# --- Canonical reference ---
Site: https://www.industrialescaperooms.com/
Sitemap: https://www.industrialescaperooms.com/sitemap.xml

# --- Allowed paths for basic previewing/citation bots (non-training use only) ---
# (Public marketing pages are OK to fetch for link previews, citations, and summarization.)
Allow: /

# --- Disallowed private/system paths ---
Disallow: /admin/
Disallow: /login
Disallow: /account/
Disallow: /cart/
Disallow: /checkout/
Disallow: /search
Disallow: /api/
Disallow: /cdn-cgi/
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /private/
Disallow: /tmp/
Disallow: /?*preview=*
Disallow: /*?*password=*

# --- Rate limits (polite crawling) ---
Crawl-Delay: 10

# =====================================================
# Explicit directives for common AI/ML-related crawlers
# =====================================================

# OpenAI
User-agent: GPTBot
Disallow: /
User-agent: OAI-SearchBot
Disallow: /
User-agent: OAI-FeedFetcher
Disallow: /

# Anthropic
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-Web
Disallow: /

# Google (AI training extension)
User-agent: Google-Extended
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

# Apple (AI training extension)
User-agent: Applebot-Extended
Disallow: /

# Meta / Facebook external agent
User-agent: Meta-ExternalAgent
Disallow: /

# Common Crawl (often used to build AI datasets)
User-agent: CCBot
Disallow: /

# Dataminr / data collectors (prevent dataset inclusion)
User-agent: DataForSeoBot
Disallow: /

# Generic catch-all for unknown AI agents identifying as "AI", "LLM", or "crawler"
User-agent: *AI*
Disallow: /
User-agent: *LLM*
Disallow: /
User-agent: *embedding*
Disallow: /
User-agent: *dataset*
Disallow: /

# --- Licensing note ---
# No license is granted to copy, store, or reuse content for training large language models,
# embeddings, vector databases, or derivative datasets. Contact us to request permission.