# Beat The GMAT - robots.txt
# https://www.beatthegmat.com

# === AI CRAWLERS — EXPLICITLY WELCOMED ===
# BTG wants to be cited by AI assistants for GMAT/MBA content

User-agent: GPTBot
Allow: /
Disallow: /forum/ucp.php
Disallow: /forum/mcp.php
Disallow: /forum/adm/
Disallow: /mba/admin/

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

# === GENERAL CRAWLERS ===
User-agent: *
Allow: /

# CMS admin
Disallow: /mba/admin/
Disallow: /mba/tmp/
Disallow: /mba/lib/
Disallow: /mba/assets/
Disallow: /mba/uploads/

# Forum internals
Disallow: /forum/ucp.php
Disallow: /forum/mcp.php
Disallow: /forum/adm/
Disallow: /forum/install/
Disallow: /forum/cache/
Disallow: /forum/store/
Disallow: /forum/memberlist.php
Disallow: /forum/search.php
Disallow: /forum/posting.php
Disallow: /forum/report.php

# Session/login params
Disallow: /*?sid=
Disallow: /*&sid=
Disallow: /*?mode=login
Disallow: /*?mode=register

# Duplicate content prevention
Disallow: /forum/viewtopic.php?*&start=0
Disallow: /forum/viewforum.php?*&start=0

# Crawl-delay for aggressive SEO bots
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: MJ12bot
Crawl-delay: 30

User-agent: DotBot
Crawl-delay: 30

# Sitemaps
Sitemap: https://www.beatthegmat.com/sitemap.xml

# LLM content discovery
# /llms.txt — concise AI-readable summary
# /llms-full.txt — complete resource map
# /.well-known/ai-plugin.json — plugin manifest