# PatrolTech Robots.txt
# https://patroltech.online

# Sitemap location
Sitemap: https://patroltech.online/sitemap.xml

# LLMs.txt for AI crawlers
# https://patroltech.online/llms.txt
# Expanded variant (full product reference) for AI crawlers
# https://patroltech.online/llms-full.txt

# Default rules for all crawlers
User-agent: *
Allow: /
# Open Graph image endpoint must stay crawlable so social bots
# (Twitterbot, LinkedInBot, facebookexternalhit) can fetch link previews.
Allow: /api/og
Disallow: /api/
Disallow: /dashboard/
Disallow: /404

# Google specific
User-agent: Googlebot
Allow: /
Crawl-delay: 1

# Bing specific
User-agent: Bingbot
Allow: /
Crawl-delay: 1

# AI Crawlers - Allow access for training/indexing
User-agent: GPTBot
Allow: /
Allow: /llms.txt

User-agent: ChatGPT-User
Allow: /
Allow: /llms.txt

User-agent: Claude-Web
Allow: /
Allow: /llms.txt

User-agent: Anthropic-AI
Allow: /
Allow: /llms.txt

User-agent: PerplexityBot
Allow: /
Allow: /llms.txt

User-agent: Cohere-ai
Allow: /
Allow: /llms.txt

# SEO crawlers (Ahrefs, Semrush, Moz/DotBot, Majestic/MJ12) allowed —
# covered by "User-agent: *" above; no per-bot Disallow.

# Answer-engine crawlers and AI assistants (search, citation and user-triggered fetches) - allowed.
User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: MistralAI-User
Allow: /

# Host directive
Host: https://patroltech.online