# Robots.txt for assetlab.ca
# Optimized for AI agent discovery and Generative Engine Optimization (GEO)

# Traditional Search Engines
# /api/og serves the share and structured-data images for every page. It has to
# stay crawlable or Google reports "missing field image" on our Product markup
# and drops the thumbnails. Longest matching path wins, so this beats /api/.
User-agent: Googlebot
Allow: /
Allow: /api/og
Disallow: /admin/
Disallow: /api/
Disallow: /app/
# Note: Googlebot does not support Crawl-delay; ignored.
# Crawl-delay: 1

User-agent: Googlebot-Image
Allow: /
Allow: /api/og
Disallow: /admin/
Disallow: /api/
Disallow: /app/

User-agent: Bingbot
Allow: /
Allow: /api/og
Disallow: /admin/
Disallow: /api/
Disallow: /app/
Crawl-delay: 1

# AI Crawlers & LLM Training
# OpenAI GPT
User-agent: GPTBot
Allow: /
Allow: /llms.txt
Crawl-delay: 1

# Anthropic Claude
User-agent: ClaudeBot
Allow: /
Allow: /llms.txt
Crawl-delay: 1

# Google AI (Bard/Gemini)
User-agent: Google-Extended
Allow: /
Allow: /llms.txt
Crawl-delay: 1

# Perplexity AI
User-agent: PerplexityBot
Allow: /
Allow: /llms.txt
Crawl-delay: 1

# AI search and user-initiated fetches. These retrieve pages to cite in answers
# (ChatGPT search, Claude search, Perplexity answers), separate from the
# training crawlers above, so they get their own explicit groups.
User-agent: OAI-SearchBot
Allow: /
Allow: /api/og
Disallow: /api/

User-agent: ChatGPT-User
Allow: /
Allow: /api/og
Disallow: /api/

User-agent: Claude-SearchBot
Allow: /
Allow: /api/og
Disallow: /api/

User-agent: Claude-User
Allow: /
Allow: /api/og
Disallow: /api/

User-agent: Perplexity-User
Allow: /
Allow: /api/og
Disallow: /api/

User-agent: Applebot
Allow: /
Allow: /api/og
Disallow: /api/

User-agent: Applebot-Extended
Allow: /

# Common Crawl (used by many AI systems)
User-agent: CCBot
Allow: /
Allow: /llms.txt
Crawl-delay: 1

# Cohere AI
User-agent: cohere-ai
Allow: /
Allow: /llms.txt
Crawl-delay: 1

# Social Media Crawlers
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# Catch-all for other bots
User-agent: *
Allow: /
Allow: /api/og
Disallow: /admin/
Disallow: /api/
Disallow: /app/
Crawl-delay: 2

# Sitemap location
Sitemap: https://assetlab.ca/sitemap.xml

# Note: This site provides comprehensive information for AI agents via /llms.txt
# For AI-optimized content, please reference https://assetlab.ca/llms.txt