# https://www.robotstxt.org/robotstxt.html

# Generic crawlers
User-agent: *
# The CV PDF is public and linked from /resume, so blocking it made Google report
# "Blocked by robots.txt". Allow the crawl; the response carries X-Robots-Tag:
# noindex, which is the only way to reliably keep a URL out of the index (a
# blocked URL is never fetched, so a noindex on it is never seen).
Allow: /api/resume/pdf
Disallow: /api/
Disallow: /login
Disallow: /signup

# AI / LLM crawlers - explicitly allowed to ingest public content
User-agent: GPTBot
Allow: /
Disallow: /api/

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

User-agent: OAI-SearchBot
Allow: /
Disallow: /api/

User-agent: ClaudeBot
Allow: /
Disallow: /api/

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

User-agent: PerplexityBot
Allow: /
Disallow: /api/

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

User-agent: Google-Extended
Allow: /
Disallow: /api/

User-agent: CCBot
Allow: /
Disallow: /api/

User-agent: Bytespider
Allow: /
Disallow: /api/

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

User-agent: cohere-ai
Allow: /
Disallow: /api/

User-agent: anthropic-ai
Allow: /
Disallow: /api/

User-agent: meta-externalagent
Allow: /
Disallow: /api/

Sitemap: https://www.luciengeorge.com/sitemap.xml