# robots.txt for drzeminchen.com
#
# Strategy: allow standard search engines and AI "live answer / citation"
# crawlers (so the site can be cited in AI assistants), but block crawlers
# that scrape content for AI model training. This complements the
# machine-readable TDM reservation at /tdmrep.json and the Copyright Notice
# at /copyright.
#
# Note: robots.txt is a request, not a guarantee. Compliance depends on the
# crawler operator. The legal opt-out lives in the Copyright Notice.

# ----------------------------------------------------------------------
# Default: allow all standard search engines, hide admin and API routes.
# ----------------------------------------------------------------------
User-agent: *
Allow: /
Disallow: /admin
Disallow: /api/

# ----------------------------------------------------------------------
# Allowed: live AI "answer" and "citation" crawlers (no model training).
# These help the site appear in ChatGPT, Claude, Perplexity and Google
# AI Overviews when users ask AI assistants a live question.
# ----------------------------------------------------------------------
User-agent: OAI-SearchBot
Allow: /
Disallow: /admin
Disallow: /api/

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

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

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

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

User-agent: DuckAssistBot
Allow: /
Disallow: /admin
Disallow: /api/

User-agent: MistralAI-User
Allow: /
Disallow: /admin
Disallow: /api/

User-agent: YouBot
Allow: /
Disallow: /admin
Disallow: /api/

# ----------------------------------------------------------------------
# Disallowed: AI MODEL TRAINING crawlers.
# Content on this site is not licensed for training, fine-tuning,
# evaluation or benchmarking of AI/ML systems. See /copyright for the
# full reservation under EU CDSM Art. 4(3) and UK CDPA 1988 s.29A.
# ----------------------------------------------------------------------
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Cohere-AI
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: TimpiBot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: img2dataset
Disallow: /

# ----------------------------------------------------------------------
Sitemap: https://drzeminchen.com/sitemap.xml