User-agent: *
Allow: /

# ── AI crawler policy: split ─────────────────────────────────────────────
# Retrieval yes, training no. note.md's search strategy depends on being citable
# inside AI answers, so every assistant's *search/citation* bot stays allowed.
# Only the bots that crawl to build training corpora are blocked.
#
# Each assistant ships BOTH kinds of bot, and they have to be split one by one:
# blocking ClaudeBot while forgetting to allow Claude-SearchBot would drop the
# site out of Claude's citations while only meaning to opt out of training.
#
# Caveats: robots.txt is a signal, not access control. Google-Extended does not
# opt you out of AI Overviews — those read the regular Google index, and there
# is no robots.txt lever for them.

# Training / bulk-dataset crawlers — blocked
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: CCBot
User-agent: Google-Extended
Disallow: /

# Search & citation retrieval — allowed
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
Disallow:

# Classic search indexing — allowed
User-agent: Googlebot
User-agent: Bingbot
Disallow:

Sitemap: https://www.notemd.org/sitemap.xml