# justtext.pizza
# AI training opt-out: we allow indexing/search, but do not permit AI training scrapers to use our content as model training data.

User-agent: *
Allow: /
Disallow: /api/
Disallow: /_next/

# AI training bots — explicit opt-out (in addition to the Content-Signal header below)
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Bytespider
Disallow: /

Sitemap: https://justtext.pizza/sitemap.xml
Host: https://justtext.pizza

# IETF draft: Content-Signal — declare that search indexing is allowed but AI training is not.
# Crawlers that honor this signal (e.g. license-aware crawlers) should treat the site as
# searchable but excluded from training corpora.
Content-Signal: search=yes,ai-train=no