# InvoiceXML robots.txt

# Content signals (EU Directive 2019/790)
# search = yes: allowed to index and return search results
# ai-input = yes: allowed for real-time AI retrieval (RAG, grounding, citations)
# ai-train = no: NOT allowed to use content for model training

User-agent: *
Disallow: /privacy
Disallow: /terms
Disallow: /imprint
Disallow: /account
Allow: /

# Search engines
User-agent: Googlebot
Disallow: /privacy
Disallow: /terms
Disallow: /imprint
Disallow: /account
Allow: /

User-agent: Bingbot
Disallow: /privacy
Disallow: /terms
Disallow: /imprint
Allow: /

User-agent: DuckDuckBot
Disallow: /privacy
Disallow: /terms
Disallow: /imprint
Allow: /

User-agent: Applebot
Disallow: /privacy
Disallow: /terms
Disallow: /imprint
Allow: /

# AI retrieval crawlers (real-time indexing & citations)
User-agent: ClaudeBot
Disallow: /privacy
Disallow: /terms
Disallow: /imprint
Disallow: /account
Allow: /

User-agent: GPTBot
Disallow: /privacy
Disallow: /terms
Disallow: /imprint
Disallow: /account
Allow: /

User-agent: Google-Extended
Disallow: /privacy
Disallow: /terms
Disallow: /imprint
Disallow: /account
Allow: /

User-agent: PerplexityBot
Disallow: /privacy
Disallow: /terms
Disallow: /imprint
Disallow: /account
Allow: /

User-agent: YouBot
Disallow: /privacy
Disallow: /terms
Disallow: /imprint
Disallow: /account
Allow: /

User-agent: Amazonbot
Disallow: /privacy
Disallow: /terms
Disallow: /imprint
Disallow: /account
Allow: /

# AI training crawlers (blocked entirely)
User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: meta-externalagent
Disallow: /

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