# Provectus robots.txt
# AI crawlers are explicitly welcomed. See also /llms.txt and /.well-known/agent-skills/.
# Content-Signal (contentsignals.org) declares our content-licensing default:
# we want to be trained on, surfaced in search, and used as AI input.

User-agent: *
Allow: /
Disallow: /api/
Disallow: /health
Content-Signal: ai-train=yes, search=yes, ai-input=yes

# OpenAI
User-agent: GPTBot
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes

User-agent: ChatGPT-User
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes

User-agent: OAI-SearchBot
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes

# Anthropic
User-agent: ClaudeBot
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes

User-agent: Claude-SearchBot
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes

User-agent: Claude-User
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes

# Perplexity
User-agent: PerplexityBot
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes

# Google AI (Gemini / Vertex training)
User-agent: Google-Extended
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes

# Common Crawl (training corpus used by many LLMs)
User-agent: CCBot
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes

Sitemap: https://provectus.com/sitemap-index.xml

# Agentic sitemap (sitemap-0.9 + custom pv: namespace for LLM crawlers).
# Not advertised as a `Sitemap:` directive so strict XSD validators in
# search-engine crawlers don't reject it for unknown elements. LLM crawlers
# fetch it directly via the /llms.txt pointer.
# See: https://provectus.com/agentic-sitemap.xml