# Robots.txt for Preuve AI
#
# Content Signals (https://contentsignals.org/, IETF draft-romm-aipref-contentsignals).
# We declare a fully open AI usage preference: search, AI answer/grounding (ai-input),
# and model training (ai-train) are ALL permitted. Preuve content is marketing we want
# distributed everywhere, including into model weights. RFC 9309 makes each crawler read
# only its most-specific User-agent group, so the directive is repeated per AI-bot group.

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

# Sitemap
Sitemap: https://preuve.ai/sitemap.xml

# Disallow API routes from indexing. The machine-readable API description
# stays crawlable: agents discover the API through these three documents
# (an Allow beats a Disallow of equal or shorter length under RFC 9309).
Disallow: /api/
Allow: /api/agent$
Allow: /api/openapi.json
Allow: /api/openapi.yaml
Allow: /api/.well-known/api-catalog

# Disallow user-generated share pages (thin content)
Disallow: /share/

# Disallow SPA shell (noindexed, save crawl budget)
Disallow: /app

# Disallow OG image template render routes (noindexed, source for /og/*.jpg)
Disallow: /og-template/

# Googlebot can crawl /app so it can see the noindex header and stop
# surfacing it as a blocked URL in external audits.
User-agent: Googlebot
Content-Signal: search=yes, ai-train=yes, ai-input=yes
Allow: /
Disallow: /api/
Allow: /api/agent$
Allow: /api/openapi.json
Allow: /api/openapi.yaml
Allow: /api/.well-known/api-catalog
Disallow: /share/

# AI Crawlers - Allow access for GEO (Generative Engine Optimization)
# These crawlers index content for AI-powered search engines

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

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

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

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

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

# Microsoft Copilot / Bing AI
User-agent: Bingbot
Content-Signal: search=yes, ai-train=yes, ai-input=yes
Allow: /

# Meta AI
User-agent: FacebookBot
Content-Signal: search=yes, ai-train=yes, ai-input=yes
Allow: /
User-agent: meta-externalagent
Content-Signal: search=yes, ai-train=yes, ai-input=yes
Allow: /

# Cohere AI
User-agent: cohere-ai
Content-Signal: search=yes, ai-train=yes, ai-input=yes
Allow: /

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

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

# Amazon AI
User-agent: Amazonbot
Content-Signal: search=yes, ai-train=yes, ai-input=yes
Allow: /

# You.com AI Search
User-agent: YouBot
Content-Signal: search=yes, ai-train=yes, ai-input=yes
Allow: /

# Point AI crawlers to llms.txt for structured content
# https://preuve.ai/llms.txt