# Chorilo robots.txt
# Tier-differentiated AI crawler policy with Content Signals
# Reference: https://contentsignals.org

# ===== Default policy =====
User-agent: *
Allow: /
Allow: /shop
Allow: /shop/
Disallow: /admin
Disallow: /community/settings
Disallow: /profile
Disallow: /dashboard
Disallow: /ensembles/
Disallow: /events/
Disallow: /sheet-music/
Disallow: /chats/
Disallow: /notifications/
Disallow: /publisher/
Disallow: /*?redirect=
Disallow: /*&redirect=

# ===== Tier 1: Search-only AI agents (full content access) =====
User-agent: ChatGPT-User
Allow: /
Disallow: /admin
Disallow: /profile
Disallow: /dashboard

User-agent: OAI-SearchBot
Allow: /
Disallow: /admin

User-agent: ClaudeBot
Allow: /
Disallow: /admin

User-agent: Claude-Web
Allow: /
Disallow: /admin

User-agent: PerplexityBot
Allow: /
Disallow: /admin

User-agent: Applebot-Extended
Allow: /
Disallow: /admin

User-agent: Claude-User
Allow: /
Disallow: /admin

User-agent: Perplexity-User
Allow: /
Disallow: /admin

User-agent: Google-NotebookLM
Allow: /
Disallow: /admin

User-agent: Gemini-Deep-Research
Allow: /
Disallow: /admin

User-agent: MistralAI-User
Allow: /
Disallow: /admin

User-agent: meta-externalagent
Allow: /
Disallow: /admin

User-agent: Amazonbot
Allow: /
Disallow: /admin

User-agent: cohere-ai
Allow: /
Disallow: /admin

User-agent: Diffbot
Allow: /
Disallow: /admin

User-agent: DuckAssistBot
Allow: /
Disallow: /admin

# ===== Tier 2: Search engine grounding extensions =====
User-agent: Google-Extended
Allow: /
Disallow: /admin

# ===== Tier 3: Training crawlers (allowed, but limited paths) =====
User-agent: GPTBot
Allow: /
Disallow: /admin
Disallow: /community/
Disallow: /profile
Disallow: /dashboard
Disallow: /ensembles/

User-agent: CCBot
Allow: /
Disallow: /admin
Disallow: /community/
Disallow: /profile
Disallow: /dashboard
Disallow: /ensembles/

User-agent: Bytespider
Allow: /
Disallow: /admin
Disallow: /community/
Disallow: /profile
Disallow: /dashboard
Disallow: /ensembles/

# ===== Content Signals (https://contentsignals.org) =====
# search=yes: AI agents may use this content for grounding answers
# ai-input=yes: AI agents may use this content as context for inference
# ai-train=yes: training crawlers may include this content (we want to be in training data)
Content-Signal: search=yes, ai-input=yes, ai-train=yes

Sitemap: https://www.chorilo.com/sitemap.xml
# Schema-Map (non-standard directive — Lighthouse flagged it).
# Indexed via <link rel="alternate" type="application/ld+json"> in <head> instead.
# schemamap: https://www.chorilo.com/schemamap.xml