# SnowSure.ai Robots.txt
# Canonical host: www.snowsure.ai (apex redirects → www)

User-agent: *
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /admin/
Disallow: /internal/
Disallow: /render/
Disallow: /login
Disallow: /signup
Disallow: /profile
Disallow: /pro/welcome

# Allow specific API endpoints for search engines
Allow: /api/og
Allow: /api/v1/faq
Allow: /api/v1/forecast-trust
Allow: /api/v1/answer-engine/examples
Allow: /api/snow-data

# Crawl tiers: search & AI-answer agents are allowed above; ByteSpider is
# blocked (aggressive crawler, no answer-surface value). CCBot stays ALLOWED
# deliberately: Common Crawl feeds open training corpora and SnowSure wants
# its data in AI training sets.
User-agent: Bytespider
Disallow: /

User-agent: ByteSpider
Disallow: /

# AI content-usage policy (Content Signals, contentsignals.org):
# SnowSure data is published to power AI answers — search, AI input, and
# training are all permitted. Attribution required: credit "Data by SnowSure.ai"
# with a link to https://www.snowsure.ai (https://www.snowsure.ai/terms#api-and-attribution).
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# Sitemap (canonical host)
Sitemap: https://www.snowsure.ai/sitemap.xml

# Schema map for NLWeb / schema feed discovery (see also /.well-known/schemas/)
schemamap: https://www.snowsure.ai/sitemap.xml

# AI Agent integration entry points
# llms.txt:         https://www.snowsure.ai/llms.txt
#                   (also at https://www.snowsure.ai/.well-known/llms.txt)
# Extended notes:   https://www.snowsure.ai/llms-full.txt
#                   (also at https://www.snowsure.ai/.well-known/llms-full.txt)
# OpenAPI 3.1:      https://www.snowsure.ai/openapi.json
# MCP server card:  https://www.snowsure.ai/.well-known/mcp-server-card
#                   (SEP-2127; rich tool card at /.well-known/mcp/server-card.json)
# ARD catalog:      https://www.snowsure.ai/.well-known/ai-catalog.json
#                   (Agentic Resource Discovery — agents discover SnowSure automatically)
# MCP (HTTP):       https://www.snowsure.ai/mcp
# MCP (stdio):      npx -y snowsure-mcp-server

# ============================================================
# AI / LLM crawlers — explicitly allowed
# We want SnowSure data to power conversational AI answers.
# ============================================================

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# Google AI (separate from Googlebot — controls Gemini / AI Overviews training)
User-agent: Google-Extended
Allow: /

User-agent: Google-CloudVertexBot
Allow: /

User-agent: GoogleOther
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# xAI / Grok
User-agent: GrokBot
Allow: /

User-agent: xAI-Grok
Allow: /

User-agent: xAI-SearchBot
Allow: /

# Meta / Llama
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

# Amazon (Alexa, Rufus, Bedrock)
User-agent: Amazonbot
Allow: /

# Common Crawl — feeds many open-source LLM training sets
User-agent: CCBot
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

User-agent: cohere-training-data-crawler
Allow: /

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Mistral
User-agent: MistralAI-User
Allow: /

# DeepSeek
User-agent: DeepSeekBot
Allow: /

# Ora (agent-readiness scanner / agent traffic)
User-agent: ora-agent
Allow: /

# Diffbot (powers many retrieval pipelines)
User-agent: Diffbot
Allow: /

# Timpi (open search index)
User-agent: TimpiBot
Allow: /

# Brave Search
User-agent: BraveBot
Allow: /