User-agent: *
Allow: /
Disallow: /_next/
Disallow: /api/

# ─── AI search & retrieval crawlers (ALLOW for citations) ───

# OpenAI search retrieval
User-agent: OAI-SearchBot
Allow: /

# OpenAI user-initiated browsing
User-agent: ChatGPT-User
Allow: /

# Anthropic search retrieval
User-agent: Claude-SearchBot
Allow: /

# Anthropic user-initiated browsing
User-agent: Claude-User
Allow: /

# Perplexity search
User-agent: PerplexityBot
Allow: /

# Perplexity user-initiated
User-agent: Perplexity-User
Allow: /

# Bing preview (used by ChatGPT behind the scenes)
User-agent: BingPreview
Allow: /

# Google AI Overviews (uses standard Googlebot)
# No separate rule needed — Googlebot is allowed by default

# Google deep research agent
User-agent: Gemini-Deep-Research
Allow: /

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

# DuckDuckGo AI assistant
User-agent: DuckAssistBot
Allow: /

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

# Amazon Bedrock retrieval
User-agent: bedrockbot
Allow: /

# ─── AI training crawlers (BLOCK — no search benefit) ───

# OpenAI training crawler
User-agent: GPTBot
Disallow: /

# Anthropic training crawler
User-agent: ClaudeBot
Disallow: /

# Anthropic training crawler (alternate)
User-agent: anthropic-ai
Disallow: /

# Google AI indexing — allow so Google AI Overviews + Gemini can cite bounti.ai.
# (This token also governs Gemini training. Accepting that trade-off: the AEO
# upside from being indexable on AI surfaces outweighs the training concern,
# and the Google-trusted search bots we allow above already see all content.)
User-agent: Google-Extended
Allow: /

# Common Crawl — open dataset for AI training
User-agent: CCBot
Disallow: /

# Meta AI training
User-agent: Meta-ExternalAgent
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Meta-WebIndexer
Disallow: /

User-agent: meta-webindexer
Disallow: /

# Apple Intelligence training
User-agent: Applebot-Extended
Disallow: /

# ByteDance/TikTok training
User-agent: Bytespider
Disallow: /

# Amazon training
User-agent: Amazonbot
Disallow: /

Sitemap: https://bounti.ai/sitemap.xml