# Convoy Guardian — robots.txt
# https://convoyguardian.app/robots.txt

# Default: allow all traditional crawlers
User-agent: *
Allow: /

# ============================================================
# AI / LLM crawlers — explicitly allowed
# ============================================================

# OpenAI (ChatGPT, GPT crawler for training + browsing)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google Gemini (separate opt-in from Googlebot)
User-agent: Google-Extended
Allow: /

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

User-agent: FacebookBot
Allow: /

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

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

# Common Crawl (feeds many open LLM datasets)
User-agent: CCBot
Allow: /

# ByteDance (Doubao)
User-agent: Bytespider
Allow: /

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

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

# Diffbot (structured data extraction — used by many LLM pipelines)
User-agent: Diffbot
Allow: /

# ============================================================
# Nothing to hide — no Disallow rules.
# All product content is public and intended for indexing + citation.
# ============================================================

# Sitemaps
Sitemap: https://convoyguardian.app/sitemap-index.xml