# harvv.com — robots.txt
# Standard search crawlers
User-agent: *
Allow: /
Disallow: /internal/
Disallow: /api/
Disallow: /customer/
Disallow: /admin
Disallow: /px/
Allow: /px/*/pixel.js
Disallow: /v1/

# AI training crawlers — allow (broad LLM presence is a feature for us)
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# AI retrieval bots — always allow (these return referral traffic)
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: DuckAssistBot
Allow: /

Sitemap: https://harvv.com/sitemap.xml