# Helix Captcha - Agent Discovery Protocol
# Updated: Nov 23, 2025

# Content signals for AI agents:
# search:   building a search index and providing search results
# ai-input: inputting content into AI models (RAG, grounding)
# ai-train: training or fine-tuning AI models

# Search Engines
User-agent: Googlebot
Allow: /
content-signal: search=yes, ai-input=yes, ai-train=no

User-agent: Bingbot
Allow: /
content-signal: search=yes, ai-input=yes, ai-train=no

# AI Crawlers - Anthropic
User-agent: ClaudeBot
Allow: /
content-signal: search=yes, ai-input=yes, ai-train=no

User-agent: Claude-Web
Allow: /
content-signal: search=yes, ai-input=yes, ai-train=no

User-agent: anthropic-ai
Allow: /
content-signal: search=yes, ai-input=yes, ai-train=no

# AI Crawlers - OpenAI
User-agent: GPTBot
Allow: /
content-signal: search=yes, ai-input=yes, ai-train=no

User-agent: ChatGPT-User
Allow: /
content-signal: search=yes, ai-input=yes, ai-train=no

User-agent: OAI-SearchBot
Allow: /
content-signal: search=yes, ai-input=yes, ai-train=no

# AI Crawlers - Other
User-agent: PerplexityBot
Allow: /
content-signal: search=yes, ai-input=yes, ai-train=yes

# Default - Allow all (removed security block for Google indexing)
User-agent: *
Allow: /

# Sitemap Index
Sitemap: https://helixcaptcha.org/sitemap.xml