# AI content-usage preferences (Content Signals, contentsignals.org).
# search=yes: may be used in search results. ai-input=yes: may ground AI answers
# (RAG / AI Overviews / assistants). ai-train=no: do not train models on this content.
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# Search engine crawlers — explicitly allowed
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# Social media crawlers — explicitly allowed
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# AI / LLM crawlers — allowed sitewide EXCEPT the legal suite. /legal/ is opted
# out of AI training and AI grounding (compliant crawlers honour Disallow); it
# stays available to the search engines named above so people can still find it.
# Scraping, crawling and training on Helixar content are separately prohibited
# by the Website Terms of Use (/legal/website-terms/) and Acceptable Use Policy
# (/legal/acceptable-use/).
User-agent: GPTBot
Disallow: /legal/
Allow: /

User-agent: OAI-SearchBot
Disallow: /legal/
Allow: /

User-agent: ChatGPT-User
Disallow: /legal/
Allow: /

User-agent: ClaudeBot
Disallow: /legal/
Allow: /

User-agent: anthropic-ai
Disallow: /legal/
Allow: /

User-agent: CCBot
Disallow: /legal/
Allow: /

User-agent: PerplexityBot
Disallow: /legal/
Allow: /

User-agent: YouBot
Disallow: /legal/
Allow: /

User-agent: Google-Extended
Disallow: /legal/
Allow: /

# Archive crawlers — blocked
User-agent: ia_archiver
Disallow: /

Sitemap: https://helixar.ai/sitemap.xml
Sitemap: https://helixar.ai/news-sitemap.xml