# CONNECT AHEAD — ROBOTS.TXT
# Transparent crawler permissions distinguishing live retrieval agents from model training crawlers

# -----------------------------------------------------------------------------
# 1. Standard Web Search Crawlers (Traditional Search Engines)
# -----------------------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# -----------------------------------------------------------------------------
# 2. Live AI Search & Retrieval Agents (Fetch real-time answers on behalf of users)
# -----------------------------------------------------------------------------
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

# -----------------------------------------------------------------------------
# 3. Foundation Model Training Crawlers (Offline dataset collection)
# -----------------------------------------------------------------------------
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Google-Extended
Allow: /

# -----------------------------------------------------------------------------
# 4. Default Rule for All Other Crawlers
# -----------------------------------------------------------------------------
User-agent: *
Allow: /
Disallow: /docs/
Disallow: /scratch/
Disallow: /tmp/

# Canonical Sitemap & LLM Manifest
Sitemap: https://connectahead.co.uk/sitemap.xml