# ==============================================================================
# Quanzix LLP Robots Exclusion Directives (https://quanzix.com)
# ==============================================================================
# Note: Granting crawler permissions provides access for public discovery,
# indexing, and retrieval, but does not guarantee indexing or citations.
#
# Conceptual Crawler Categories:
# 1. Search & Discovery Bots: Index public pages for direct web search engines.
# 2. Retrieval & Real-Time Query Bots: Assist conversational AI in answering
#    real-time user inquiries with source citations (e.g., OAI-SearchBot, Claude-SearchBot).
# 3. Model Training Bots: Crawl content for offline AI training or foundation
#    model tuning (e.g., GPTBot, Google-Extended, ClaudeBot).
# ==============================================================================

# Default Crawlers (Traditional Search Engines)
User-agent: *
Allow: /

# Google Search Engine Crawler (Indexing & Search Results)
User-agent: Googlebot
Allow: /

# OpenAI Real-Time Search & Retrieval Bot (Citations in ChatGPT Search)
User-agent: OAI-SearchBot
Allow: /

# OpenAI AI Model Training Crawler
User-agent: GPTBot
Allow: /

# Anthropic Real-Time Search Crawler (Citations in Claude Search)
User-agent: Claude-SearchBot
Allow: /

# Anthropic User-Initiated Web Retrieval (User-directed tool browsing)
User-agent: Claude-User
Allow: /

# Anthropic AI Model Training Crawler
User-agent: ClaudeBot
Allow: /

# Google AI Extended Crawler (Gemini & Vertex AI training/grounding)
# Maintained independently from standard Googlebot search indexing.
User-agent: Google-Extended
Allow: /

# Canonical Sitemap
Sitemap: https://quanzix.com/sitemap.xml