# llms.txt — Guidance for AI/LLM Crawlers
# Site: https://doublejautonv.com
# Effective: 2025-08-29
# Purpose: Clarify how AI systems can use site content in addition to robots.txt

site: https://doublejautonv.com
contact: info@doublejautonv.com           # Update this with the official contact email if different
sitemap: https://doublejautonv.com/sitemap.xml  # Please replace if your actual sitemap is available at a different path

# ---------- Default policy ----------
default:
  training: disallow            # AI model training or fine-tuning is not permitted
  fine_tuning: disallow
  embeddings: disallow
  summarization: allow          # Short summaries allowed with proper attribution
  cache: 7d                     # Caching permitted for up to 7 days
  retention: 0d                 # Do not retain raw content beyond cache
  attribution: required         # Must link back to the canonical page URL
  rate_limit_rps: 1             # Respectful crawling: limit ≤1 request per second
  respect_robots_txt: true      # Follow robots.txt and meta "noai" directives
  restricted_paths:
    - /wp-admin/
    - /wp-login.php
    - /privacy-policy/
    - /terms/
    - /search/
    - /?s=
    - /cart
    - /checkout
    - /my-account
  parameters_to_strip:
    - utm_source
    - utm_medium
    - utm_campaign
    - utm_term
    - utm_content
    - gclid
    - fbclid

# ---------- Agent-specific overrides ----------
agents:
  - name: GPTBot                 # OpenAI
    training: disallow
    summarization: allow
    crawl_delay: 1

  - name: Google-Extended        # Google AI / Gemini
    training: disallow
    summarization: allow

  - name: ClaudeBot              # Anthropic
    training: disallow
    summarization: allow

  - name: PerplexityBot          # Perplexity.ai
    training: disallow
    summarization: allow
    citation: required

  - name: CCBot                  # Common Crawl
    training: disallow
    summarization: disallow

  - name: Applebot-Extended      # Apple AI
    training: disallow

  - name: Amazonbot              # Amazon
    training: disallow

  - name: Facebook-Research      # Meta research
    training: disallow

  - name: YouBot                 # You.com
    training: disallow

terms:
  license: "© Double J Auto NV (doublejautonv.com). All rights reserved. No AI training, dataset creation, embeddings, or content redistribution without explicit written permission."
  pii: "Do not collect, store, or process personal or sensitive data from this site."
  legal: "Use is subject to the site's Terms of Use and Privacy Policy."
last_updated: 2025-08-29