# ============================================================
# ardinois.com — robots.txt
# Posture: search = yes | AI retrieval/grounding = yes | AI training = no
# Rights reserved under Art. 4 EU Directive 2019/790 (TDM opt-out)
# ============================================================

# --- Content signals (applies to all agents) ---
User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=no
Allow: /

# ============================================================
# AI RETRIEVAL / SEARCH CRAWLERS — ALLOWED
# These fetch live pages to ground and cite AI answers (GEO).
# ============================================================

# OpenAI (ChatGPT search + live user fetches)
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic (Claude search + live user fetches)
User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: ClaudeBot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google AI surfaces (Gemini grounding, AI Overviews)
User-agent: Google-Extended
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Meta AI
User-agent: meta-externalagent
Allow: /

# ============================================================
# TRAINING-ONLY / BULK SCRAPERS — BLOCKED
# Consistent with ai-train=no. These primarily ingest for
# model training rather than live citation.
# ============================================================

User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

# ============================================================
# TRADITIONAL SEARCH — unrestricted (Googlebot, Bingbot, etc.)
# Default allow for everything not named above.
# ============================================================

User-agent: *
Allow: /

Sitemap: https://ardinois.com/sitemap-index.xml