# ====================================================================
# 1. AI SEARCH & CITATIONS — allow (drives link traffic to the shop)
# ====================================================================
# Real-time search/answer bots that cite and link back. We want these to
# crawl public content, but keep them out of the same operational/private
# paths we hide from Google (one shared group — no per-bot duplication).

User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
Allow: /
Disallow: /admin/
Disallow: /buy
Disallow: /cancelled/
Disallow: /checkout/
Disallow: /legal/
Disallow: /qr/
Disallow: /success/
Content-Signal: search=yes, ai-input=yes, ai-train=no

# ====================================================================
# 2. AI TRAINING CRAWLERS — block (no model training on the artwork)
# ====================================================================
# Mirrors the Cloudflare AI Crawl Control "Training" tier (ADR-019).
# Verified enforced at the edge 2026-08-03 — these return 403 before
# robots.txt is read. Section 1 above maps to the "Search" tier, except
# ChatGPT-User which Cloudflare classes as "Agent"; both are allowed.
# Google-Extended / Applebot-Extended are training opt-outs only — they
# do NOT affect Googlebot search indexing or Applebot search, and no HTTP
# request ever arrives with those user-agents (robots.txt tokens only).

User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Meta-ExternalAgent
User-agent: CCBot
User-agent: Bytespider
Disallow: /
Content-Signal: search=no, ai-input=no, ai-train=no

# ====================================================================
# 3. EVERYONE ELSE — standard search engines (Google, Bing, etc.)
# ====================================================================
# Keep human-facing search fully crawlable; keep operational and
# private paths out of the index.

User-agent: *
Allow: /
Disallow: /admin/
Disallow: /buy
Disallow: /cancelled/
Disallow: /checkout/
Disallow: /qr/
Disallow: /success/
Content-Signal: search=yes, ai-input=yes, ai-train=no

Sitemap: https://nadiapoe.co.uk/sitemap-index.xml