# absolutewindowco.co.uk
# AI crawlers explicitly allowed for citation/training visibility.
# /404.html carries its own noindex meta tag (intentionally not Disallowed
# here so crawlers can still see the directive).

# ─── AI search & training crawlers (explicit allows) ──────────────────────

# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: claude-searchbot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google Gemini (separate from Googlebot search index)
User-agent: Google-Extended
Allow: /

# Apple Intelligence (Applebot-Extended is opt-out-by-omission;
# explicit Allow signals affirmative consent for AI training)
User-agent: Applebot-Extended
Allow: /

# Microsoft Bing & Copilot
User-agent: Bingbot
Allow: /

# Common Crawl (foundation training corpus for many LLMs)
User-agent: CCBot
Allow: /

# ByteDance / Doubao
User-agent: Bytespider
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

# ─── Default fallback for everything else ─────────────────────────────────

User-agent: *
Allow: /

Sitemap: https://www.absolutewindowco.co.uk/sitemap.xml