# Search indexing and user-requested citation fetches are allowed.
# Training crawl by Common Crawl (CCBot), Bytespider, GPTBot, ClaudeBot and Applebot-Extended is allowed.
# The other named training crawlers below remain blocked.
# Unnamed agents must not silently redefine this policy; named rows state the intended treatment.
# Google-Extended is allowed so Gemini and Vertex AI grounding can cite this site; it is not a search crawler.
# Canonical machine index: https://duguid.com.au/llms.txt
# Full page text: https://duguid.com.au/llms-full.txt
User-agent: *
Allow: /

User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: Claude-User
Allow: /
User-agent: Claude-Search
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Applebot
Allow: /
User-agent: YouBot
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /
User-agent: Bytespider
Allow: /
User-agent: GPTBot
Allow: /
User-agent: ClaudeBot
Allow: /
User-agent: Applebot-Extended
Allow: /

User-agent: Amazonbot
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: meta-externalagent
Disallow: /

Sitemap: https://duguid.com.au/sitemap.xml