# ---------- AI training bots: BLOCK ----------
# These crawlers collect content to train large language models or
# image-generation models. We do not permit training use of this site.
 
User-agent: GPTBot
Disallow: /
 
User-agent: ClaudeBot
Disallow: /
 
User-agent: anthropic-ai
Disallow: /
 
User-agent: Google-Extended
Disallow: /
 
User-agent: CCBot
Disallow: /
 
User-agent: FacebookBot
Disallow: /
 
User-agent: Meta-ExternalAgent
Disallow: /
 
User-agent: Applebot-Extended
Disallow: /
 
User-agent: Bytespider
Disallow: /
 
User-agent: Amazonbot
Disallow: /
 
User-agent: cohere-ai
Disallow: /
 
User-agent: Diffbot
Disallow: /
 
User-agent: ImagesiftBot
Disallow: /
 
User-agent: Omgilibot
Disallow: /
 
User-agent: PerplexityBot-Train
Disallow: /
 
User-agent: AI2Bot
Disallow: /
 
User-agent: Timpibot
Disallow: /
 
User-agent: PanguBot
Disallow: /
 
User-agent: ChatGPT-User-Train
Disallow: /
 
# ---------- AI search and citation bots: ALLOW ----------
# These crawlers fetch pages on demand to answer user queries with citations.
# We want to be cited as a Melbourne photographer in AI search results.
 
User-agent: OAI-SearchBot
Allow: /
 
User-agent: ChatGPT-User
Allow: /
 
User-agent: PerplexityBot
Allow: /
 
User-agent: Perplexity-User
Allow: /
 
User-agent: Claude-SearchBot
Allow: /
 
User-agent: Claude-User
Allow: /
 
User-agent: Claude-Web
Allow: /
 
User-agent: DuckAssistBot
Allow: /
 
User-agent: YouBot
Allow: /
 
User-agent: MistralAI-User
Allow: /
 
# ---------- Default policy for all other bots ----------
# Standard search engines and unspecified crawlers can access the site.
 
User-agent: *
Allow: /
Disallow: /administrator/
Disallow: /cache/
Disallow: /cli/
Disallow: /components/
Disallow: /includes/
Disallow: /installation/
Disallow: /language/
Disallow: /layouts/
Disallow: /libraries/
Disallow: /logs/
Disallow: /modules/
Disallow: /plugins/
Disallow: /tmp/
 
# ---------- LLM discovery files ----------
# These files describe the site for AI tools that support llms.txt.
 
Allow: /llms.txt
Allow: /llms-full.txt
 
# ---------- Sitemap ----------
Sitemap: https://lucneves.com/component/osmap?view=xml&id=1&format=xml