# START YOAST BLOCK # --------------------------- # User-agent: * # Disallow: Sitemap: https://samuelautomation.com/sitemap_index.xml # --------------------------- # END YOAST BLOCK # Default search crawler policy: allow public site discovery. User-agent: * Allow: / # WordPress/API utility endpoint often needed by themes and forms. Allow: /wp-admin/admin-ajax.php # Keep low-value, duplicate, private, or infinite URL spaces out of crawl paths. Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /search Disallow: /*?s= Disallow: /*?sort= Disallow: /*?filter= Disallow: /*?utm_ Disallow: /*?fbclid= Disallow: /*?gclid= Disallow: /*?sessionid= # AI-search discovery: allow public content, but keep private/duplicate paths blocked. User-agent: OAI-SearchBot User-agent: ChatGPT-User User-agent: PerplexityBot User-agent: Perplexity-User Allow: / Allow: /wp-admin/admin-ajax.php Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /search Disallow: /*?s= Disallow: /*?sort= Disallow: /*?filter= Disallow: /*?utm_ Disallow: /*?fbclid= Disallow: /*?gclid= Disallow: /*?sessionid= # AI-search discovery: allow public content, but keep private/duplicate paths blocked. User-agent: Claude-User User-agent: Claude-SearchBot Allow: / Allow: /wp-admin/admin-ajax.php Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /search Disallow: /*?s= Disallow: /*?sort= Disallow: /*?filter= Disallow: /*?utm_ Disallow: /*?fbclid= Disallow: /*?gclid= Disallow: /*?sessionid= # OpenAI training crawler: blocked by default. Change to Allow: / if Samuel's policy permits model-training use. User-agent: GPTBot Disallow: / # Google AI usage control. This does not block Google Search crawling. # Change to Allow: / if Samuel's policy permits Gemini/Vertex AI usage. User-agent: Google-Extended Disallow: / # Anthropic crawler. Change to Allow: / if Samuel's policy permits it. User-agent: ClaudeBot Disallow: / # Common Crawl is often used by downstream AI/data systems. # Change to Allow: / if open dataset inclusion is desired. User-agent: CCBot Disallow: /