# Servion Global Solutions - robots.txt
# Updated 29 July 2026 by MyDigipal
# Change vs previous version: AI assistant crawlers are now named explicitly and
# allowed, and llms.txt is referenced. Nothing that was previously crawlable has
# been blocked - the existing rules are unchanged.

User-agent: *
Disallow: /wp-admin/
Disallow: /healthcheck
Allow: /wp-admin/admin-ajax.php

# --- AI assistants and answer engines -------------------------------------
# Explicitly allowed so Servion can be read, understood and cited by AI
# assistants. Without a named rule these crawlers fall back to the wildcard
# above, which already allows them - naming them makes the intent unambiguous
# and is what the crawler operators document as best practice.

# OpenAI - training/crawling
User-agent: GPTBot
Allow: /

# OpenAI - ChatGPT browsing and search
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

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

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# Google - Gemini and AI Overviews (separate from Googlebot)
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Microsoft Copilot
User-agent: Bingbot
Allow: /

# Common Crawl - feeds several AI training sets
User-agent: CCBot
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Meta AI
User-agent: meta-externalagent
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# --- Sitemaps and AI-readable index ---------------------------------------
Sitemap: https://servion.com/sitemap_index.xml

# Structured summary of the site for AI assistants: https://servion.com/llms.txt