# ==============================
# LinkTek.com robots.txt
# Goal: Max AI visibility (EEAT) while keeping noise low
# Last updated: 2025-08-22
# ==============================

# Block Wayback Machine (keep)
User-agent: ia_archiver
Disallow: /

# ------------------------------
# Global rules for most crawlers
# ------------------------------
User-agent: *
# Block specific paths
Disallow: /calendar/action*
Disallow: /events/action*
Disallow: /stats/

# Block query-string HTML URLs only (duplicate content)
Disallow: /*?*=


# Allow essential assets
Allow: /*.css
Allow: /*.js

# ------------------------------
# AI & search assistant crawlers
# We WANT visibility (training + discovery)
# These agents get full access, overriding global rules
# ------------------------------

# OpenAI model training & browsing
User-agent: GPTBot
Allow: /

# OpenAI Search / SearchGPT indexer
User-agent: OAI-SearchBot
Allow: /

# Google’s AI training control (does NOT affect normal Googlebot indexing)
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: Claude-User
Allow: /

# Apple (search & AI)
User-agent: Applebot
Allow: /
User-agent: Applebot-Extended
Allow: /

# Common Crawl (widely consumed by AI researchers)
User-agent: CCBot
Allow: /

# Microsoft/Bing (for Copilot ecosystem)
User-agent: Bingbot
Allow: /

# ------------------------------
# Sitemaps
# ------------------------------
Sitemap: https://www.linktek.com/sitemap_index.xml