# ==========================================
# Loyalty Juggernaut, Inc. - robots.txt
# Last Updated: 2026-05-12
# Purpose: Control how search engines crawl and index the LJI website.
# ==========================================
# Default rules for all well-behaved crawlers
User-agent: *
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /
Disallow: /gatedcontent
Disallow: /comingsoon
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /private/
Disallow: /test/
Disallow: /beta/
Disallow: /internal/
Disallow: /*?replytocom
Disallow: /*.pdf$      # Block indexing of PDFs if not required
# Allow important sections
Allow: /$
Allow: /about/
Allow: /careers/
Allow: /contact/
Allow: /gravty/
Allow: /news/
Allow: /solutions/
Allow: /industries/
Allow: /blog/
# Sitemap locations
Sitemap: https://www.lji.io/sitemap.xml
Sitemap: https://www.lji.io/news-sitemap.xml
Sitemap: https://www.lji.io/blog-sitemap.xml
# Google-specific directives
User-agent: Googlebot
Disallow:
Allow: /
# Bing
User-agent: Bingbot
Disallow:
Allow: /
# Media files (allow image crawling for branding)
Allow: /images/
Allow: /assets/
# Block specific crawlers known for scraping or spam
User-agent: AhrefsBot
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: dotbot
Disallow: /
# Crawl-delay (optional, to reduce server load)
Crawl-delay: 5
# ==========================================
# Notes:
# - Keep Sitemap paths updated after new pages are added.
# - Use Google Search Console to test this robots.txt.
# ==========================================