# Theneo robots.txt
# Default: let search engines and AI crawlers index public pages
User-agent: *
Allow: /

# Keep non-content/system paths out of the index
Disallow: /admin/
Disallow: /dashboard/
Disallow: /editor/
Disallow: /api/
Disallow: /cart/
Disallow: /checkout/
Disallow: /ajax/
Disallow: /_*
Disallow: /search?*
Disallow: /?*

# Be polite (optional)
Crawl-delay: 5

# Block bandwidth-heavy crawlers
User-agent: AhrefsBot
Disallow: /

User-agent: PetalBot
Disallow: /

# Sitemaps (point to the canonical host)
Sitemap: https://www.theneo.io/sitemap.xml
# (Optional safety for legacy links hitting apex)
Sitemap: https://theneo.io/sitemap.xml

# Major AI crawlers (kept explicit for clarity; all are already allowed by the default group)
User-agent: GPTBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /