User-agent: *

# AI agent discovery files
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /.well-known/mcp/server.json
Allow: /.well-known/agent.json

# Sitemap location - ONLY these URLs should be indexed
Sitemap: https://gleanmark.com/sitemap.xml

# ===========================================
# ALLOW PUBLIC CONTENT PAGES
# ===========================================

# Search pages with query params are allowed (served via Prerender.io with correct meta tags)
# Only sitemap search URLs get indexing priority
Allow: /search
Allow: /trademark-search
Allow: /nice-class/

# Entity pages - all publicly accessible
Allow: /owner/

# Firm and correspondent pages (top entries in sitemap)
# Legacy /firm/ and /correspondent/ paths redirect to /entity/ equivalents
Allow: /entity/firm/
Allow: /entity/correspondent/

# TTAB proceeding pages (active proceedings in sitemap)
Allow: /ttab/

# ===========================================
# BLOCK PRIVATE/ADMIN AREAS
# ===========================================
Disallow: /admin/
Disallow: /api/
Disallow: /auth/
Disallow: /.well-known/
Disallow: /dashboard/
Disallow: /portfolio/
Disallow: /alerts/
Disallow: /settings/
Disallow: /account/

# ===========================================
# BLOCK AUTHENTICATION PAGES
# ===========================================
Disallow: /register
Disallow: /forgot-password
Disallow: /login
Disallow: /reset-password

# Block old blog URLs (redirected to /insights/)
Disallow: /blog/

# ===========================================
# ALLOW STATIC ASSETS
# ===========================================
Allow: /images/
Allow: /*.css
Allow: /*.js