# Avant One Marketing Site (avantone.io)
# This robots.txt applies to the marketing domain only.
# The app domain (app.avantone.io) has separate noindex handling via meta tags.

# =============================================================================
# MARKETING SITE (avantone.io) - FULLY INDEXABLE
# =============================================================================

# Google
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Googlebot-Image
Allow: /

# Bing
User-agent: Bingbot
Allow: /
Crawl-delay: 1

# Social platforms
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

# Other search engines
User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

# Job aggregator bots (for public careers pages)
User-agent: IndeedBot
Allow: /careers
Allow: /jobs/

User-agent: CareerjetBot
Allow: /careers
Allow: /jobs/

User-agent: Jooble
Allow: /careers
Allow: /jobs/

User-agent: TalentBot
Allow: /careers
Allow: /jobs/

User-agent: JobbotsSpider
Allow: /careers
Allow: /jobs/

# AI/LLM crawlers - allow indexing of marketing content
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Anthropic-AI
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Cohere-ai
Allow: /

# Default: allow all other bots
User-agent: *
Allow: /

# =============================================================================
# DISALLOWED PATHS (authentication, admin, API)
# =============================================================================
# These paths should not be indexed even on the marketing site
Disallow: /login
Disallow: /register
Disallow: /reset-password
Disallow: /accept-invitation
Disallow: /dashboard
Disallow: /settings
Disallow: /api/
Disallow: /_next/
Disallow: /admin/

# =============================================================================
# SITEMAPS
# =============================================================================
# Submit this one to Search Console — it lists every sitemap below plus one
# per org's job-site subdomain.
Sitemap: https://www.avantone.io/sitemap-index.xml

# Marketing content (content/**): industries, platform, solutions, compare,
# blog, insights. Generated at build time by generate-sitemap-pages.mjs.
Sitemap: https://www.avantone.io/sitemap-pages.xml

# Job listings for the base marketing-site job board.
Sitemap: https://www.avantone.io/sitemap.xml

# =============================================================================
# HOST DIRECTIVE
# =============================================================================
# Preferred domain for indexing
Host: https://www.avantone.io