# NeoHireX robots.txt
# Last updated: 2026-04-20

# Default: allow all
User-agent: *
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /internal/
Disallow: /.json$
Disallow: /?utm_
Disallow: /*?ref=

# AI / generative crawlers — explicitly allowed for citations in ChatGPT, Claude, Perplexity, Google AI Overviews
User-agent: GPTBot
Allow: /
Disallow: /api/
Disallow: /admin/

User-agent: ClaudeBot
Allow: /
Disallow: /api/

User-agent: Claude-Web
Allow: /
Disallow: /api/

User-agent: anthropic-ai
Allow: /
Disallow: /api/

User-agent: PerplexityBot
Allow: /
Disallow: /api/

User-agent: Google-Extended
Allow: /
Disallow: /api/

User-agent: CCBot
Allow: /
Disallow: /api/

User-agent: Applebot-Extended
Allow: /
Disallow: /api/

# Block aggressive scrapers
User-agent: Bytespider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

# Sitemaps
Sitemap: https://neohirex.ai/sitemap.xml