# New-U Research Compounds
# Crawl policy updated 2026-11-04

Sitemap: https://new-u.io/sitemap-index.xml
Sitemap: https://new-u.io/sitemap.xml

# Explicitly allowed search, assistant and social retrieval agents
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: GPTBot
User-agent: OAI-AdsBot
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Grok
User-agent: GrokBot
User-agent: xAI-Grok
User-agent: Grok-DeepSearch
User-agent: Twitterbot
User-agent: XBot
User-agent: DuckDuckBot
User-agent: DuckAssistBot
User-agent: SerpApi
User-agent: Googlebot
User-agent: Google-Extended
User-agent: Google-CloudVertexBot
User-agent: Gemini-Deep-Research
User-agent: Google-NotebookLM
User-agent: Google-GeminiNotebook
User-agent: GoogleAgent-URLContext
User-agent: Bingbot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: Meta-ExternalFetcher
User-agent: MistralAI-User
User-agent: YouBot
User-agent: kagi-fetcher
User-agent: YandexBot
User-agent: LinkedInBot
User-agent: facebookexternalhit
User-agent: TavilyBot
User-agent: FirecrawlAgent
User-agent: Diffbot
Allow: /robots.txt
Allow: /sitemap.xml
Allow: /sitemap-*.xml
Allow: /llms.txt
Allow: /llm.txt
Allow: /llms/
Allow: /llms-full.txt
Allow: /ai
Allow: /ai-instructions.txt
Allow: /blog/rss.xml
Allow: /_vercel/insights/script.js
Allow: /_vercel/speed-insights/script.js
Disallow: /admin
Disallow: /distributor
Disallow: /account
Disallow: /login
Disallow: /logout
Disallow: /register
Disallow: /checkout
Disallow: /pay
Disallow: /payment
Disallow: /confirm-payment
Disallow: /order
Disallow: /orders
Disallow: /thank-you
Disallow: /api/
Disallow: /webhook
Disallow: /internal/
Disallow: /operator
Disallow: /packer/
Disallow: /fulfillment
Disallow: /dispatch/
Disallow: /metrics/
Disallow: /debug/
Disallow: /deployment-center
Disallow: /email-dashboard
Disallow: /email-preferences
Disallow: /staff
Disallow: /forum/moderation
Disallow: /dev/
Disallow: /healthz
Disallow: /readyz
Disallow: /_vercel/
Disallow: /search?
Disallow: /*?sort=
Disallow: /*?filter=
Disallow: /*?variant=
Disallow: /*?session=
Disallow: /*?checkout=
Disallow: /*?payment=
Disallow: /*?orderRef=
Disallow: /*?email=
Allow: /

# Default policy for search engines, AI assistants and social preview agents
User-agent: *
Allow: /robots.txt
Allow: /sitemap.xml
Allow: /sitemap-*.xml
Allow: /llms.txt
Allow: /llm.txt
Allow: /llms/
Allow: /llms-full.txt
Allow: /ai
Allow: /ai-instructions.txt
Allow: /blog/rss.xml
Allow: /_vercel/insights/script.js
Allow: /_vercel/speed-insights/script.js
Disallow: /admin
Disallow: /distributor
Disallow: /account
Disallow: /login
Disallow: /logout
Disallow: /register
Disallow: /checkout
Disallow: /pay
Disallow: /payment
Disallow: /confirm-payment
Disallow: /order
Disallow: /orders
Disallow: /thank-you
Disallow: /api/
Disallow: /webhook
Disallow: /internal/
Disallow: /operator
Disallow: /packer/
Disallow: /fulfillment
Disallow: /dispatch/
Disallow: /metrics/
Disallow: /debug/
Disallow: /deployment-center
Disallow: /email-dashboard
Disallow: /email-preferences
Disallow: /staff
Disallow: /forum/moderation
Disallow: /dev/
Disallow: /healthz
Disallow: /readyz
Disallow: /_vercel/
Disallow: /search?
Disallow: /*?sort=
Disallow: /*?filter=
Disallow: /*?variant=
Disallow: /*?session=
Disallow: /*?checkout=
Disallow: /*?payment=
Disallow: /*?orderRef=
Disallow: /*?email=
Allow: /

# Owner policy: block bulk-training and low-value scraper agents
User-agent: CCBot
User-agent: Bytespider
User-agent: Meta-ExternalAgent
User-agent: cohere-ai
User-agent: AhrefsBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: PetalBot
User-agent: Apify
User-agent: ScrapingBee
User-agent: Zyte
Disallow: /