# squarelight.ai — crawl policy
# Updated 2026-09-27. AI-training notice: /.well-known/ai.txt · AI context: /llms.txt
#
# A crawler obeys only the most specific group that names it, so every group
# below repeats the rules it needs; nothing is inherited from "User-agent: *".
# Noindex pages (legal drafts, checkout results, design-system) stay crawlable
# on purpose so crawlers can read their noindex tag.

# AI model-training crawlers — not authorized to use site content for training.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Meta-ExternalAgent
User-agent: FacebookBot
User-agent: Bytespider
User-agent: cohere-training-data-crawler
User-agent: Diffbot
User-agent: Timpibot
Disallow: /

# AI search and user-requested retrieval — allowed so answers can cite the site.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: Claude-Web
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Meta-ExternalFetcher
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: YouBot
User-agent: Amazonbot
User-agent: cohere-ai
Allow: /
Disallow: /admin
Disallow: /api/
Allow: /api/notion-image

# Search engines and link previews.
User-agent: Googlebot
User-agent: Bingbot
User-agent: Yeti
User-agent: Daumoa
User-agent: DuckDuckBot
User-agent: Applebot
User-agent: Twitterbot
User-agent: facebookexternalhit
User-agent: LinkedInBot
Allow: /
Disallow: /admin
Disallow: /api/
Allow: /api/notion-image

User-agent: *
Allow: /
Disallow: /admin
Disallow: /api/
Allow: /api/notion-image

Sitemap: https://squarelight.ai/sitemap.xml