# triangle.digital - crawl policy
# Search, answer-engine retrieval, and model training crawlers are all welcome.
# Rules first, then the content signal. An empty Disallow is the canonical
# "allow everything" record and keeps naive validators green.
User-agent: *
Allow: /
Disallow:
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# retrieval / citation
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Applebot
User-agent: DuckAssistBot
User-agent: bingbot
User-agent: Googlebot
Allow: /
Disallow:

# training
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: CCBot
User-agent: meta-externalagent
User-agent: Amazonbot
Allow: /
Disallow:

Sitemap: https://triangle.digital/sitemap.xml

# mxAURA publishes this hub's article URLs as https://triangle.digital/insights/{slug}/.
# A sitemap hosted off-domain is only honoured when the site it describes references it
# from robots.txt, which is what this line does. Without it the article URLs are only
# discoverable through JavaScript-rendered links.
Sitemap: https://hubs.mxaura.ai/e/f3ba3399d21c490306697a06/sitemap.xml
Sitemap: https://hubs.mxaura.ai/e/c3de36438d3e2055d69e485e/sitemap.xml
Sitemap: https://hubs.mxaura.ai/e/eaec5c2a9d829664194fa006/sitemap.xml