How it discovers and cites pages
Copilot doesn't crawl the web itself. When it needs web data, it generates short search queries from your prompt, sends them to the Bing search service, and composes an answer grounded in what Bing returns — Microsoft describes Copilot Chat as 'grounded in data from the public web from the Bing search service.' Since Copilot Search launched in April 2025, and more so after the late-2025 Fall Release, sources are cited prominently with inline links and a full list of every link used. There is no separate Copilot crawler: bingbot does the crawling, so being indexed in Bing is the practical gateway. Publishers get page-level controls — NOARCHIVE keeps content out of Copilot responses and grounding, NOCACHE limits Copilot to your URL, title and snippet — and since February 2026, Bing Webmaster Tools' AI Performance report shows how often your content is cited across Copilot and Bing's AI summaries.
What this means for getting cited
To be cited by Microsoft Copilot, your page first has to be reachable through the index it draws on (Bing (web grounding via the Bing search service)) and crawlable by the relevant bots, then it has to answer the user's question clearly enough to be quoted. I test exactly these variables at HZ and publish what moves the needle.