Microsoft Copilot Optimisation
Last updated
Microsoft Copilot generates answers by retrieving content from the Bing index. The optimisation principles overlap significantly with ChatGPT Search (both draw from the same index) but Copilot has distinct integration points, a B2B-weighted audience, and the only first-party citation measurement tool available from any major AI search platform.
How does Copilot retrieve content?
When a user asks Copilot a question, Copilot does not simply search for that exact query. It generates a set of internal reformulations, called grounding queries, and retrieves the most relevant passages from pages in the Bing index. A user asking “what’s the best approach to international hreflang” might trigger grounding queries like “hreflang implementation guide,” “hreflang errors common mistakes,” and “international SEO hreflang best practices.”
This has a practical consequence: content that covers a topic thoroughly across multiple angles is more likely to be retrieved and cited than content that targets a single exact query phrase.
The Bing index is the entry point
Copilot cannot cite content that is not indexed in Bing. A page that ranks well in Google but has not been submitted to, or crawled by, Bing is invisible to Copilot. The first step for any Copilot optimisation effort is confirming that key pages are indexed in Bing.
Submit your sitemap through Bing Webmaster Tools and use the URL Inspection tool to verify indexing status for priority pages. The Bing Webmaster Tools guide covers this in full.
Content formatting
Copilot extracts passages rather than entire pages, so the structure of individual sections matters as much as overall page quality.
Answer first. Place the core answer in the first one to two sentences of each section, not at the end of a long explanation. Copilot retrieves openings and summary sentences more reliably than conclusions.
Question-formatted headings. H2 and H3 headings phrased as questions (“How does Copilot choose which sources to cite?”) act as retrieval signals. They match the question-like nature of conversational queries and make it easier for Copilot to identify which passage answers which question.
One point per paragraph. Passages of 50 to 150 words covering a single claim or concept are easier to extract accurately than long, discursive paragraphs covering multiple points.
Summary blocks on longer pages. A short TL;DR or summary section near the top of long articles provides a ready-made excerpt. Copilot frequently cites these rather than constructing a summary from body content.
Structured data
FAQPage schema lets Copilot extract question-and-answer pairs without interpreting surrounding prose. For pages that address discrete questions (product FAQs, how-to guides, policy explanations), FAQPage schema is the most direct structured data signal for AI citation.
Note: FAQPage schema no longer produces rich result visual enhancements in Google Search (deprecated in 2026), but it retains value as an extraction aid for AI engines including Copilot.
Schema.org entity markup (Organisation, Person, Product) helps Copilot identify and correctly attribute your site in responses. Accurate entity data reduces the chance of your content being misattributed or paraphrased without citation.
LinkedIn and B2B queries
Copilot draws on LinkedIn content for professional and B2B topics. This is more pronounced in Copilot than in other AI engines because of Microsoft’s ownership of LinkedIn and Copilot’s deep integration into enterprise workflows via Microsoft 365.
For B2B publishers, maintaining an active LinkedIn presence, particularly long-form articles that link back to the main site, reinforces authority on professional topics in Copilot responses. The same entity consistency matters: the organisation name on LinkedIn, the site’s About page, and Schema.org Organisation markup should all match.
Measuring with the AI Performance report
Since February 2026, Bing Webmaster Tools includes an AI Performance report.1 It shows:
- Total citations: how many times your pages have been cited in Copilot responses and Bing AI summaries during the selected period
- Grounding queries: the internal queries Copilot generated that led to your content being retrieved
- Cited pages: which specific URLs are being cited and how citation volume is trending
This is the only first-party citation measurement tool currently available from any major AI search platform. Google Search Console separates AI Overviews impressions from standard search impressions but does not show citation-level data in the same way.
The report currently shows citation volume and trend data, without click-through data from citations. Microsoft has indicated that additional metrics are planned.
Copilot’s integration points
Copilot surfaces in the Edge sidebar, as a standalone product at copilot.microsoft.com, within Windows search, and throughout Microsoft 365 applications. Each context brings a different audience and query type.
Edge sidebar queries tend to be research-oriented, often while a user is already reading a webpage. Microsoft 365 queries tend to be task-oriented: summarising documents, answering work-related questions, generating drafts. Web content cited in these contexts is more likely to be professional, reference-style material than consumer-facing content.
Optimising for Copilot is therefore not one undifferentiated task. Informational and reference content is most relevant to Edge sidebar retrieval. Authoritative, entity-clear content on professional topics is most relevant to Microsoft 365 integration.