Skip to content

Measurement

News

Bing Webmaster Tools now groups AI grounding queries by topic and shows where other sites are cited

A beta tab in Bing Webmaster Tools groups the AI grounding queries a site appears for into topics and lists queries where other sites are cited instead. Microsoft says to treat the figures as directional signals, not precise counts.

Key takeaways

  • On Oct. 13, 2026, Microsoft added a Topics Portfolio beta to the AI Performance report in Bing Webmaster Tools. It groups the grounding queries where a site appears into thematic clusters.
  • Each topic shows Topic Size (approximate citations across all sites), Sites Cited and Queries, plus “Opportunity Queries” where “other sites appear and yours does not.”
  • Microsoft says the classification is AI-generated, the figures are approximate, opportunity volumes are shown as ranges, and small sites may not see the feature at all.

Direct answer: Topics Portfolio is a beta view in the AI Performance report of Bing Webmaster Tools. It groups a site’s AI grounding queries into topics and lists queries in those topics where other sites appear and the site does not. Microsoft says to “treat the numbers as directional signals for planning, not as a precise ledger.”

What happened: Microsoft’s Krishna Madhavan, Saral Nigam and Vivek Jain announced Topics Portfolio in an Oct. 13, 2026, post on the Bing Webmaster blog. It is a new tab inside AI Performance, next to Citations & Pages.

What the report shows

  • Topic table. Topic, Topic Size (“the approximate total citations across all sites for this topic over the selected period”), Sites Cited (“how crowded the topic is”) and Queries.
  • Top Opportunity Queries. Microsoft describes these as “the strongest queries across your whole portfolio where other sites appear and yours does not.” Citation volumes are shown as ranges.
  • Topic detail. Three cards (Topic Size, your citations in the topic, number of queries), then two tables: Your Grounding Queries and Opportunity Queries.
  • Personalized. Topics and opportunity queries “are surfaced from your own presence and activity in AI Search, not from a generic ecosystem list.”
  • Time window. One, two or three months.

Why it matters

This is first-party Microsoft data about grounding in its own AI search. The new view adds topic-level context: “how big each topic is, and how crowded it is with other sites.” Microsoft states the limits itself: AI-generated topic labels, approximate figures, ranges for opportunity volumes, and smaller sites that “may see a shorter list or may not even see this feature.” Microsoft’s help page says the report covers three AI surfaces: Microsoft Copilot, AI-generated summaries in Bing, and select partner AI integrations. The post also notes that branded queries for a competitor can be “listed as an opportunity.”

Our view: The Oct. 13 post describes citation and query counts and does not mention clicks, and Microsoft’s help page says a citation “does not represent traffic, clicks, or user engagement.” The view measures presence in AI answers, not traffic. Because Microsoft says the topic labels are AI-generated, treat opportunity queries as leads to check, not as targets.

What we don’t know yet

  • How Topic Size and Sites Cited are computed beyond “approximate.” The post gives no method.
  • What minimum activity a site needs to see the tab. The post says only that topics with “insufficient site presence or insufficient ecosystem activity are not shown.”

What to do now

  1. In Bing Webmaster Tools, open AI Performance and look for the Topics tab; if it is missing, Microsoft says your site may not have enough data yet.
  2. Before acting on an opportunity query, check whether it is a competitor’s brand name, which Microsoft says can appear there.
  3. Use the thumbs up and down controls to flag wrong topics; Microsoft says that feedback goes to the classification team.

Update log: Oct. 28, 2026 — First published.
Oct. 28, 2026 — Added the AI surfaces the report covers and Microsoft’s statement that a citation does not represent clicks, both from the AI Performance help page [2]; corrected a quote (“listed as an opportunity”).

Sources

[1] Madhavan, K., Nigam, S., & Jain, V. (2026, Oct. 13). “Introducing Topics Portfolio (Beta) in AI Performance.” Bing Webmaster Blog. Accessed Oct. 28, 2026. https://blogs.bing.com/webmaster/2026/10/introducing-topics-portfolio-beta-in-ai-performance/

[2] Microsoft. “AI Performance in Bing Webmaster Tools.” Bing Webmaster Tools Help. Accessed Oct. 28, 2026. https://www.bing.com/webmasters/help/ai-performance-9f8e7d6c

How this was made

Prepared with AI assistance from the sources cited above. Editorial review by Nhi Phan (editor) and fact-checking by Jackies continue after publication; any change will be recorded in the update log and in our Corrections Policy and Log at https://aivisibilityjournal.com/corrections/

More from AVJ

Get the next one in your inbox.

The Visibility Brief: weekly, evidence-led, free. Every Friday.