Segoznac: Bing AI Report reveals Insights Intent Classification & Cited-By

Key Takeaways:

• Segoznac analyzed the Bing AI Report Code and found an Intent Classification, a Cited By Dimension as well as a Compare Mode

  • Intent Classification shows 13 intents: Alongside "Navigational" and "Informational Search", you'll find "Learning and Problem Solving", "Creation", "Planning", "Comparison", "Entertainment", "Small Talk."

  • CitedBy Dimension could

    1. either be a breakdown into the different data sources or rather AI features such as Bing Search, Bing Chat, Partner Integrations, Windows 360 integration etc.

    2. or be an authority metric for the citation of the source e.g. in the web

• In general, the data of the report is nice to have - especially as its the first of its kind showing data for AI features - However the data quality is limited and it is almost impossible to draw conclusions, because:

  1. only shows number of citations for gournding, no position within cited sources nor link impressions within the answer

  2. clearly unbalanced towards Bing Search - in accounts I've got access to a rough 90% of queries stem from Bing Search terms

  3. limited amount of Fanout-Queries - documentation even states that not the queries itself but a summarized title is reported

Sources:

• https://www.linkedin.com/posts/resoneo_the-ai-performance-report-in-bing-webmaster-ugcPost-7429658883201085440-NBEC/

• https://www.linkedin.com/posts/hannskronenberg_das-4-intent-modell-know-do-buy-navigate-activity-7429820354476511232-WIt7/

• https://www.afaik.de/wie-klassifizieren-generative-engines-nutzer-intents/

• https://blogs.bing.com/webmaster/February-2026/Introducing-AI-Performance-in-Bing-Webmaster-Tools-Public-Preview