When Microsoft Clarity made AI citations available to all users, it opened up a new playing field for SEOs to leverage AI visibility data. Finally, we can see the “basic questions” that the AI engine uses to pull our content.
It raises a big question because this is a Microsoft tool: Is insight useless if your audience doesn’t touch the Bing ecosystem?
Microsoft Clarity Grounding Questions
When you ask Copilot a question, it translates your words into simple search terms called grounding queries to find facts on the web before you answer. You can use this data to improve your website and content.
- Finding spaces where your content doesn’t match what AI is searching for.
- Simplifying pages that AI reads but doesn’t link to.
- Using these simple properties will help your Google search results.
Pilot Vs. Gemini
Both Copilot and Gemini use add-on recovery methods. Instead of generating answers using only pre-trained parameters, they dynamically queried external search indexes for real-time data, which they then used as context to support their final answers.
| A feature | Microsoft Copilot | Google Gemini |
| The structure | It uses a query translator, Bing index search, and OpenAI models to write the final script. | It uses query translator, Google Search, and Google Gemini models to write the final text. |
| Drainage Sources | It uses the Bing and Microsoft Graph index to scan web pages, emails, and Microsoft 365 files. (With permissions enabled) | It uses Google Search and Google Workspace to scan web pages, Google Drive files, and Gmail. (With permissions enabled) |
| Combining Answers | It focuses on specific answers. Uses structured lists, tables, and bullet points to quickly display facts. | Focuses on creative, conversational responses. It is designed to handle text, images, and code at the same time. |
Do Rankings on Bing Matter?
Yes (Integration).
One of my websites was performing very well on Copilot, with over 36,000 citations across all queries. Now, Clarity doesn’t give you the information/questions itself, but it gives you Response questions (basic questions and key phrases used to retrieve your site’s content).
My website has a history, running for years with a previous domain that was put together in 2019, and boasts over 1,000 topics. Given that Google doesn’t send much traffic, and third-party SEO tools often call it spam because of non-English backlinks (includes search engines like Baidu, CocCoc, SwissCows, which attract an international audience), I never expected 36,000 citations.
So, why is Copilot so popular? I took 147 basic queries and tracked their position on Google and Bing.
Of the 147 questions, Bing ranked all but 6, most of them in the driving position (top 20). Google didn’t rate a single one.
So, If This Is So Dependent on Bing Indexing, Is Clarity Data Useful Outside of the Bing/Microsoft Ecosystem?
Because this is a Microsoft tool, the background data that feeds this dashboard primarily captures how your site has been cited in all of Microsoft’s AI areas (such as Copilot search and Bing’s productive search).
It doesn’t give you a direct window into how OpenAI’s ChatGPT (using its own search), Google Gemini, or Perplexity are citing your links, because those platforms don’t share their internal Microsoft logs.
And historically, we as an industry have been ignoring Bing.
Even though the data collection source is skewed toward Microsoft’s AI engine, the data itself is highly transferable to your broader, platform-agnostic AI optimization strategies.
Can We Take Other LLMs to Return Data in the Same Way?
AI engines, whether Google Gemini or Microsoft Copilot, use the same RAG frameworks to retrieve data.
If the Bing ecosystem flags that a certain page on your site has a high “Authority Share” value for a complex query, then that page is well-designed for AI use (clear tables, character scores, specific answers). The data suggests that you can repeat that formatting throughout your site to appeal to Google Gemini as well.
However, this can be argued as some research suggests that the similarity between LLMs is subject to positional bias, and some may use the SDSR method rather than the RAG.
SEO researchers have also discovered that ChatGPT has started using Google Search as a fallback, where it was originally Bing.
In summary
If your audience doesn’t touch the Microsoft ecosystem, this dashboard won’t give you a complete 1-to-1 display of your complete AI traffic, but it doesn’t make the data useless.
What the fundamental questions reveal is how AI systems break down user intent into search terms that can be retrieved. That process is broadly consistent across platforms, even if the underlying indicators differ. Page quotes that benefit from Copilot do something structurally right with clear answers, well-scoped topics, relevant content and how AI engines translate questions into questions. Bing’s dependencies tell you where the data comes from. Structural patterns tell you something transferable.
The gap data is equally instructive. Pages that rank for your site in Bing that don’t show up as basic queries show a mismatch. It may be that the content is not designed for AI retrieval, or the topic is not AI engines that support continuous responses.
Treat Clarity’s Citations dashboard as a useful proxy or “lab space” and window into how LLMs read, refine/categorize, and credit your website content. Even if Copilot isn’t your primary source of AI traffic, the emerging patterns are worth paying attention to.
Additional resources:
Featured Image: Prostock-studio/Shutterstock
