When Microsoft Clarity created AI Quotes Available to All Usersthis opened a new playing field for SEOs collect AI visibility data. Finally, we can see the exact “base queries” that an AI engine uses to extract our content.
This raises a huge question because this is a Microsoft tool: is the information useless if your audience doesn’t touch the Bing ecosystem?
Microsoft Clarity Grounding Queries
When you ask Copilot a question, it translates your words into simple search terms called basic queries to find facts on the web before answering. You can use this data to improve your own website and content.
- Find gaps where your content doesn’t match what the AI is looking for.
- Simplify pages that the AI reads but does not link to.
- Use these simple layouts to improve your Google search results.
Co-pilot vs. Gemini
Both Copilot and Gemini use augmented recovery approaches. Instead of generating answers using only pre-trained parameters, they dynamically query external search indexes to retrieve data in real-time, which they then use as context to support their final answers.
| Functionality | Microsoft Copilot | Google Gemini |
| Structure | Uses a query translator, Bing index search, and OpenAI models to write the final text. | Uses a query translator, Google Search, and Google Gemini templates to write the final text. |
| Extract sources | Uses Bing Index and Microsoft Graph to analyze Microsoft 365 web pages, emails, and files. (With permissions enabled) | Uses Google Search and Google Workspace to scan web pages, Google Drive and Gmail files. (With permissions enabled) |
| Summary of responses | Focuses on direct answers. It uses structured lists, tables and bullets to quickly display facts. | Focuses on creative, conversational responses. It is designed to handle text, images and code simultaneously. |
Does ranking in Bing matter?
Yes (Correlation).
One of my websites performed extremely well in Copilot, with over 36,000 citations for all queries. Now, Clarity doesn’t give you the prompts/queries themselves, but it does give you the Grounding queries (basic queries and keyphrases used to retrieve your site’s content).
My website has a years-long history with a previous domain merged in 2019 and has over 1,000 articles. Since Google barely sends traffic and third-party SEO tools often label it as spam due to non-English backlinks (it covers search engines like Baidu, CocCoc, SwissCows, attracting an international audience), I didn’t expect 36,000 citations.
So why does the co-pilot like it? I answered all 147 basic queries and tracked their rankings in Google and Bing.
Of the 147 queries, Bing ranked all but 6 of them, the majority in traffic-generating positions (top 20). Google didn’t rank any of them.
So if it relies heavily on Bing indexing, is Clarity data useful outside of the Bing/Microsoft ecosystem?
Since this is a Microsoft tool, the backend data powering this dashboard primarily captures how your site is cited on Microsoft’s AI surfaces (like Copilot and Bing generative search).
This doesn’t give you a direct window into how OpenAI’s ChatGPT (using its own search), Google Gemini, or Perplexity cites your links, because these platforms don’t share their internal grounding logs with Microsoft.
And historically, our industry has been neglecting Bing.
Even though the data collection source is oriented toward Microsoft’s AI engine, the information itself is highly transferable to your broader, platform-agnostic AI optimization strategies.
Can we assume that other LLMs retrieve data in the same way?
AI engines, whether Google Gemini or Microsoft Copilot, use Similar RAG frameworks for retrieving data.
If the Bing ecosystem reports that a specific page on your site has a high “authority share” for a complex query, that means that page is perfectly structured for AI consumption (clean tables, bullet points, direct answers). The data suggests that you can replicate this formatting on your site to attract Google Gemini as well.
However, this may be disputed as other research suggests that similarity between LLMs depends on position bias, and some may use the SDSR method rather than RAG.
SEO researchers also found that ChatGPT started using Google search as a fallbackwhen it was initially about Bing.
In summary
If your audience doesn’t touch the Microsoft ecosystem, this dashboard won’t give you a perfect reflection of your total AI traffic, but it doesn’t make the data useless.
What fundamental queries reveal is how AI systems distill user intent into retrievable search terms. This process is broadly consistent across all platforms, even when the underlying indices differ. A page that receives citations in Copilot is doing something right structurally with clear answers, well-focused topics, and content aligned with how AI engines translate questions into queries. The Bing dependency tells you where the data is coming from. Structural models tell you something more transferable.
The gap data is equally instructive. Pages that your site ranks for in Bing and never appear because basic queries report mismatch. Either the content is not structured for AI retrieval, or the topic is not one that the AI engines are actively basing answers on.
Treat Clarity’s Citations dashboard as a useful proxy or “lab environment” and open a window to how LLMs read, cut and credit your website content. Even if Copilot isn’t your primary source of AI traffic, the patterns it reveals are worth paying attention to.
More resources:
Featured image: Prostock-studio/Shutterstock
