It does have easy to access links, but the links feel like a secondary part of it, so it still feels like maybe it's not as accurate as it could be. Google's AI in search feels so intrusive and takes up so much of the page. While Google's AI mode is not available to everyone, the current search is pretty easy to beat. The interface is simplified and doesn’t show traditional web links, but users can still access them through other options. It is similar to what Google is testing with its own AI Mode for search. With the explosion of e-commerce and online search activity, every new product leaves a digital footprint, from Google Shopping listings and reviews to news mentions.
SerpApi Weekly Changelog: November 24-30, 2025
For the query “what is a spaghetti western”, there were 6 URLs cited, and all of them are in the top 10 results for that query. 28.3% of URLs were found to not rank in the top 20 results for the query. In the 18 examples observed, it appears that Bing’s Generative Search doesn’t just pull information from the top-ranking documents related to a query but also includes lower-ranking and unranked documents.
If your implementation is relatively simple and only uses the q and mkt parameters, then when you make these changes, you should see a full response come back from our endpoint at this stage. Once you have signed up and verified your account, you will need to take note of your SerpApi API key found on your dashboard so that you can use it in the following steps. If you don't already have an account with us, your first step is going to be signing up for an account (we offer a free account with 100 free searches per month). The official Bing Search API is soon to be retired on 11th August 2025 (or has already been retired depending on when you're reading this) and you may be searching for a suitable replacement. Curiously, this new experience doesn't appear to use the Copilot brand anywhere.
Microsoft unveils Bing Generative Search — enhanced with AI, it's a complete overhaul of traditional search
The new Bing Generative Search experience is rolling out to a small wave of users now, and will likely make its way gtbet casino login to more Bing users over the coming months. There's a growing concern in the industry that websites that create content for free will eventually go out of business if AI bots scrape that content to present it directly in a chat window or search page. Microsoft says it continues to evaluate the impact that AI in search is having on websites in terms of direct traffic and readership. When you purchase through links on our site, we may earn an affiliate commission.
From the analysis of link and search position data, we understand that the system does not solely select sources directly responsive to the query. I explore this in an earlier article highlighting how A Overviews explore related queries for documents to provide unique information. You might be able to gain visibility for that query by targeting related queries. For the query, “how long can elephants live”, 3 URLs were in the top 10 results, 2 were out of the top 10, and 3 did not rank at all in the top 100 results for the query.
The warning states “Generative AI is experimental.” For health- and finance- related queries, the summar directs the searcher to seek out professional advice. In AIOs, links may be provided in a carousel underneath the full summary or individual sections. Below each section of the summary, Bing also provides the sourced documents. Both BGS and AIO summaries provide links to URLs cited as sources for the summaries. Both Chrome and Safari show organic results automatically, in Microsoft Edge you have to select See more on the right.
Will each query have an AI-generated page experience as robust as these examples? So far, we have seen the BGS experience for a small number of queries. This development promises to have a sizable impact on user experience as well as the visibility and engagement with the organic performance of content.
- What insights can we gain about influencing Bing Generative Search (BGS) to display specific URLs in its summaries?
- There is a a significant difference between how organic results are presented in Microsoft Edge and other browsers.
- Currently, BGS only activates for a small number of queries.
- The Bing search URL that would be found under webPages.webSearchUrl in the official API can be found under search_metadata.bing_url in our API.
- TensorRT-LLM is a tool that helps reduce the time and cost of running large models on NVIDIA GPUs.
There is a a significant difference between how organic results are presented in Microsoft Edge and other browsers. This design reduces visual clutter, enhancing user experience by making the summary more visually accessible. The answer summaries are shifted down the page to make room for ads at the top of the page for specific queries. Bing has officially entered the AI-enhanced search arena with Bing Generative Search, their response to Google’s AI Overviews.
I identified queries that trigger BGS results by entering the query “bing generative search” in the Bing search box. This suggests that for your target query, securing a spot within the top five organic search results dramatically increases your chances of visibility in BGS summaries. Bing has stated that its answer summaries are created “by combining the power of generative AI and large language models (LLMs) with the search results page.”
Bing Generative Search: An In-Depth Analysis of Bing’s Response to Google AI Overviews
- Leveraging both Large Language Models (LLMs) and Small Language Models (SLMs) marks a significant milestone in enhancing our search capabilities.
- This design reduces visual clutter, enhancing user experience by making the summary more visually accessible.
- With the explosion of e-commerce and online search activity, every new product leaves a digital footprint, from Google Shopping listings and reviews to news mentions.
- 28.3% of URLs were found to not rank in the top 20 results for the query.
- A key distinction here is that Google uses text fragments in URLs to highlight relevant excerpts directly on the sourced document page, enhancing the specificity and transparency of the citations.
- The Bing search URL found at images.webSearchUrl in the official API can be found at inline_images.see_more_link in ours.
- This aspect of personalization in search results could customize the information to more closely address user needs.
Microsoft isn't the only company adding AI-generated results to search pages. The company claims this new experience maintains the same number of clicks to websites that traditional search does, but time will tell if that's true. This new AI search experience has been built from the ground up with this concern in mind, Microsoft says. It will break down that answer into a document index that can provide more information about particular subjects within that search query if you'd like to learn more. At the very top of the page will be an AI-generated answer created by large and small language models that have reviewed millions of sources to provide the most accurate answer. Currently available to a small subset of users, Bing Search now incorporates AI-generated answers in addition to traditional search results directly on the search page.
This new style is similar to other AI search engines like Perplexity, but Perplexity is a lot better overall in my opinion. Some answers even include direct links to the websites for more details if you want to explore further. At the bottom of these summaries, you’ll find citations to check the sources. The search just looks like a page with text, which does the job but is hard to want to use more than once.
Comparisons with Google AI Overviews
With TensorRT-LLM, the latency was reduced to 3.03 seconds per batch, and throughput increased to 6.6 queries per second per instance. TensorRT-LLM is a tool that helps reduce the time and cost of running large models on NVIDIA GPUs. Using LLMs in search systems can create problems with speed and cost. Leveraging both Large Language Models (LLMs) and Small Language Models (SLMs) marks a significant milestone in enhancing our search capabilities. “At Bing, we are always pushing the boundaries of search technology.
Significantly more is available on these organic results when using our API, so don't forget to check out the Bing Organic Results API documentation page. When available, the estimated number of results that was previously found under webPages.totalEstimatedMatches will be available under search_information.total_results in our API. The Bing search URL that would be found under webPages.webSearchUrl in the official API can be found under search_metadata.bing_url in our API. Google is also adding Gemini-based answers to search results too, which appear at the top of the search result page.
Bing Search Updates: Faster, More Precise Results
The dateLastCrawled and datePublished attributes are not available and have no equivalent, however, the datePublishedDisplayText has a similar property in our result named date. Due to the sheer number of different possible response objects available, I'm only going to cover a few of them directly in this blog post. While the previous steps have all been quite straightforward, the changes to the response format handling will likely be the most involved for you depending on how much of the data you have been using. All of the above query parameters, with the exception of textDecorations and textFormat can be used as-is or ported to use with our API. The official API's response format differs from our own so there are still changes to make, but we're part way there.
BGS adopts a more elaborate layout that takes up more real estate both horizontally and vertically on the search results page, offering detailed information about the query. Both BGS and Google’s AIOs aim to provide a summarized response to search queries, but they differ significantly in design and functionality. Organic search results are positioned to the right of the answer summary, ensuring they remain visible and relevant. Over the past few months, we have seen a mixed response to Google’s AI Overviews with summaries that range from inaccurate and false to downright disturbing and dangerous. To improve efficiency, we trained SLM models (~100x throughput improvement over LLM), which process and understand search queries more precisely.” While transformer models have served us well, the growing complexity of search queries necessitated more powerful models.”