Ever since Microsoft announced the new Bing AI search and chat experience, they have been mentioning the technology “Prometheus.” Early on, Prometheus was described as a model to power the integration of Bing Search and AI chat. Now, Microsoft explained in more technical detail how Prometheus works to just that.
“We developed a proprietary technology we call Prometheus, which is a first-of-its-kind AI model that combines the fresh and comprehensive Bing index, ranking, and answers results with the creative reasoning capabilities of OpenAI’s most-advanced GPT models,” Jordi Ribas Corporate Vice President, Search & AI at Microsoft wrote.
Prometheus. As quoted above, this Prometheus technology is an AI model that Microsoft Bing created to combine the Bing index, ranking, and answers search results with OpenAI’s GPT models. This makes the ChatGPT models have fresher, almost real-time, content and data to use for its training models almost immediately.
As I understand it, the Prometheus technology works across Bing in these areas:
- Query interpretation: It takes your long-winded spoken-like query, and breaks it down into a bit size normal search type of query so Bing Chat can process it faster and find content faster.
- Bing’s index. It leverages the really fresh and comprehensive Bing search index, so Bing Chat can utilize the information that is literally up to the minute. Bing calls this the “Bing Orchestrator.”
- Bing ranking. The Bing ranking algorithm is incorporated to see what content to surface in the answer and which documents ChatGPT should use to give the answers.
- Bing answers and results. Bing can also show answers such as weather, sports scores, news boxes, local results and/or even ads from Bing Search directly in the Bing Chat answers.
- Citations and links. And Bing Chat, currently unlike ChatGPT, provides links and citations to where it found the content, something Microsoft said it can only do because of the Prometheus technology.
Query interpretation. I believe the query interpretation piece might be one of the most fundamental aspects of Prometheus. For example, as I illustrated in this search, Bing Chat AI is taking my long query and breaking it into a shorter query that Bing Search can understand, find the right documents for, plug into ChatGPT and also surface more answers from Bing Search.
Look at how Bing Chat took my query, “why does bing call their ai chat technology prometheus and what does it do?” and made it “bing ai chat technology prometheus.”
Fresh answers. Bing then takes this query, goes through its Bing Search index, which is mind-blowing fast, and gives almost real-time answers. Here is an example of a post I wrote last night and it showing up in Bing AI chat in minutes (via Glenn Gabe on Twitter last night):
Bing found the article I wrote at 5:08pm and responded to Glenn’s query by around 6:30pm the same night with that information.
Merging chat and search. The blog post then expands into how Microsoft Bing thought about the user experience, how to merge the Bing Search product with the Bing Chat product. “This product or UX innovation is arguably just as important as the Prometheus technology to ensure people can use the product to its full potential in an intuitive way,” Jordi Ribas wrote.
Why we care. Understanding that Bing Chat AI leverages so much of the core Bing Search features is useful to know. It gives us hope that some of our basic SEO practices will be even more fundamental and important for how we can help our clients and our own websites rank (if we call it ranking) high in these chat experiences.
“Prometheus is also able to integrate citations into sentences in the Chat answer so that users can easily click to access those sources and verify the information. Sending traffic to these sources is important for a healthy web ecosystem and remains one of our top Bing goals,” is what Jordi Ribas wrote in that blog post and we, as publishers, content creators and marketers certainly hope that is true.
