When we think of Microsoft and search, it’s usually with the knowledge of the company’s struggles to make Bing compete with Google Search in the consumer market. In enterprise, the company has more success. Microsoft Search is a tool the company uses to tie its various business services together.
If you are unfamiliar with Microsoft Search, it is a search tool that functions across Microsoft Teams, SharePoint, Office, OneDrive, Yammer, Windows, and Bing. Announced at Build 2018 and developed in preview, Search because generally available at Build 2019.
Microsoft Search leverages Microsoft Graph and Bing’s AI integrations to surface results stored by organizations. It also integrates with third-party services such as Google Drive, SAP, Salesforce, and Amazon Web Services (AWS).
While Microsoft can arguably protect Search on its own services, its on these third parties where Amazon’s Kendra poses a threat. Not least on the company’s own AWS, the largest cloud provider in the world.
Like Microsoft Search, Amazon’s tool allows users to search with natural language. It also supports connectors to other services, among them OneDrive and Salesforce.
Main Abilities of Kendra
- Kendra actively retrains deep learning models built for your data set and employee usage patterns to improve search accuracy. As end-users interact with search results, Kendra fine tunes its results. This means that if you click on a result or give it a ‘thumbs up’ or ‘thumbs down’, Kendra will learn which results are more relevant and surface those first.
- Kendra gives you the option to manually tune relevance; you can boost certain fields in your index like document freshness, view counts, or specific data sources. For example, you could boost documents that are not only viewed more often but that are also more recent, like trending news or updates.
- Use natural language questions instead of just simple keywords to get the answers you’re looking for. Kendra will connect the dots within your files to return answers, whether that is a text snippet, FAQ, or document. Instead of sifting through long lists of documents to find specific answers, Kendra can provide a suggested answer upfront.