AWS brings enterprise search tool Kendra into GA

Amazon Kendra uses machine learning to help organizations build better search engines for internal content and documents.

Amazon Web Services on Monday announced the general availability of Amazon Kendra, a machine learning-powered service for enterprise search. The service aims to help organizations build a better search engine for their internal documents, without the need for machine learning expertise.

When AWS debuted Amazon Kendra at its re:Invent conference in Las Vegas last year, the company stressed that -- unlike information on the world wide web -- data within an organization can be hard to search. 

Internal data is often unstructured and siloed, explained Matt Wood, AWS's VP of AI. Files may use different jargon and formats, and it may exist in SharePoint, Dropbox, or any number of places. Consequently, internal enterprise search tools typically offer limited accuracy, and they often only link up a limited number of data silos. 

Wood called Kendra "a step-change in the capability for internal search."

Customers can set up Kendra from the AWS console, providing the service with their credentials for the services they want Kendra to query. Kendra then uses machine learning to build a search index based on their organization's documents and any FAQs. It uses natural language understanding to learn the intent and context of information within a document, as well as the relationships between content and documents. 

The service can be queried with either keywords or natural language. In addition to surfacing relevant documents, the search service will provide a direct answer if it can. For instance, if someone were to ask, "Where is the IT support desk?" Kendra could reply, "On the third floor" in addition to providing relevant links. 

Kendra is also optimized to understand complex language from specific domains, Amazon says. For instance, a customer in the healthcare and life sciences sector may want to ask, "What is the genetic marker for ALS?" A customer from the insurance industry could query, "How long does it take for policy changes to go into effect?" 

Currently, Kendra supports industry-specific language from IT, healthcare, insurance, energy, industrial, financial services, legal, media and entertainment, travel and hospitality, human resources, news, telecommunications, mining, food and beverage and automotive. Additional industry support is slated for the second half of this year.

Customers and partners already using Kendra include 3M, PwC and the Allen Institute.