AWS begins global rollout of Kendra Search

Amazon Web Services (AWS) has announced the general availability of Amazon Kendra, its new enterprise search service that uses machine learning to enable organizations to index all of their internal data sources, make that data searchable, and allow users to get precise answers to natural language queries.

It is available initially in US East (N. Virginia), US West (Oregon), and EU West (Ireland), with other regions coming soon.

When users ask a question, Amazon Kendra uses machine learning algorithms to understand the context and return the most relevant results, whether that be a precise answer or an entire document. For example, businesses can use Amazon Kendra to search internal documents spread across portals and wikis, research organizations can create a searchable archive of experiments and notes, and contact centre can use Kendra to find the right answer to customer questions across the complete library of support documentation. Amazon Kendra requires no machine learning expertise and can be set up completely within the AWS Management Console.

Despite many attempts over many years, searching for information within an organization remains a vexing problem for today’s enterprises. Many businesses and organizations struggle implementing internal search across their siloed troves of data, requiring their end-users to use keywords to find information.

Organizations have vast amounts of unstructured text data, much of it incredibly useful if it can be discovered, stored in many formats, and spread across different data sources (e.g. SharePoint, Intranet, Amazon Simple Storage Service, and on-premises file storage systems).

Even with common web-based search tools widely available, organizations still find internal search difficult because none of the available tools do a good job indexing across existing data silos, don’t provide natural language queries, and can’t deliver accurate results.

When end-users have questions, they are required to use keywords that may appear in multiple documents in different contexts, and these searches typically generate long lists of random links that end-users have to sift through to find the information they seek – if they find it at all.

Amazon Kendra is claimed to reinvent enterprise search by allowing end-users to search across multiple silos of data using real questions (not just keywords) and leverages machine learning models under the hood to understand the content of documents and the relationships between them to deliver the precise answers they seek (instead of a random list of links).

Because natural language understanding is at the core of Amazon Kendra’s search engine, employees can run their searches using natural language (keywords still work, but most users prefer natural language searches). As an example, an employee can ask a specific question like “when does the IT help desk open?” and Amazon Kendra will give them a specific answer like “9:30 AM,” and highlight the passage in the source document where it found the answer, along with links back to the IT ticketing portal and other relevant sites.

Amazon Kendra is also optimized to understand complex language from multiple domains, including IT (e.g. “How do I set up my VPN?”), healthcare and life sciences (e.g. “What is the genetic marker for ALS?”), and insurance (e.g. “How long does it take for policy changes to go into effect?"). Currently, Amazon Kendra supports industry-specific language from IT, healthcare, and insurance, plus energy, industrial, financial services, legal, media and entertainment, travel and hospitality, human resources, news, telecommunications, mining, food and beverage, and automotive, with additional industry support coming in the second half of this year.

“Our customers often tell us that search in their organizations is difficult to implement, slows down productivity, and frequently doesn’t work because their data is scattered across many silos in many formats. Using keywords is also counterintuitive, and the results returned often require scanning through many irrelevant links and documents to find useful information,” said Swami Sivasubramanian, Vice President, Amazon Machine Learning, Amazon Web Services, Inc.

“Today, we’re excited to make Amazon Kendra available to our customers and enable them to empower their employees with highly accurate, machine learning-powered enterprise search, which makes it easier for them to find the answers they seek across the full wealth of an organization’s data.”

Amazon Kendra encrypts data in transit and at rest and easily integrates with commonly used data repository types such as file systems, applications, Intranet, and relational databases, so developers can index their company’s content with just a few clicks, and provide end-users with highly accurate search without writing a single line of code. Amazon Kendra provides a wide range of native cloud and on-premises connectors to popular data sources such as SharePoint, OneDrive, Salesforce, ServiceNow, Amazon Simple Storage Service, and relational databases, with more being added throughout this year.

David Frazee, Technical Director, 3M Corporate Research Systems Lab, said “Finding the right information is often exhausting, time consuming, and sometimes incomplete. With Amazon Kendra, our scientists find the information they need quickly and accurately using natural language queries. With Kendra, our engineers and researchers are enthusiastic about the ability to quickly find information which will enable them to innovate faster, collaborate more effectively, and accelerate the ongoing stream of unique products for our customers.”

Baker Tilly is a US advisory, tax, and assurance firm.

“Amazon Kendra provides direct connection with unbelievable levels of efficiency and accuracy. We found that by using Kendra, our clients are able to surface relevant information 10 times faster when compared to SharePoint full text search,” said Ollie East, Director of Advanced Analytics and Data Engineering at Baker Tilly.

“As an example, Amazon Kendra allows product managers to ask questions in everyday language such as ‘What parts are made of titanium?’ quickly surfacing an answer such as a list of relevant product manuals, technical bulletins, service alerts, and patent registrations previously not possible with keyword search and connecting them to relevant content across an enterprise-wide repository, or providing marketing managers quick access to crucial research on customer behaviour.”