The company claims "just a few clicks" is enough to index all internal data sources so users can make natural language queries.
It currently supports vocabularies from IT, healthcare, and insurance, energy, industrial, financial services, legal, media and entertainment, travel and hospitality, human resources, news, telecommunications, mining, food and beverage, and automotive, with more to come in the second half of 2020.
Thus it can respond to queries such as "when does the IT help desk open?”, “How do I set up my VPN?”, “What is the genetic marker for ALS?” and “How long does it take for policy changes to go into effect?"
Amazon Kendra connects to popular data sources such as SharePoint, OneDrive, Salesforce, ServiceNow, Amazon Simple Storage Service, and relational databases, with more coming during the year.
“Our customers often tell us that search in their organisations is difficult to implement, slows down productivity, and frequently doesn’t work because their data is scattered across many silos in many formats," said AWS vice president of Amazon machine learning Swami Sivasubramanian.
"Using keywords is also counterintuitive, and the results returned often require scanning through many irrelevant links and documents to find useful information.
“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 organisation’s data.”
Amazon Kendra is initially available today in AWS's US East (N. Virginia), US West (Oregon), and EU West (Ireland) regions. Other regions will be added "soon."