Amazon Kendra is an intelligent search service powered by machine learning. Kendra reimagines enterprise search for your websites and applications so your employees and customers can easily find the content they are looking for, even when it’s scattered across multiple locations and content repositories within your organization.
Using Amazon Kendra, you can stop searching through troves of unstructured data and discover the right answers to your questions, when you need them. Amazon Kendra is a fully managed service, so there are no servers to provision, and no machine learning models to build, train, or deploy.
Get better answers upfront using natural language
Use natural language questions in addition to just simple keywords to get the answers you’re looking for. Kendra will return an exact answer from within a document, whether that is a text snippet, FAQ, or PDF document. Instead of sifting through long lists of documents to find specific answers, Kendra also provides suggested answers upfront. See the difference between the search experience before and after Kendra.
Find relevant answers, quickly
Centralize access to knowledge
Fine-tune search results
Kendra’s deep learning models come pre-trained across 14 industry domains, allowing it to extract more accurate answers across a wide range of business use cases from the get-go. You can also fine-tune search results by manually adjusting the importance of data sources, authors, freshness, or using custom tags.
Deploy with just a few clicks
Improve customer interactions
Whether it’s through Q&A chatbots, agent-assist, or customer web search, Amazon Kendra better understands what your customers are asking to provide more relevant answers and intuitive experiences.
Accelerate research and development
Scientists and developers leading new research and innovation need access to information from prior work that’s buried within their corporate data stores. With faster, more accurate search, these groups waste less time searching and more time innovating.
Minimize regulatory and compliance risks
Use machine learning to quickly identify and interpret regulatory policies published across hundreds of diverse regulatory websites so you can improve policy enforcement and compliance processes.
Equip employees with the data they need
By unifying and indexing content from diverse, disparate, and multi-structure information silos across the organization, enterprises build and maintain an active knowledge catalog. With this centralized view, users can quickly see what information is available and become more informed.
“When our material scientists lead new research, they need access to information from prior relevant research—information that’s buried in the many patents we hold in our huge knowledge base… Kendra lets our scientists find the information they need by handling natural language queries quickly and accurately.”
"Our goal is to help our customers get to the answers they need faster - even when the right answers may be buried within documents over 100 pages long - so they can understand regulatory information faster and make decisions more quickly and confidently"
Kendra finds the answer to questions like ‘What is the length of the pipeline at Pluto?’ quickly and accurately. This step-change in cognitive capability will enable even better, faster decision making to improve our operations and the working lives of our people.”
Get started with Kendra today
Reimagine search for yourself. With Amazon Kendra, you can now connect your own data sources and start testing the search experience on your own content in minutes.
Create an index where you'll add your data sources.
Use Kendra's connectors for popular sources like S3, SharePoint, Salesforce, Servicenow, RDS databases, One Drive and many more coming later this year.
Test the search experience directly in the console. Plus, access sample code for each component of the search experience so you can easily deploy to new or existing applications.