AWS Machine Learning Blog

Amazon Kendra adds new search connectors from AWS Partner, Perficient, to help customers search enterprise content faster

Today, Amazon Kendra is making nine new search connectors available in the Amazon Kendra connector library developed by Perficient, an AWS Partner. These include search connectors for IBM Case Manager, Adobe Experience Manger, Atlassian Jira and Confluence, and many others.

Improving the Enterprise Search Experience

These days, employees and customers expect an intuitive search experience. Search has evolved from simply being considered a feature to being considered a critical element of how every product works.

Online searches have trained us to expect specific, relevant answers, and not choices when we ask a search engine a question. Furthermore, we expect this level of accuracy everywhere we perform a search, particularly in the workplace. Unfortunately, enterprise search does not typically deliver the desired experience.

Amazon Kendra is an intelligent search service powered by machine learning. Amazon Kendra uses deep learning and reading comprehension to deliver more accurate search results. It also uses natural language understanding (NLU) to deliver a search experience that is more in line with asking an expert a specific question so you can receive a direct answer, quickly.

Amazon Kendra’s intelligent search capabilities improve the search and discovery experience, but enterprises are still faced with the challenge of connecting troves of unstructured data and making that data accessible to search. Content is often unstructured and scattered across multiple repositories making critical information hard to find, costing employees’ time and effort to track down the right answer.

Data Source Connectors Make Information Searchable

Due to the diversity of sources, quality of data, and variety of connection protocols for an organization’s data sources, it’s crucial for enterprises to avoid time spent building complex ETL jobs that aggregate data sources.

To achieve this, organizations can use data source connectors to quickly unify content as part of a single, searchable index, without needing to copy or move data from an existing location to a new one. This reduces the time and effort typically associated with creating a new search solution.

In addition to unifying scattered content, data source connectors that have the right source interfaces in place, and the ability to apply rules and enrich content before users begin searching, can make a search application even more accurate.

Perficient Connectors for Amazon Kendra

Perficient has years of experience developing data source connectors for a wide range of enterprise data sources. After countless one off implementations, they identified patterns which can be repeated for any connection type. They developed their search connector platform Handshake and integrated with Amazon Kendra to deliver the following:

  • Reduced setup time when creating intelligent search applications
    • Handshake’s integration with Amazon Kendra out of the box indexes, extracts and transforms metadata making it easy to configure and get started with whatever data source connector you choose.
  • More connectors for many popular enterprise data sources
    • With Handshake, Amazon Kendra customers can license any of Perficient’s existing source connectors, including IBM Case Manager, Adobe Experience Manger, Nuxeo, Atlassian Jira and Confluence, Elastic Path, Elastic search, SQL databases, file systems, any REST-based API, and 30 other interfaces ready upon request.
  • Access to the most up-to-date enterprise content
    • Data source connectors can be scheduled to automatically sync an Amazon Kendra index with a data source, to ensure you’re always securely searching through the most up-to-date content.

Additionally, you can also develop your own source connectors using Perficient’s framework as an accelerator. Wherever the data lives, whatever format, Perficient can build hooks to combine, enhance, and index the critical data to augment Amazon Kendra’s intelligent search.

Perficient has found Amazon Kendra’s intelligent search capabilities, customization potential, and APIs to be powerful tools in search experience design. We are thrilled to add our growing list of data source connectors to Amazon Kendra’s connector library.

To get started with Amazon Kendra, visit the Amazon Kendra Essentials+ workshop for an interactive walkthrough. To learn more about other Amazon Kendra data source connectors visit the Amazon Kendra connector library. For more information about Perficent’s Handshake platform or to contact the team directly visit their website.

About the Authors

Zach Fischer is a Solution Architect at Perficient with 10 years’ experience delivering Search and ECM implementations to over 40 customers. Recently, he has become the Product Manager for Perficient’s Handshake and Nero products. When not working, he’s playing music or DnD.



Jean-Pierre Dodel leads product management for Amazon Kendra, a new ML-powered enterprise search service from AWS. He brings 15 years of Enterprise Search and ML solutions experience to the team, having worked at Autonomy, HP, and search startups for many years prior to joining Amazon 4 years ago. JP has led the Kendra team from its inception, defining vision, roadmaps, and delivering transformative semantic search capabilities to customers like Dow Jones, Liberty Mutual, 3M, and PwC.