Amazon Q Business features

Conversational interface

Through a conversational experience, Amazon Q Business finds and synthesizes information from across your enterprise. This helps your employees have tailored conversations, ask questions and get accurate answers, brainstorm ideas, summarize lengthy reports, generate content, and take actions.

Amazon Q Business provides references and citations to the sources used to generate its answers, building user trust.

Amazon Q Business can start new conversations or continue an existing dialogue. You can ask a question, receive a response, and then ask follow-up questions and add new information while keeping the context from the previous answer.

Amazon Q Business provides thumbs-up and thumbs-down buttons for every interaction, so you can give feedback on whether the response was useful or not.

Amazon Q Business allows end users to upload files and perform tasks like summarization, Q&A, or data analysis.


Amazon Q Business handles the heavy lifting for you—there’s no need to manage complex machine learning (ML) infrastructure or models. Amazon Q Business connects to your data using pre-built connectors that support user access control. It has a built-in semantic document retriever and a ready-to-deploy chat interface for end users to allow for easy deployment.

Amazon Q Business offers pre-built connectors to over 40 supported data sources, including Amazon Simple Storage Service (Amazon S3), Microsoft SharePoint, Salesforce, and Atlassian Confluence. For more information about Amazon Q Business supported data source connectors, see Amazon Q connectors.


Amazon Q Business supports access control for your data so that users receive the right responses based on their permissions. You can integrate Amazon Q Business with your external SAML 2.0–supported identity provider (such as Okta, Azure AD, and Ping Identity) to manage user authentication and authorization.

Amazon Q Business offers administrator controls to enable or disable the following capabilities: (1) Restrict responses to enterprise content only or use its own knowledge to respond to queries when there is no relevant content in the enterprise repository. (2) Define blocked topics. (3) Set the context for optimal responses.