Amazon Quick introduces conversational analytics feature for enterprise data

Amazon Quick has launched Dataset Q&A, a feature that allows users to ask natural language questions directly about their enterprise data. This new capability complements Dashboard Q&A, offering a powerful method for data interaction in Amazon Quick. It enables users with dataset access to explore and derive meaningful insights from their data using natural language, all while adhering to governance rules, including Row Level and Column Level Security policies set by data owners.

Dataset Q&A is driven by Amazon Quick’s text-to-SQL agent, which interprets user queries, identifies the appropriate data, and generates precise SQL queries in a seamless conversational process. This agent is compatible with various data sources integrated into Amazon Quick, creating optimized SQL queries that are tailored to specific engines and dialects. This includes data from SPICE or AWS assets such as Amazon Redshift, Amazon Athena, Aurora PostgreSQL, and Apache Iceberg tables stored in Amazon S3 buckets.

Data owners can enhance their datasets by adding custom instructions, business definitions, and field descriptions directly within Amazon Quick or through straightforward file uploads. The system ingests these curated semantics, along with dataset metadata, into a knowledge graph that maps the meanings and relationships across data assets. This enables Quick’s orchestrator to accurately select relevant datasets and generate precise SQL queries.

The Dataset Q&A agent is capable of providing precise answers to a wide range of question types, including trend analysis, time-series comparisons, rankings, multi-condition analytical queries, and exploratory questions. Additionally, it features an Explain capability, which allows users to understand the reasoning behind each answer, review the underlying logic, and ensure the generated SQL accurately reflects their query before taking action based on the results.

Dataset Q&A is now available in all AWS Regions where Amazon Quick is offered. For more information on getting started, refer to the blog post.