Announcing the Agentic Catalog Experience in Amazon Quick

This article announces the Agentic Catalog Experience in Amazon Quick, an AI-powered workflow that bridges the gap between upstream data catalogs and end-user analytics by automating metadata inheritance and dataset creation.

• Natural language asset discovery lets curators find relevant tables across thousands of catalog entries without manual browsing
• Bulk agentic dataset creation automatically generates Catalog-Generated Datasets with inherited business descriptions and column definitions
• Primary and foreign key relationships are detected and used to create pre-configured Topics with star and snowflake schema joins
• Supports AWS Glue Data Catalog and Databricks Unity Catalog with read-only inherited metadata that stays synchronized to upstream sources
• End users get grounded AI answers backed by trusted Gold-standard data with full semantic lineage and governance context
• Reduces time from data discovery to actionable insights from weeks to minutes through guided conversational workflows

The Agentic Catalog Experience eliminates manual dataset configuration by making Amazon Quick a consumer of upstream catalog metadata, enabling production-ready AI analytics at enterprise scale.