Announcing the Agentic Catalog Experience in Amazon Quick

<p>As organizations embrace AI-powered analytics, the value of a natural language (Text2SQL) answer is only as good as the business context behind it. We’re entering a phase where semantic richness (table and column descriptions, and relationships) must flow directly from where it’s authored in upstream data catalogs and semantic tools into the AI products that serve end users. Products like Amazon Quick can no longer operate in isolation. They need to natively consume and reason over the definitions, relationships, and governance metadata that data teams curate in systems like AWS Glue Data Catalog and Databricks Unity Catalog. This shift from siloed metadata to connected, catalog-aware AI is what enables intelligent analytics at scale.</p> <h2 id="the-challenge-bridging-the-last-mile">The challenge: Bridging the last mile</h2> <h3 id="the-investment-is-done">The investment is done</h3> <p>Enterprise data teams have done the hard work. They have invested heavily in upstream catalog platforms such as AWS Glue, Databricks Unity Catalog, Snowflake Horizon, Collibra, and dbt. On these platforms, they meticulously define table descriptions, column semantics, primary and foreign key relationships, glossary terms, and metric definitions.</p> <p>Yet when it comes to enabling end users (such as sales managers, marketing directors, and finance leads) for production-ready AI and trusted dashboards, a significant gap remains.</p> <h3 id="three-compounding-challenges">Three compounding challenges</h3> <p>When data curators (business intelligence engineers, analytics leads, and senior analysts) need to enable their business users in Amazon Quick, they face three compounding challenges:</p> <ol> <li><strong>Limited discoverability</strong>: With thousands of tables in enterprise catalogs, discovering the right upstream assets that are curated and approved for reporting is a needle-in-a-haystack problem. There’s no way to describe what you need and have the system find it.</li> <li><strong>Semantic fragmentation and manual recreation</strong>: Rich metadata that already exists upstream (business descriptions on tables and columns, and primary and foreign key relationships) does not flow through. Curators must recreate assets from scratch, redefine descriptions, and reconcile definitions manually. Does “revenue” mean gross or net? Does “active customer” mean a purchase within 30 days or 90 days? These definitions exist upstream but require manual re-entry.</li> <li><strong>Time to insight in weeks, not hours</strong>: The combination of manual discovery and manual recreation means that the time from data to actionable insights stretches from hours to weeks. Worse, when upstream definitions change, manually created semantics in Quick Datasets become stale, causing semantic drift that erodes trust in AI answers and dashboards over time.</li> </ol> <h3 id="the-gap">The gap</h3> <p>The problem isn’t upstream. The metadata exists. The governance is defined. The relationships are mapped.</p> <p>The problem is the last mile: translating that rich catalog context into a curated, consumable experience that delivers grounded AI answers and deterministic dashboards end users can trust.</p> <h2 id="introducing-the-agentic-catalog-experience-in-amazon-quick">Introducing the Agentic Catalog Experience in Amazon Quick</h2> <p>Today, we’re announcing the Agentic Catalog Experience in Amazon Quick, an AI-powered workflow that helps data curators rapidly define their context boundary, inherit upstream semantics, and enable end users for grounded Q&amp;A and trusted dashboards at scale.</p> <p>At the heart of this experience is the Quick Agent, scoped to discovery, creation, and inheritance tasks within the catalog context. It uses the semantic context from the catalog connection to summarize the entire catalog at a glance, engage the customer in natural language conversation, surface the most relevant tables and relationships based on the c