What changed
Amazon Quick now enables users to combine structured data from databases and spreadsheets with unstructured data from documents and files stored in Amazon S3. This integration allows for a unified analysis experience through a single conversational AI agent, eliminating the need to switch between multiple tools or manually correlate results.
What this means in practice
The solution provides a layered architecture with three main components: the data layer, workspace layer, and agent layer. Users can connect structured data through enriched datasets and unstructured data through S3-backed knowledge bases. A Space brings both data types together into a single workspace, where users can ask questions that span both data types in a single conversation. The custom chat agent links to the Space and uses it as its knowledge source, determining whether to query the knowledge base, the dataset, or both, and returning a combined response with citations. Amazon Quick also applies built-in AI guardrails, such as content safety screening, to chat interactions.
Limitations and availability
To use this feature, users need an Amazon Quick account with an Enterprise subscription. They also require an Amazon S3 bucket for business documents and access to create integrations, knowledge bases, datasets, spaces, and chat agents. The solution is available through the Amazon Quick console, with specific steps outlined for creating an S3 integration, building a knowledge base, and enriching a dataset. The feature is currently in preview and requires the user to follow the outlined steps to set up and use the unified data analysis experience.
