Users can apply filters on custom metadata fields such as business region, data classification, or study identifiers alongside traditional keyword and semantic search. The filters support string and numeric types with operators allowing contains, equals, greater than, and less than comparisons, and multiple combined filters persist across sessions.
This capability streamlines asset discovery in large catalogs by enabling fine-grained search tailored to customer-specific metadata schemas. The feature is broadly available in all supported regions under standard SageMaker pricing, accessible via the web interface and programmatically through the SearchListings API, facilitating integration into existing workflows.
Source & further reading
Amazon SageMaker Unified Studio adds custom metadata filters ↗Source published 2026-03-18. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.