Metadata on StorageNews

Kappa metadata fixes broken AI data pipelines

Fri, 20 Feb 2026 00:00:00 +0000

Komprise claims KAPPA handles petabyte-scale datasets while automatically managing cloud AI service lifecycles to fix broken data pipelines. The central thesis is that serverless metadata enrichment is the only viable method to make the 90% of enterprise unstructured data actually usable for artificial intelligence. Without a central repository spanning filers, cloud stores, and SaaS services, organizations remain blind to their own assets despite heavy investment in generative models.

Agentic AI fails without field-level lineage

Thu, 19 Feb 2026 00:00:00 +0000

Over 500 sources, including legacy mainframes, now feed active metadata directly into Google Cloud via Ab Initio. The reality of agentic AI is that autonomous agents fail without precise, unified data context, rendering most current enterprise deployments useless. Readers will discover how active metadata serves as the critical operational layer for agentic AI, enabling models like Gemini to reason accurately rather than hallucinate. We examine the specific mechanics of the Google Cloud and Ab Initio partnership, which deploys bi-directional exchange across more than 500 disparate sources to solve the fragmentation problem. The discussion details how this integration extends Dataplex Universal Catalog capabilities to cover complex legacy formats like COBOL and DataStage, ensuring field-level lineage.

Snowflake catalog federation cuts AWS data costs

Wed, 14 Jan 2026 00:00:00 +0000

The new catalog federation feature eliminates 100% of data duplication costs between AWS and Snowflake environments. This integration fundamentally shifts enterprise strategy by enabling direct Iceberg format queries across platforms without moving underlying storage. By connecting the AWS Glue Data Catalog to Snowflake Horizon Catalog, organizations can finally execute true data mesh architectures while maintaining strict compliance management through centralized policies.