Context Engineering for Data Agents
September 10, 2026Why text-to-SQL accuracy collapses on enterprise schemas, the five kinds of context an agent needs, where each one hides, and how to make the semantics legible.
7 posts tagged with "metadata"
Migrating Into Iceberg Without Moving Data
September 10, 2026add_files, snapshot, and migrate compared: the three in-place paths into Iceberg, the reconciliation each requires, the layout traps, and the rollback story.
Partition Statistics Files in Apache Iceberg
September 10, 2026The underused Iceberg metadata for planning: what the partition statistics file holds, what the spec guarantees, how to write one, and when it earns its slot.
Parquet-Only Manifests in Iceberg v4: Why the Metadata Layer Is Going Columnar
August 25, 2026Iceberg v4 is moving manifests from Avro to Parquet so planners can read only the stats they need. Why the metadata layer is going columnar.
The Hidden Cost of Tiny Iceberg Commits
August 24, 2026Trace what one tiny Iceberg commit writes, then model hourly, per-minute, and per-second cadences so streaming costs become arithmetic, not adjectives.
Iceberg v4's Adaptive Metadata Tree, Explained From First Principles
August 24, 2026Iceberg v4's adaptive metadata tree, explained from first principles: why commits rewrite too much today and how the tree makes change cheaper.
Why Iceberg v4 Is Really About Making the Cost of Change Proportional to the Change
August 24, 2026Iceberg v4 is really about making the cost of a change proportional to the change. The principle, the current tax, and what the redesign pays down.