Turning an Analytics Question Into a Verified Agentic Graph
A complete AGS 1.0 graph for governed metric questions, with verification gates, deterministic check scripts, and reconciliation against a semantic layer.
The archive
Writing, page 2
652 posts on Apache Iceberg, lakehouse architecture, data engineering and applied AI.
Keeping Audit Snapshots Alive While Iceberg Snapshot Expiration Runs Every Night
How Iceberg snapshot tags keep audit snapshots alive through nightly expiration: retention calendars, RETAIN semantics, compaction cost, and erasure conflicts.
Twelve Queries That Pass Every Schema Check and Still Return the Wrong Number
Twelve query patterns that pass schema validation and still return wrong numbers, with detectors, required metadata, and tested code for each.
Why the Iceberg DataFusion Integration Is Moving to Apache DataFusion
Why the Iceberg DataFusion integration moved to the DataFusion project, and what the split means for users, Comet, and iceberg-rust contributors.
What Iceberg v4's Proposed FILE Type Means for Multimodal Tables
Iceberg v4's proposed FILE type brings first-class media references to tables, via Parquet's FILE logical type, ranges, checksums, and pre-signed URLs.
Fast Classification Models, LLMs, and the Apache Iceberg Lakehouse
How fast classification models like Jev alongside open alternatives such as GLiClass compare with LLMs, and how to run both together inside an Apache Iceberg lakehouse.
How Apache Ossie Is Deciding What Agents and BI Tools Can Ask a Semantic Layer
How Apache Ossie's layered query design gives AI agents both a constrained dimensional interface and a grain-safe SQL interface for semantic layers.
CVE-2026-73334 and the Trust Boundary Inside an Encrypted Parquet File
CVE-2026-73334 lets a tampered Parquet footer route a reader's KMS token to an attacker. Here's the fix, Iceberg's safe path, and how to audit your lakehouse.
Parquet Page Indexes and the Last Mile of Pruning in Apache Iceberg
Parquet page indexes can cut selective Iceberg scans by an order of magnitude on sorted data. How they work, what they cost, and how to lay out tables.
How Apache Polaris Plans to Share Iceberg Tables Across Organizations
Apache Polaris's Open Sharing proposal adds first-class shares, external consumers, and listings so any Iceberg REST engine can read shared tables.