Posts
All the articles I've posted.
- 32 MIN READ•Oct 5, 2026
How to Build a Golden-Question Benchmark for Your Data Agents
Build a golden-question benchmark for data agents: frozen Iceberg tags, execution-based scoring with Arrow, and CI gates.
evaluationAI agentsApache Iceberg - 31 MIN READ•Oct 5, 2026
When a Data Agent Gives a Wrong Number: Incident Response for Agentic Analytics
A plan for when a data agent gives a wrong number: severity levels, containment, Iceberg time travel reproduction, and blast radius queries.
incident responseAI agentsApache Iceberg - 31 MIN READ•Oct 5, 2026
Multi-Tenant Data Agents: Serving Many Customers From One Lakehouse
Serve many customers from one lakehouse without leaking between them: isolation models, Polaris grants, and tenant-scoped agent state.
multi-tenantApache PolarisAI agents - 31 MIN READ•Oct 5, 2026
Release Management for Data Agents: Shipping Prompts, Tools, Models, and Metrics Without Breaking Answers
Ship prompts, tools, models, and metric changes without breaking answers: agent manifests, shadow mode, canaries, and rollback.
release managementAI agentsevaluation - 31 MIN READ•Oct 5, 2026
Semantic Caching for Data Agents Without Serving Stale or Leaked Numbers
Cache data agent results safely with canonical query keys, Iceberg snapshot freshness checks, and permission-aware cache keys.
cachingAI agentsApache Iceberg - 31 MIN READ•Oct 5, 2026
Small Language Models for Data Agents: Where They Win and Where They Fail
Where small language models win inside a data agent and where they fail, plus a routing architecture that escalates only when needed.
small language modelsAI agentssemantic layer - 31 MIN READ•Oct 5, 2026
Stop Calling Everything Made With AI Slop
AI slop means low-quality content, not AI-assisted work. The three markers of slop, and the review habits that separate skilled AI-assisted work from filler.
AI WritingAI ToolsCreative Work - 31 MIN READ•Sep 28, 2026
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.
AI AgentsAgentic Graph SpecificationMulti-Agent - 31 MIN READ•Sep 28, 2026
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.
Apache IcebergSnapshot ExpirationData Governance - 31 MIN READ•Sep 28, 2026
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.
AI AgentsSemantic LayerData Quality - 31 MIN READ•Sep 21, 2026
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.
Apache DataFusionApache IcebergRust - 32 MIN READ•Sep 21, 2026
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.
Apache IcebergIceberg v4Multimodal