Databricks
Volume 342, Issue 2 · 11 articles
In This Issue
Health Plans: Your BI Tells You MLR Moved. Can Your AI Tell You Why? (Databricks, Friday, September 11th, 2026)
Moving health plan analytics from reporting that a medical loss ratio changed to explaining what drove it. Read more
Evaluation-First AI Agents: How Zepto Scales Customer Support on Databricks and MLflow (Databricks, Wednesday, September 9th, 2026)
Zepto built evaluation before deployment, using MLflow to keep support agents reliable as they scaled. Read more
Five AI Questions We're Hearing From Financial Services Leaders (Databricks, Wednesday, September 9th, 2026)
The question at Sibos has moved from whether AI works to whether your data can support it. Read more
Improving Lakebase Postgres Compute Cache (Databricks, Thursday, September 10th, 2026)
Engineering detail on caching improvements in the disaggregated storage model behind Lakebase Postgres. Read more
Unifying Governance Across Engines and Catalogs in the Open Lakehouse (Databricks, Thursday, September 10th, 2026)
How open table formats and open APIs support one governance model across multiple query engines and catalogs. Read more
Unify Your Marketing Data With Lakeflow Connect (Databricks, Friday, September 11th, 2026)
The first in a series on using Lakeflow Connect to consolidate fragmented marketing data sources. Read more
Beyond Embedding: How to Secure AI/BI Dashboards for Every Viewer (Databricks, Wednesday, September 9th, 2026)
Embedding a dashboard is easy; enforcing per-viewer data access in a customer-facing application is not. Read more
A Practical Approach to End-to-End Solvency II Reporting in Databricks (Databricks, Wednesday, September 9th, 2026)
Treating Solvency II as a business process with lineage and auditability rather than a periodic submission. Read more
Adaptive Instructed-Retriever: Frontier-Quality Search at 2x Lower Latency (Databricks, Wednesday, September 9th, 2026)
A retrieval model trained to spend extra search steps only where query complexity justifies the cost. Read more
Databricks Unveils Adaptive AI Retrieval Model to Cut Search Costs and Latency (InfoWorld, Wednesday, September 9th, 2026)
Databricks' Adaptive Instructed-Retriever adds search steps only for complex queries to balance answer quality, latency, and cost. Read more
Introducing Consort: Test-Driven Development on a Branching Database (Databricks, Wednesday, September 9th, 2026)
Bringing TDD practice to data work by branching the database the way developers branch code. Read more
More from Databricks · All section posts · This week