Databricks renamed Vector Search to AI Search. Here is how its indexes, endpoints and sync modes work for RAG on the lakehouse, and how to tell if you are ready.
RAG on Databricks: AI Search, Formerly Vector Search, Done Right
read more
— Blog · The Discipline Layer for AI
Field notes on doing AI the disciplined way.
Contrarian, data-grounded essays on the three things that decide whether AI pays: a sharper problem, governed data, and demand that survives the answer-engine age.
— Featured
Growth · Featured essay
AI Content Generation: From Caves to Code
The first content strategists painted on cave walls. The newest ones orchestrate agents. This essay traces the whole arc — and shows how a disciplined content engine drove 359% organic traffic growth for a B2B client by treating generation as a system, not a shortcut.
Frank Shines & Umer Qureshi · Read the essay →
— All essays
Read by pillar.
Every post strengthens one of the three foundations — Problem, Data, or Growth.
Agent Bricks: Building Production AI Agents on the Lakehouse
Agent Bricks turns governed lakehouse data into evaluated, deployable agents. Here is how it works, what its status really is, and how to ship one.
Databricks vs Microsoft Fabric for Mid-Market Azure Teams
Azure Databricks and Microsoft Fabric overlap more every quarter. This comparison covers pricing models, throttling, governance and the mirrored-catalog pattern that lets a mid-market team use both without paying for engineering twice.
Databricks Genie: Making Self-Service BI Answers Trustworthy
Databricks Genie answers business questions in plain language, but its accuracy depends on the gold layer and semantics underneath. Here is how to build that layer, control the compute cost, and roll it out.
Data Warehouse Modernization: The Legacy EDW Exit Path
Replace the legacy EDW with a governed Databricks lakehouse. A staged, low-drama exit path that cuts cost, fixes pipelines, ships AI.
AI Readiness Assessment for Mid-Market Data Teams
Measure pipeline debt before you fund a Databricks lakehouse. A paid front-door diagnostic that prices AI and LLM readiness in dollars.
— The newsletter
One disciplined idea, in your inbox.
New essays plus the occasional contrarian take on where AI is overhyped and where it’s underrated. No spam.
— From essay to engagement
Reading about it is step one.
When you’re ready to put the discipline to work, we ship it in 90 days.