AI

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.

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 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.

The exact fields an AI agent’s audit trail needs, from the human who directed it to the downstream action it took, and the lakehouse table that produces each one.

Why AI red teaming for agents and RAG depends on a governed gold-layer evaluation set with known-correct answers, and how to build one with taxonomies from NIST, OWASP and MITRE ATLAS.

A practical AI vendor risk assessment for mid-market teams: what to ask a vendor, how shadow AI changes procurement, and a copy-ready checklist tied to lakehouse controls.

Seven AI consulting firms for mid-market companies compared on delivery model, pricing and time to working software. Updated for 2026.

What an ISO/IEC 42001 AI management system looks like on a mid-market lakehouse: inventory, access, lineage, logging and incident handling in build order, and when certification is worth it.

The questions to ask an AI consulting firm, plus what a good answer and a red flag answer sound like for each one.