Articles

Article cover: The vector index inherits no permissions: data agents on Databricks, Fabric and Foundry

Inteligencia Artificial

The vector index inherits no permissions: data agents on Databricks, Fabric and Foundry

A vector index is a copy, and a copy inherits no permissions: the Databricks AI Search documentation states that row and column level permissions are not supported. The two routes an agent takes to the data — RAG and text-to-SQL —, where the access rule lives on each one, the Genie Agent’s two credentials, and the metric layer that stops the number from changing.

1 de September de 2026 No Comments

Article cover: Network and security for AI workloads, a private endpoint closes the entrance, not the exit

Inteligencia Artificial

Network and security for AI workloads: a private endpoint closes the entrance, not the exit

A private endpoint controls ingress; it authenticates nobody and does not decide where the agent writes afterwards. The three boundaries of an AI workload — entrance, identity, and exit —, the three DNS zones Foundry requires, the roles that were renamed, and the egress control almost every project leaves open.

24 de August de 2026 No Comments

Article cover: Guardrails and agent evaluation, what separates a demo from a production system

Inteligencia Artificial

Guardrails and agent evaluation: what separates a demo from a production system

Guardrails contain at runtime; evaluation measures over time — and neither does the other’s job. Content Safety, Prompt Shields, evaluators that see the tool call and not just the answer, red teaming with PyRIT, and the maturity signal that separates a demo from a system: a deployment blocked by a number.

21 de August de 2026 No Comments

Federate, mirror, or ingest: the decision between Databricks and Fabric

Data Architecture

Federate, mirror, or ingest: the decision between Databricks and Fabric

Federating, mirroring, and ingesting are not synonyms — and in Fabric “mirroring” already means three different mechanisms. When to use Lakehouse Federation, when to mirror a catalog or a database into Microsoft Fabric, when to ingest with Lakeflow Connect, what is actually free, and why source permissions do not cross the OneLake boundary.

16 de August de 2026 No Comments

Inteligencia Artificial

AI FinOps beyond caching: how to choose Batch, Model Router, PTU, and pay-as-you-go

Prompt caching solves reuse, but it does not decide when to run, how to buy capacity, or which model should answer. A practical framework for combining Batch, PTU, pay-as-you-go, and Model Router around cost per approved task.

13 de August de 2026 No Comments

Cover: data ontology in Azure Databricks and Microsoft Fabric

Engenharia de Dados

Data ontology: the governed context that makes AI reason across Databricks and Fabric

The bottleneck of enterprise AI is not the model, it is governed business context. How Unity Catalog Metric Views, Genie Ontology and Fabric IQ form a single semantic layer over one copy of the data — with an FSI use case, cost model and roadmap.

9 de August de 2026 No Comments