Can an Omnia agent use data in Databricks?

Yes. Point it at the APIs or MCP servers you already expose, with the end user’s identity carried to the call.

Which models can each use?

Both are broad. Omnia speaks seven providers’ native protocols and any OpenAI-compatible endpoint, including a model you host.

omnia vs agent bricks

Agent Bricks keeps agents next to your data. Getting each new version into production safely is Omnia’s job.

Omnia runs in your own cluster for agents whose tools reach past one data platform, and gets each new version into production through a test gate and a stepped rollout. Agent Bricks puts agents next to Unity Catalog, with its own judges and tracing.

A finance agent gets a new prompt the week before quarter close.

on omnia

Before it serves anyone, the new version meets simulated controllers through the real tools, one of them pushing an out-of-policy journal entry. It passes and goes to part of the traffic first. Its numbers hold, and it reaches everyone before close. docs

on agent bricks

Multi-turn conversation simulation is experimental, and its API and behaviourbehavior might change. An eval-gated release, staged rollout and automatic rollback aren’t documented. their docs

Simulation you can build a release on

Omnia’s simulated users are generally available, with adversarial and voice testing alongside. A version that fails them doesn’t ship. docs

Agent Bricks: An LLM-driven simulator with goals and personas, marked experimental. Voice testing isn’t documented. source

Stepped rollout

The old version keeps serving while the new one takes traffic in steps. A conversation stays on the version it started on, and if the new version’s metrics drop, the traffic goes back. docs enterprise

Agent Bricks: Agents deploy with the Agent Bricks CLI. Versioning, staged rollout and rollback aren’t documented. source

Runs where the rest of your stack runs

Omnia installs into your Kubernetes cluster and deploys the same pack to AWS Bedrock AgentCore, Google’s Agent Runtime or Azure AI Foundry. Telemetry goes live to your own OpenTelemetry collector. docs

Agent Bricks: Agents run on Databricks-hosted compute, and traces are stored in OpenTelemetry format in Unity Catalog tables. source

At a glance

Topic	Omnia	Agent Bricks, per its docs
Simulated users	yes Generally available, adversarial included. docs	partly Experimental. source
Eval-gated release	yes The suite decides whether a version ships. docs	not documented Not documented. source
Stepped rollout, auto rollback	yes Traffic shifts in steps and rolls back on its own. docs	not documented Not documented. source
End-user identity to tools	yes Carried through the agent to every call. docs	documented The user’s token is forwarded, scoped to the workspace. source
Argument-level tool policy	yes A CEL rule on every call, before the tool runs. docs enterprise	partly Access, guardrails and rate limits on models, MCP servers and skills. source
Runs in your own cluster	yes Yes, installed with Helm. docs	not documented Databricks-hosted compute. source
Voice	yes Duplex voice, and tests for it. docs	not documented Not documented. source

Common questions

Can an Omnia agent use data in Databricks?: Yes. Point it at the APIs or MCP servers you already expose, with the end user’s identity carried to the call.
Which models can each use?: Both are broad. Omnia speaks seven providers’ native protocols and any OpenAI-compatible endpoint, including a model you host.

Put your own agent through the gate.

Install Omnia in your cluster and run it free while you build.

Agent Bricks claims are from Databricks’s published documentation, checked 22 October 2026. Spot something out of date? Tell us.

Install it in your cluster Or walk through it with us →