Can I use Omnia with Foundry?

Yes. Omnia deploys a pack to Azure AI Foundry with one command, uses Azure OpenAI and Foundry models, and runs its scenarios against the deployed agent.

Does Omnia publish agents to Teams?

Omnia serves agents over WebSocket, REST, A2A or MCP. Deployed to Foundry, the same agent can use Foundry’s publishing.

omnia vs foundry agent service

Foundry runs agents inside Microsoft’s stack, and Omnia can deploy to it with a stepped rollout and voice tests added.

Omnia moves traffic to a new version in steps, pulls it back on the metrics, and tests voice agents as calls. Foundry Agent Service publishes into Teams with an Entra identity, but each endpoint serves one version, so a release reaches everyone the moment it’s live.

A voice agent on the customer line gets a new version.

on omnia

Simulated callers have already rung it, interrupting, talking over it and leaving long silences, and it passed. It goes live on a share of calls first. On real lines its interruption handling is worse, the metrics show it, and the previous version is back before the morning peak. docs

on foundry agent service

An agent endpoint serves one version at a time and routes all of its traffic to it; traffic splitting between versions isn’t supported. Simulated-conversation evaluation isn’t supported for voice agents. their docs

A slice of traffic first

Old and new versions serve at the same time. A call that started on the old one finishes there, and the new one gets more calls as its metrics hold. If they don’t, it’s rolled back. docs enterprise

Foundry Agent Service: One version per endpoint, all traffic. Roll back by pinning an earlier version. source

Voice agents get tested too

Voice scenarios run full duplex against the agent, and each session is recorded so you can listen back. docs

Foundry Agent Service: Single-turn and simulated-conversation evaluation aren’t supported for voice agents. The red-teaming agent supports text scenarios only. source

Rules on tool calls

A CEL rule reads each tool call’s arguments and the caller’s identity, and allows or denies it deterministically. If the broker can’t answer, the call is refused. docs enterprise

Foundry Agent Service: Tool-call guardrails, in preview, run content-risk classifiers on arguments for a listed set of tools. source

At a glance

Topic	Omnia	Foundry Agent Service, per its docs
Immutable versions	yes A versioned pack: prompts, tools, policy and tests. docs	documented Immutable agent versions. source
End-user identity to tools	yes OIDC or edge trust, carried to every call. docs	documented Entra Agent ID and on-behalf-of. source
Traffic splitting	yes Stepped rollout with automatic rollback. docs	not documented Not supported. source
Voice agent testing	yes Simulated callers, barge-in, dead air. docs	not documented Not supported. source
Adversarial testing	yes Against the agent’s real tools. docs	partly Red-teaming agent, text only, mock tools. source
Deterministic argument policy	yes A CEL rule on every call. docs enterprise	partly Classifier guardrails, preview. source
Runs outside Azure	yes Your cluster, AWS or Google. docs	not documented Not documented. source

Common questions

Can I use Omnia with Foundry?: Yes. Omnia deploys a pack to Azure AI Foundry with one command, uses Azure OpenAI and Foundry models, and runs its scenarios against the deployed agent.
Does Omnia publish agents to Teams?: Omnia serves agents over WebSocket, REST, A2A or MCP. Deployed to Foundry, the same agent can use Foundry’s publishing.

Put your own agent through the gate.

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

Foundry Agent Service claims are from Microsoft’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 →