# Assurance — it passed on Friday. That says nothing about Tuesday | AltairaLabs

> Run the same cases against every model you allow and compare outcomes side by side, before release and against the real work. Every run is a record you can hand to someone who asks.

Canonical page: https://www.altairalabs.ai/assurance/

Assurance

# It passed on Friday. That says nothing about Tuesday.

Nothing in your repository changed. The provider shipped a new model snapshot, and an agent that had settled ten thousand invoices the same way starts deciding differently. Run the same cases against every model you allow and compare the outcomes side by side. Every run is a record you can hand to someone who asks.

awaiting capture Every evaluation, load test and data generation run against a project, with its worker pool and how far through it is. images/product/runs.png

![The Runs view in Omnia — every evaluation and load test run against a project]()

evaluation, load and data gen · against one project 480 cases · eight workers · a verdict on each

before it ships

## Everything you can only do when nothing is at stake.

The awkward cases put through the agent’s real tools: the malformed record, the duplicate claim, the request that looks legitimate and isn’t. Adversaries trying to talk it out of its rules. And where there is a voice line, callers who interrupt, go quiet, or talk over the top of it.

scenariospersonasself-playadversarialduplex voice

after it ships

## Then the same tests run against the real work.

The same assertions at the deploy gate, and inline against the real work: sampled and rate-limited, scored, and used to decide whether a rollout carries on or stops itself.

inline in productionjudge scoringscheduled runsgated promotion

## Changing an agent while someone is mid-sentence.

A new version goes out to a slice of the traffic first, and carries on only if the numbers hold. If they don’t, it goes back on its own, without anyone watching a dashboard.

The verdict is computed from the platform’s own record of what happened. It doesn’t depend on a monitoring stack being installed.

sticky sessions

Someone halfway through a conversation, or a run halfway through its work, stays on the version it started on. A rollout is not a reason for one customer to get two different agents.

graceful drain

On shutdown, in-flight work finishes. That matters more when the thing in flight is a payment than when it’s a chat.

and it scales itself

Replicas follow the load, so the Monday queue and the Sunday trickle cost differently.

## Once is a sample size of one.

The same cases run ten thousand wide, on one set of machines in your cluster.

[Point it at an agent you already run](https://promptarena.altairalabs.ai)

the tour 7 of 8

1.  [Platform](https://www.altairalabs.ai/platform)
2.  [The console](https://www.altairalabs.ai/console)
3.  [Run anywhere](https://www.altairalabs.ai/run-anywhere)
4.  [Governance](https://www.altairalabs.ai/governance)
5.  [Privacy](https://www.altairalabs.ai/privacy)
6.  [Memory](https://www.altairalabs.ai/memory)
7.  Assurance
8.  [At scale](https://www.altairalabs.ai/scale)

[Memory](https://www.altairalabs.ai/memory) [At scale: ten thousand different conversations](https://www.altairalabs.ai/scale)