> ## Documentation Index
> Fetch the complete documentation index at: https://docs.oumi.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# NEXT STEPS

> Where to go from here

Once your model is in production, you can begin using it for inference and applying it to downstream applications. Oumi keeps all your project assets (models, datasets, evaluations, evaluators, and recipes) automatically version controlled, so you can iterate and enjoy exporting models for repeatable deployments.

As data and usage patterns change, performance will invariably degrade, making periodic retraining necessary. When this happens, you can use Oumi to [evaluate](/guides/evaluations), [retrain](/guides/training), and [redeploy](/guides/deployment) your model seamlessly within the same workflow.

<CardGroup cols={2}>
  <Card title="Running evaluations" icon="diagram-project" href="/guides/evaluations">
    Using the Builder to evaluate your model.
  </Card>

  <Card title="Diagnosing failure modes" icon="users-gear" href="/guides/evaluations/failure-modes">
    Generate a new dataset directly from an evaluator’s identified failure modes.
  </Card>
</CardGroup>