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

# Remediate a Domino endpoint

After reviewing the [data drift](/cloud/platform-capabilities/features/monitoring/5-use-monitoring/3-analyze-data-drift) and [model quality monitor](/cloud/platform-capabilities/features/monitoring/5-use-monitoring/4-analyze-model-quality), use the monitoring results and [Cohort Analysis](/cloud/platform-capabilities/features/monitoring/6-remediation/1-review-cohort-analysis) to determine whether there are concerns with your model. If you do have concerns, [review your data](#review-your-data).

If you want to review the model and its associated code to investigate further, you can [reproduce the original code commits and artifacts](#reproduce-the-environment) in the environment in which you deployed the model. If necessary, you can update the model code or retrain it with the latest production data. Then you can [deploy a new, improved version of the Domino endpoint](#publish-a-new-domino-endpoint).

## Review the Domino endpoint predictions

Domino automatically creates a prediction dataset named `prediction_data` for every project that can be accessed from any workspace. The predictions are in Parquet format and are updated hourly as the Domino endpoint processes inputs. If there is no data in an hour, no file is created. If you configured [data drift monitoring](/cloud/platform-capabilities/features/monitoring/5-use-monitoring/3-analyze-data-drift) or [Set up Model Quality Monitoring](/cloud/platform-capabilities/features/monitoring/5-use-monitoring/4-analyze-model-quality) then the stored prediction data is automatically consumed by the Model Monitor.

By default, a daily job deletes data older than 30 days. Your administrator defines the retention policy for predictions.

### Review your data:

1. In your workspace, open the IDE.

2. Use the following paths to read the data:

   * To load individual Parquet files:

<Tabs>
  <Tab title="To load individual Parquet files for DFS-based projects">
    ```console theme={null}
    /domino/datasets/local/prediction_data/<model_version_id>/$$date$$=<date_in_utc>/$$hour$$=<hour_in_utc>/predictions_<uuid>.parquet
    ```
  </Tab>

  <Tab title="To load individual Parquet files for GIT-based projects">
    ```console theme={null}
    /mnt/data/prediction_data/<model_version_id>/$$date$$=<date_in_utc>/$$hour$$=<hour_in_utc>/predictions_<uuid>.parquet
    ```
  </Tab>

  <Tab title="To load the entire Parquet dataset for DFS-based projects">
    ```console theme={null}
    /domino/datasets/local/prediction_data/<model_version_id>
    ```
  </Tab>

  <Tab title="To load the entire Parquet dataset for Git-based projects">
    ```console theme={null}
    /mnt/data/prediction_data/<model_version_id>/$$date$$=<date_in_utc>/$$hour$$=<hour_in_utc>/predictions_<uuid>.parquet
    ```
  </Tab>
</Tabs>

<Warning>
  Do not rename the generated Parquet files and directories. Doing so can cause inconsistent behavior.
</Warning>

## Reproduce the environment

### Prerequisites

<Tabs>
  <Tab title="For Git-based projects">
    * This feature is only enabled for models published in Domino 5.0 and higher.
  </Tab>

  <Tab title="For Domino File System-based projects">
    * This feature is available for pre-5.0 published models as well as newly-published models, as long as no additional Git repositories are involved.
  </Tab>
</Tabs>

### Remediate the model

1. From the navigation pane, click **Endpoints**.

2. Click the model that you want to remediate and then click **Open in Workspace**.

3. From the Open in New Workspace and Branch window, type a name for the workspace.

4. Select a **Hardware Tier**.

5. In New Branch Name, type a name for the code branch.

6. Click **Open**. A Domino workspace opens and is ready for you to take remedial action.

   <Note>
     If you manage file changes and code commits outside of Domino (such as in an external Git client) and only use Domino to publish the Domino endpoint, the window will show a list of tools. Select from these tools to create a new workspace.
   </Note>

## Publish a new Domino endpoint

When you reproduce a workspace, as you did in the [Reproduce the environment](#reproduce-the-environment) topic, Domino creates a branch in every repository involved in the project.

To publish a new model based on this reproduced branch, you must apply the [commit to the master branch](/cloud/platform-capabilities/core-concepts/workspaces/use-git-in-your-workspace) because Domino supports Git-based projects. The way that you do this depends on whether you are working with a Domino File System-based project or a Git-based project.

<Tabs>
  <Tab title="Commit projects based on the Domino File System (DFS)">
    1. Go to the Project.
    2. Click **Code** in the navigation bar.
    3. From the **Branch** list, select the reproduced branch.
    4. Click **Revert Project** to ensure that the commits made in this branch are added in the Master branch.

           <Note>
             **Revert Project** only works for the DFS files. For imported Git repositories or projects, you must revert the artifacts independently.
           </Note>
  </Tab>

  <Tab title="Commit Git-based projects">
    * In a Domino workspace or the Git tool of your choice, merge your latest code update into the master branch.

    <Note>
      Perform the same merge operation for any artifacts (such as `.pkl` files) that you maintain in a separate repository. You can use Domino for the artifacts.

      1. In your Git-based project, in the navigation pane, click **Artifacts**.
      2. Click **Revert Project** to restore the artifacts from your reproduced branch to the master branch.
    </Note>
  </Tab>
</Tabs>

Go to the **Domino endpoint** section of your project to publish a new Domino endpoint or a new version of an existing Domino endpoint. See [Publish the Domino endpoint](/cloud/platform-capabilities/features/model-deployment).