Autotune Experiments in Warehouse Native have a setup similar to cloud [Autotunes](/autotune/overview). In Warehouse Native, Autotune success events are pulled from a Metric Source, and results are computed in your warehouse.

{% callout type="info" %}
Continuous Autotune in WHN is in beta. Contact the team to
get it enabled in your account.
{% /callout %}

## Creating an Autotune

To set up an Autotune on Warehouse Native, start by defining your objective. The objective can be an *event* or a *value* from a Metric Source. For detailed instructions, refer to [how to set up a Metric Source](/statsig-warehouse-native/configuration/metric-sources).

You can also specify the optimization direction (Maximize or Minimize) to determine how Autotune evaluates variant performance.

{% figure %}
![Autotune configuration interface](/images/statsig-warehouse-native/features/autotune/autotune-config.png)
{% /figure %}

1. Navigate to the [Experiments section](https://console.statsig.com/experiments) in the sidebar of the Statsig Console.
2. Click on the [Autotune tab](https://console.statsig.com/autotune) at the top.
3. Click the Create button and enter the name and description of the Autotune Experiment that you want to create.
4. Select an ID Type for your Experiment.
5. Create and name your variants for your Autotune Experiment. The variant listed as Control/Default is returned when the Autotune Experiment isn't running.
6. Select your Metric Source that you defined earlier as shown below.

{% figure %}
![Autotune metric source configuration interface](/images/statsig-warehouse-native/features/autotune/autotune-metric-source.png)
{% /figure %}

The following parameters are available:

| Parameter | Description |
|---|---|
| Exploration Window | The initial time period where Autotune splits traffic equally. Useful for noisy or temporal metrics where hourly swings can bias initial measurements. |
| Attribution Window | The maximum duration between the exposure and success event that counts as a success. 1 hour is recommended for most applications; adjust if the success event is expected to lag the exposure event by several hours. |
| Winner Threshold | The "probability of best" threshold a variant must reach for Autotune to declare it the winner, stop collecting data, and direct all traffic. A lower value results in faster decisions but increases the probability of selecting the wrong winner. |

Click **Create** to finalize the setup.

7. The Autotune is configured and ready. Click **Start** when you are ready to launch your Autotune test.