# Create an experiment

This page shows you how to interact with Experiments on Gemini Enterprise Agent Platform
by using the side panel in Colab Enterprise.

To access Google Cloud services and APIs by running code in
your Colab Enterprise notebook, you can use the
credentials associated with your Google Account. To learn more, see
[Access Google Cloud services and APIs](https://docs.cloud.google.com/colab/docs/run-code-adc.md.txt).

The side panel is an additional way to interact with
Experiments on Agent Platform without leaving the
Colab Enterprise interface.

The side panel appears to the right of an open notebook.

![Buttons on the side panel to the right of an open notebook](https://docs.cloud.google.com/static/colab/images/side-panel.png)

## Before you begin

### Required roles


To get the permissions that
you need to use the side panel in a Colab Enterprise notebook,

ask your administrator to grant you the
following IAM roles on the project:

- [Colab Enterprise User](https://docs.cloud.google.com/iam/docs/roles-permissions/aiplatform.md.txt#aiplatform.colabEnterpriseUser) (`roles/aiplatform.colabEnterpriseUser`)
- [Agent Platform User](https://docs.cloud.google.com/iam/docs/roles-permissions/aiplatform.md.txt#aiplatform.user) (`roles/aiplatform.user`)


For more information about granting roles, see [Manage access to projects, folders, and organizations](https://docs.cloud.google.com/iam/docs/granting-changing-revoking-access.md.txt).


You might also be able to get
the required permissions through [custom
roles](https://docs.cloud.google.com/iam/docs/creating-custom-roles) or other [predefined
roles](https://docs.cloud.google.com/iam/docs/roles-overview#predefined).
One or more of the required roles includes the `dataform.repositories.list` permission. Users who are granted the `dataform.repositories.list` permission or the [Code Creator
(`roles/dataform.codeCreator`)](https://docs.cloud.google.com/dataform/docs/access-control#dataform.codeCreator) role in a project can list the names of code assets in that project by using the Dataform API or the Dataform command-line interface (CLI). Non-administrators using BigQuery Studio can only see code assets that they created or that were shared with them.

## Experiments on Agent Platform

Experiments on Agent Platform helps you track and analyze different
model architectures, hyperparameters, and training environments by
letting you track the steps, inputs, and outputs of an experiment run.
To learn more, see [Introduction to
Experiments on Agent Platform](https://docs.cloud.google.com/gemini-enterprise-agent-platform/machine-learning/experiments/intro-vertex-ai-experiments).

## Create and view an experiment

You can create and view the results of an experiment by using the
side panel in Colab Enterprise.

1. In the Google Cloud console, go to
   the Colab Enterprise **My notebooks** page.

   [Go to My notebooks](https://console.cloud.google.com/agent-platform/colab/notebooks)
2. In the **Region** menu, select the region that contains your notebook.

3. Click the notebook that you want to open. If you haven't created a notebook yet,
   [create a notebook](https://docs.cloud.google.com/colab/docs/create-console-quickstart.md.txt#create).

4.
   To the right of your notebook, in the side panel, click the
   ![](https://docs.cloud.google.com/static/colab/images/icon-manage-experiments.png) **Experiments** button.

   The side panel expands the **Experiments** tab.
5. Click the **Insert sample code** button.


   Colab Enterprise adds code cells to your notebook for
   interacting with an experiment.
6.
   In your notebook, find the code cell that stores parameter values.
   You'll use these parameters to interact with
   Experiments on Agent Platform.

7.
   Update the values for the following parameters:

   - `PROJECT_ID`: The ID of the project that your notebook is in.
   - `REGION`: The region that your notebook is in.
   - `BUCKET_URI`: A Cloud Storage bucket URI, in the format `gs://BUCKET_NAME`. This can be an existing bucket, or you can create it when you run the code. This bucket must be in the same project and region as your Colab Enterprise notebook.
   - `EXPERIMENT_NAME`: The name of your experiment. If your experiment doesn't exist, Experiments on Agent Platform creates one.
8.
   If you need to create your Cloud Storage bucket, find and
   uncomment the following line of code:

   ```
   # ! gcloud storage buckets create {BUCKET_URI} --location={REGION} --project={PROJECT_ID}
   ```
9. Run the code cells that the side panel added to your notebook.

10.
    After the last code cell runs, click the
    ![](https://docs.cloud.google.com/static/colab/images/icon-manage-experiments.png) **View
    experiment** button that appears.

11.
    In the side panel, click the **Runs** tab or
    **Details** tab to see information about your experiment.
    To learn more, see
    [Create
    and manage experiment runs](https://docs.cloud.google.com/gemini-enterprise-agent-platform/machine-learning/experiments/create-manage-exp-run).

    The side panel shows information about your experiment runs. You can create, manage, and delete runs by using [Experiments on Agent Platform
    in the Google Cloud console](https://console.cloud.google.com/agent-platform/experiments) or through the Agent Platform API.

## What's next

- Learn more about
  [Experiments on Agent Platform](https://docs.cloud.google.com/gemini-enterprise-agent-platform/machine-learning/experiments/intro-vertex-ai-experiments.md.txt).

- To find a notebook that can help you get your project started quickly,
  see the [notebook gallery](https://console.cloud.google.com/agent-platform/colab/notebook-gallery).