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

# Enabling Box AI Studio and Managing Agents

> [!NOTE]
>
> Box AI Studio is only available for Enterprise Advanced accounts.

Box AI Studio allows admins to configure and build AI agents for their organizations to use in no-code solutions.

## Admin Enablement

Within the Admin Console, go to the **Box AI section** and then the **Settings** tab and set the permissions for both users and groups. If your organization has not fully enabled Box AI, you can select **Enable for All** to do so for all services.

![Box AI Settings page listing AI features with Enabled for all status and Configure access tooltip on Box AI Home.](https://mintcdn.com/product-docs/pLC-uWMnSTtWjsJb/images/box-ai/box-ai-settings-page-listing.png?fit=max\&auto=format\&n=pLC-uWMnSTtWjsJb\&q=85\&s=b7b6eb1409c2fe6c4ded0d998ec56a98)

### Enabling AI Settings

To enable Box AI Studio, first enable Box AI home:

1. Navigate to **Box AI -> Settings**.
2. Select **Configure** on **AI Home**.
3. Select **Enable**.

Once a Box AI setting is enabled, admins can toggle between the existing Box AI Agent experience (i.e., the legacy agents experience) and the new Agent experience by enabling the AI Home in the Box AI Settings page.

Considerations with AI Home:

* After enabling AI Home, organizations that had AI Studio enabled with the legacy version will automatically have the new version of AI Studio enabled.
* After enabling AI Home, Admins cannot create new legacy agents. However, they can still modify existing legacy agents.

## Upgrading Agents

When accessing legacy agents, you can upgrade the agent to begin using updated features. When configuring a legacy agent, select **Upgrade Agent** to create a new agent that mirrors the legacy agent.

![Blue banner reading Upgrade Legacy Agent with Upgrade Agent button on the right.](https://mintcdn.com/product-docs/pLC-uWMnSTtWjsJb/images/box-ai/blue-banner-reading-upgrade-legacy.png?fit=max\&auto=format\&n=pLC-uWMnSTtWjsJb\&q=85\&s=14db55a4f38437f2958fe2f200201b99)

The process sets the model to **Auto** by default and copies:

* Agent name and appends "(new)" to it
* Description
* Custom instructions (if the legacy agent has both Q\&A and Compose modes, only the Q\&A custom instruction is copied; otherwise, the entire custom instruction is copied)

The new agent is **disabled** by default. The existing legacy agent remains active and unaffected unless manually disabled.

> [!NOTE]
>
> For new and upgraded agents, API usage is not supported.

## Enabling Access for Co-Admins

To enable Box AI Studio for Co-Admins:

1. Go to the **Admin Console ->** then **Users & Groups**.
2. Select **View** on the co-admin to configure.
3. Select **Edit** on the **Role and Access Permissions** section.
4. Toggle on for **AI Studio**.

## Models tab in Box AI Settings page

The **Models** tab in the Box AI Settings is a catalog of all the models available for Box AI. The list displays the model name, provider, tier, whether it is available in Pro Mode, compliance badges (FRD, FRC, IL2, IL4), and query usage.

As an admin, you can enable or disable models here by selecting the **...** button (**More options** menu) > **Enable** or **Disable**. You can also open **Model Settings** to set [compliance requirements](#compliance-requirements) for FedRAMP or DoW.

![Enable or disable a specific model.](https://mintcdn.com/product-docs/1VNqak0e-UF218wK/images/box-ai/model-enable-disable.png?fit=max\&auto=format\&n=1VNqak0e-UF218wK\&q=85\&s=08574063140415546a51dea451f12a55)

> [!WARNING]
>
> Currently, disabling models only impacts model selection for the Box Agent and custom agents, including the Box Agent in Automate and the Box Agent (Pro Mode). However, in the future, disabling models can also impact additional products or features, such as Box Extract, Box Automate, and Shield Pro.

## Compliance support

Your organization is responsible for configuring AI models to meet your compliance requirements. Box establishes FedRAMP and related boundaries at the product and feature level. You choose which models stay available, and Box enforces that configuration.

Visit [Supported AI models - Box Dev Docs](https://developer.box.com/guides/box-ai/ai-models) for a full list of models and providers.

## Security

### Guardrails

Guardrails help protect your organization from unauthorized access to sensitive content by restricting agent actions based on your organization's policies.

To control the scope of an agent, you can define which content and users have restrictions. Guardrails set the operating boundaries for an agent, ensuring it only takes actions within the scope you've defined. For example, you can restrict an agent from adding external collaborators, so the agent behaves predictably regardless of how it's triggered.

To configure guardrails:

1. Open guardrails settings in the agent configuration.
2. Select a section to modify:
   * **Create File**
3. Choose a scope:
   * **No restrictions**: Apply to all matching content or users.
   * **Allow on specific items**: Apply only to the items or users you select.
   * **Don't allow on specific items**: Apply broadly, except for the items or users you exclude.
4. Select the folders, classifications, or users referenced by your selection.
5. Save the agent configuration to apply your guardrail changes.

> [!NOTE]
>
> Guardrails don't apply to session folders. If guardrails block the agent from saving a file to another folder, the agent saves the file in the session folder instead.

For more information on each configuration, see [Guardrails in Box AI](https://docs.box.com/en/box-ai/admins/guardrails-in-box-ai.md).

> [!NOTE]
>
> * Saving the configuration applies the guardrails to new agents only.
> * When you open a new agent, the guardrails are applied to the agent, but you can modify them later.

> [!NOTE]
>
> As part of processing a query, Box can choose the best available model from the list of enabled models. The final generated answer always uses the user-selected model.

### Compliance requirements

Set compliance requirements from **Model Settings** on the **Models** tab. Non-compliant models are disabled automatically, including newly added models. These controls apply to models that Box Agents use directly. Both requirements are off by default.

**Require FedRAMP certification**

1. Go to **Admin Console** > **Box AI** > **Models**.
2. Select **Model Settings**.
3. Turn on **Require FedRAMP certification**.
4. Select **FedRAMP Class D (High) (FRD)** or **FedRAMP Class C (Moderate) (FRC)**. Class D is selected by default when you turn the toggle on.
5. Select **Save**.

**Require DoW compliance**

1. Go to **Admin Console** > **Box AI** > **Models**.
2. Select **Model Settings**.
3. Turn on **Require DoW compliance**.
4. Select **DoW Impact Level 4 (IL4)** or **DoW Impact Level 2 (IL2)**. IL4 is selected by default when you turn the toggle on.
5. Select **Save**.

**How compliance requirements affect models**

When a compliance requirement is on:

* A banner on the **Models** page shows the requirement you set and how many non-compliant models were disabled.
* Non-compliant models are disabled and listed under an expandable row such as **models hidden by compliance requirements**. Expand that row to review them.
* If both FedRAMP and DoW requirements are on, only models that meet both stay enabled in the main list.
* New models without the matching compliance tag start disabled for your enterprise. Box enables them automatically after they are certified for that requirement.
* You can't enable a model that's hidden by a compliance requirement while the requirement is on.
* You can disable a model that meets the selected requirement from the model's **More options** menu.
* You must keep at least one enabled model. To disable the last enabled model, enable another compliant model first.

**Turn off or lower a compliance requirement**

When you turn off a compliance requirement in **Model Settings**, or change the selection to a less restrictive option (for example, from Class D to Class C, or from IL4 to IL2), Box re-enables previously restricted models that meet the new setting. Models that an admin disabled manually stay disabled.

**Audit events for compliance requirements**

When an admin turns a compliance requirement on or off, Box emits an enterprise event. You can ingest these events through Box Events.

### Recommended setup for FedRAMP and DoW compliance

1. Go to **Admin Console** > **Box AI** > **Settings**.
2. Select **Configure** on **AI Home**.
3. Enable AI Home only for yourself by selecting **Enable for selected users and groups**.
4. Go to **Box AI** > **Models**.
5. Select **Model Settings**, turn on **Require FedRAMP certification**, **Require DoW compliance**, or both, and select the levels your organization requires. Select **Save**.
6. Review the **Models** list and any models hidden by compliance requirements. Disable any remaining models that your policies exclude, even if they carry a compliance badge.

![List of available compliance filters.](https://mintcdn.com/product-docs/cwJeew3iU12hOBZZ/images/box-ai/model_filters.png?fit=max\&auto=format\&n=cwJeew3iU12hOBZZ\&q=85\&s=077305818b581e62017d0bc2237c2dea)

You can then enable AI Home for a wider group of users or for your whole organization.

If you prefer not to use compliance requirements in **Model Settings**, use the **Compliance** filter (FRD, FRC, IL2, IL4) and disable models that do not meet your requirements one at a time.

> [!NOTE]
>
> Government customers who must abide by the DoW order regarding restricting use of Anthropic must manually disable all Anthropic models, even when compliance requirements are on.

### When disabled models affect agents

Disabling a model, whether by a compliance requirement or manually, can change how agents behave.

**The agent's selected model is disabled.** The custom agent stops working. AI Studio shows a red warning icon in the agents list. Hover over the icon for a prompt to review the agent configuration. In AI Home, the agent is grayed out in the agent dropdown. Reconfigure the agent to use an enabled model.

**Pro Mode models are disabled for an agent that has Pro Mode on.** The agent keeps working as long as at least one enabled model remains available for it. AI Studio shows a yellow warning icon in the agents list. Hover over the icon for a prompt to review the configuration. In AI Home, Pro Mode is grayed out for that agent, with a tooltip that Pro Mode is unavailable.

**Box Agent with Auto.** If you disable a model that Auto requires, Box replaces Auto with the first available non-restricted model in the ranked list. If no model remains available for your enterprise, Box Agent is removed from the AI Home dropdown.

## Managing Custom Box Agents in Box AI Studio

To see a list of agents available, go to the **AI Studio** tab from the Box AI section in the Admin Console.

![AI Studio agents table listing Box, Marketing Agent, and HR Agent with access status and monthly queries.](https://mintcdn.com/product-docs/pLC-uWMnSTtWjsJb/images/box-ai/ai-studio-agents-table-listing.png?fit=max\&auto=format\&n=pLC-uWMnSTtWjsJb\&q=85\&s=3004aee4b89eef9c8d20c1b5289d0a8a)

### Managing Legacy Agents

From the legacy **Agent** view, you can see:

* Name
* Capabilities
  * Content Q\&A
  * Text Generation
* Access
  * Enabled
  * Enabled for selected
  * Disabled
* Monthly Queries
* Last Used

You can filter from:

* Type
  * Content Q\&A
  * Text Generation
* Access
  * Enabled
  * Enabled for selected
  * Disabled

For additional options, hover over the right side of the agent and select the ellipsis to:

* Edit
* Access
* Delete
  * **Deleting an agent cannot be undone.**

To set the AI model provider, hover over the right side of the agent and select the ellipsis to choose between the Box Recommended option and specific providers.

You can also upgrade the legacy agent from the right ellipsis button, selecting **Upgrade Agent** from the dropdown menu.

### Managing Agents

To see a list of agents available, go to the AI Studio tab from the Box AI section in the Admin Console.

From the **Agent** view, you can see:

* Name
* Access
* Created By
* Monthly Queries
* Last Used

You can filter from:

* Access
  * Enabled
  * Enabled for selected
  * Disabled

For additional options, hover over the right side of the agent and select the ellipsis to:

* Edit
* Duplicate
* Delete
  * Deleting an agent cannot be undone.
