# Agent Settings

## Cost Control

Go to the Agent Settings tab on the lefthand-side menu. Once there, you will see the Cost Control window, you can set spending limits for usage of AI models by members of your organization.

There are two types of limits you can impose.

First, adjust your entire organization’s monthly cost limits by going to Monthly Organizational Token Cost Cap and entering the amount in the box next to the $ symbol.

Secondly, you can limit the cost per individual user. Next to Monthly Single User Token Cost Cap, enter the amount in the box next to the $ symbol.

<figure><img src="/files/3HKX2FyFhUKLgx5Bs0Eg" alt=""><figcaption></figcaption></figure>

#### Per-Team Quota Enforcement ([v6.1.0](https://docs.tabnine.com/main/administering-tabnine/managing-your-team/settings/pages/risy3bTOlfBfgFRRXK8K#v6.1.0))

You can also set a per-team quota.

Select a team from the dropdown in the upper righthand corner.

Set your monthly cost cap.

Then hit <mark style="background-color:$primary;">**Save**</mark> to save the changes.

Team usage is tracked against the cap, and requests are blocked after the limit is reached until the next reset period.

The Agent Usage analytics view shows each team’s consumed quota so you can see which teams are close to their limits.

### Agent Features

#### Restricting Agent from Running Tools Outside the Workspace ([v6.1.0](https://docs.tabnine.com/main/administering-tabnine/managing-your-team/settings/pages/risy3bTOlfBfgFRRXK8K#v6.1.0))

Tabnine Agent enforces workspace boundaries for file-system tools, preventing it from accessing or modifying files outside the active project directory. This protection is on by default and requires no configuration.

To activate, toggle the option under the Agent Features section.

<figure><img src="/files/0PzWeG52HDx38cC63WTi" alt=""><figcaption></figcaption></figure>

\ <br>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.tabnine.com/main/administering-tabnine/managing-your-team/settings/agent-settings.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.