> For the complete documentation index, see [llms.txt](https://docs.otari.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.otari.ai/how-to-guides/manage-workspaces.md).

# Manage Workspaces

Create, switch, organize, and delete workspaces in the otari.ai dashboard.

For background on what workspaces are and how they fit into the organization, see [Workspaces](/learn/workspaces.md).

***

### Create a workspace <a href="#h_118405b983" id="h_118405b983"></a>

1. From the main dashboard, click on **Organization** in the bottom-left corner. You'll automatically be taken to the Workspaces tab.
2. Click on **Create workspace**.
3. Give it a name, an optional description, and create it.

Workspaces inherit all provider keys available at the organization level. If a provider has multiple keys, you can choose which one a specific workspace should use. This setting determines which credential is used to send requests, rather than which models are available.

To select which provider keys a workspace can use, click **Edit** (the pencil icon) and update the settings accordingly.

{% hint style="warning" %}
**Capture the workspace ID after creation**

If you plan to use the SDK, CLI, or automation, copy the `workspace_id` from workspace settings. You'll need it then.
{% endhint %}

***

### Manage a workspace <a href="#h_5324f4e103" id="h_5324f4e103"></a>

From the main dashboard, click on **Organization** at the bottom of the menu, then use the sidebar to move between different areas:

* **Usage**: for analytics and request history.
* **Members**: to invite members and manage their workspace-specific access.
* **Spend & Budgets**: to define how much can be spent and over what period. To enforce the budget, you need to create a **spend ceiling** that applies it to an organization, workspace, or API key.
* **Providers**: to manage provider-key access. All workspaces within the organization can use the credentials for connecting to model providers, but you can also choose which provider keys a workspace can use (see **Create a workspace**, above).
* **Guardrails**: to check the content users send to a model. Each guardrail can be applied to specific workspaces and configured to either block requests that meet its conditions or record them for monitoring without blocking them.

***

### Organize workspaces by environment <a href="#h_1255ec061b" id="h_1255ec061b"></a>

For naming conventions and team patterns, see [Workspaces](/learn/workspaces.md).

***

### Delete a workspace <a href="#h_6105b01057" id="h_6105b01057"></a>

1. From the main dashboard, click **Organization** in the bottom-left corner. You’ll be taken directly to the **Workspaces** tab.
2. Find the workspace you want to delete, click **Delete** (the bin icon), and confirm the deletion.

{% hint style="warning" %}
**This action is permanent**

* Removes provider access and workspace-scoped configuration
* Deletes all usage history and analytics
* Removes all budget configuration
* Disables any API tokens scoped to this workspace

Move any apps that still use this workspace ID before you delete it.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.otari.ai/how-to-guides/manage-workspaces.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.