> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://help.sigmacomputing.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://help.sigmacomputing.com/_mcp/server.

# Chat with Sigma agents

> Chat with Sigma agents in workbook chat elements to ask data questions and accomplish analysis tasks.

> **Note**
>
> The use of AI features is subject to the following [disclaimer](/docs/notice-for-enabling-ai-enabled-features-in-sigma).

> **Note**
>
> Usage of this feature uses consumption credits. For details about what usage is billed, see [About billable usage events](/docs/about-billable-usage-events).

If you have access to a workbook that contains a chat element, you can chat with an agent to ask questions of the data in the workbook, accomplish tasks, enrich your understanding with context from third-party systems, and more.

## User requirements

You can chat with a Sigma agent if you have the following:

* **Can view** access or higher to a workbook that contains a chat element.
* The **View workbooks** permission enabled on your account type.

> **Info**
>
> An agent might be configured with tools that you do not have access to or permission to use, such as an MCP server or an action that edits an input table. If you do not have permission to perform an action or access to a tool, the agent cannot use those tools.

## Chat with an agent in a workbook

To chat with a Sigma agent in a workbook:

1. Open a workbook with a chat element.
2. When the workbook page with the chat element loads, the agent describes what it can do and what it has access to.
3. Enter a prompt or query to chat with the agent.

   Some actions that the agent can perform might prompt you for approval. To allow the agent to perform the action, click **Approve**, or to skip performing the action, click **Skip**.

   If the agent uses an MCP connector that requires authorization, such as one that accesses Atlassian services, you are prompted to **Authorize** the MCP connector so the agent can perform actions with your access.

## Access and manage recent chats

If [chat history is enabled for your organization](/docs/configure-chat-history), you can view, resume, rename, and delete your own recent chats with Sigma agents in chat elements. The retention period depends on your organization's chat history settings.

Sigma retains a separate chat history for each chat element, so the **Recent chats** list in the following steps includes chats with one or more agents in the selected chat element.

1. Open a workbook with a chat element.
2. In the element header, click  **View chat history**, then complete any of the following tasks in the popover:

   * To view or resume a chat, select it from the list. Sigma reopens it where you left off.
   * To rename a chat, click  **More** next to the current chat name, then select **Rename**. Edit the name inline and press <kbd>Enter</kbd>.
   * To delete a chat, click  **More** next to the chat name, then select **Delete**. The chat is immediately deleted from your recent chats, but admins can still review it in the [AI usage dashboard](/docs/ai-usage).
   * To start a new chat, select  **New chat**. Sigma closes the current chat and opens a new one.

   > **Info**
   >
   > When you resume a chat, it uses the current agent selected in the chat element, even if you started the chat with a different agent.

## Choose an agent to chat with

If you have **Can explore** access to the workbook and the **Full explore** permission enabled on your account type, you can change which agent you chat with:

1. In the workbook, click **Customize this view**.
2. Select the chat element.
3. In the **Properties** tab of the editor panel, click **Select agent** and choose a different agent.
4. Return to the chat element and start chatting with the new agent. When you exit the [custom view](/docs/create-and-interact-with-custom-views), the agent selection returns to the agent available in the published version of the workbook.

## Related resources

* [About Sigma agents](/docs/sigma-agents)
* [Build Sigma agents](/docs/build-agents)
* [Example use cases for Sigma agents](/docs/example-agent-implementations)