> 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.

# Configure chat history (Beta)

> Set up chat history for Sigma agents conversations.

This documentation describes one or more public beta features that are in development and available only to customers who meet certain conditions. For more information, contact your Account Executive.

Beta features are subject to quick, iterative changes; therefore, the current user experience in the Sigma service can differ from the information provided in this page.

This page should not be considered official published documentation until Sigma removes this notice and the beta flag on the corresponding feature(s) in the Sigma service. For the full beta feature disclaimer, see [Beta features](/docs/sigma-product-releases#beta-features).

Before users can see and revisit past chat conversations with [Sigma agents](/docs/chat-with-agent), an admin must turn on chat history for the organization.

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

## About chat history

* Chat history is not stored in your data platform. It is stored by Sigma in the same cloud and region as your Sigma organization.

Consider the following for chat history for Sigma agents specifically:

* Chat history for a Sigma agent is available when you chat with the agent using a chat element in a workbook. Chat history is specific to each chat element.
* Stored chat conversations are user-specific. A user can only review and restart their own chat conversations. If an admin wants to review all chat conversations for an agent, [configure the AI usage dashboard](/docs/configure-a-usage-dashboard-for-assistant).
* If you delete the chat element, the agent remains available but the history of conversations that occurred on that element are removed. If you restore a version of the workbook from before the element was deleted, the history is restored with the chat element.
* Chat conversations are version-specific. Chat conversations that happen in the published version of a workbook are not available to tagged versions of the workbook and vice versa.
* Chat conversations are shared across a user's custom and saved views. If a user has a conversation with an agent in a saved view, then returns to the published version, they can resume their chat conversation in the published version of the workbook.

## Requirements

* You must be assigned the Admin [account type](/docs/create-and-manage-account-types).
* Your organization must have granted Sigma storage rights for both inputs and outputs. If your organization only allows partial data storage, or none, chat history is currently turned off and cannot be turned on.

## Limitations

* You cannot store chat history in your own storage service.
* You cannot retain chat history indefinitely. The longest available retention period is 90 days.
* Chat history is only stored for chat conversations with Sigma agents associated with a chat element. Other conversations, such as with agents on the home page, Sigma Assistant in the workbook or on the home page, or warehouse agents, are not stored.

## Configure chat history

To turn chat history on or off for your organization:

1. Go to **Administration** > **AI settings**, then choose the **Assistant** tab.
2. In the **Chat history** section, select **Edit**.
3. To allow Sigma to store chat history, turn on the **Chat history** toggle. Otherwise, turn off the **Chat history** toggle.
4. If you turned on chat history, choose how long to store the chat history data:

   * 30 days
   * 60 days
   * 90 days

   Chat storage is based on when the last message was sent in a chat conversation.
5. Select **Save**.

When you turn off chat history, Sigma does not store new chat conversations. Chat conversations that were already stored are deleted when the retention period for the chat is reached.

## Related resources

* [Chat with Sigma agents (Beta)](/docs/chat-with-agent)
* [Configure AI features for your organization](/docs/configure-ai-features-for-your-organization)