> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://help.sigmacomputing.com/docs/configure-ai-features-for-your-organization/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://help.sigmacomputing.com/_mcp/server. # Configure AI features for your organization > Configure AI features for a Sigma organization to accelerate insights, automate tasks, and enable Assistant, agents, and more. Several features in Sigma use AI to accelerate insights and tasks that you might perform in Sigma: * **Sigma Assistant** is a natural language query (NLQ) interface that allows you to ask questions about your data and interact with AI-generated responses. See [Ask natural language queries with Sigma Assistant](/docs/ask-natural-language-queries-with-assistant). * **Sigma Assistant in the workbook** lets you ask natural language questions about workbook data when viewing a workbook, and build or edit dashboards and apps using natural language when editing a workbook draft. See [Use Sigma Assistant to explore and analyze workbook data](/docs/sigma-assistant-in-the-workbook) and [Use Sigma Assistant to build dashboards and apps](/docs/use-ai-to-build-dashboards-and-apps). * **Sigma agents** let you build agentic solutions in Sigma workbooks capable of analyzing data, calling warehouse agents, triggering action sequences, and more. See [About Sigma agents](/docs/sigma-agents). * **Warehouse agents** let you interact directly with a Snowflake Cortex Agent or a Databricks Genie Agent from Sigma Assistant or Sigma agents. See [Use warehouse agents with Sigma](/docs/use-warehouse-agents-sigma). * The **formula assistant** uses AI to write new formulas, correct formula errors, and explain existing formulas. See [Use AI with formulas](/docs/use-ai-with-formulas). * **Explain this chart** uses AI to instantly generate a description of any chart. See [Explain charts with AI](/docs/explain-visualizations-with-ai). > **Note** > > The use of AI features is subject to the following [disclaimer](/docs/notice-for-enabling-ai-enabled-features-in-sigma). To use AI-enabled features in Sigma, do the following: 1. [Set up an AI provider](#set-up-an-ai-provider) 2. [Choose which agents are available from the home page](#choose-which-agents-are-available-from-the-home-page) 3. If Sigma Assistant is enabled, [decide which data sources to use with Assistant](#choose-data-sources-for-sigma-assistant) 4. [Manage access to AI features](#manage-access-to-ai-features) 5. (Optional) [Configure chat history and AI usage tracking](#configure-chat-history-and-ai-usage-tracking) 6. (Optional) [Review data access for AI features](#review-data-access-for-ai-features) ## User requirements You must be assigned the **Admin** [account type](/docs/create-and-manage-account-types). ## Set up an AI provider When you set up an AI provider in Sigma, you connect Sigma to either an external AI service or a data platform with access to specific AI models that Sigma can use: * To connect to an AI model hosted by your data platform, see [Configure a warehouse-hosted model as AI provider](/docs/configure-warehouse-ai-model-integration). When you choose the option to configure a warehouse-hosted model, your data is managed fully in your data platform. * To connect to an externally hosted model, see [Configure an external AI provider](/docs/manage-external-ai-integrations). Sigma uses a reasoning model for AI-powered features, and an embeddings model to create embeddings of your documents for [semantic search](/docs/search-in-sigma). The models that Sigma uses for AI-powered features depend on your AI provider. You cannot choose which model Sigma uses. To review the models that Sigma uses for each provider, including deprecated and planned models, see [Supported AI models](/docs/supported-ai-models). > **Info** > > Warehouse agents do not require an AI provider and instead use the AI models configured for the agents in your data platform. ## Choose which agents are available from the home page By default, users with permissions can chat with Sigma Assistant and any Snowflake Cortex Agents or Databricks Genie Agents on Sigma connections that they can access. You can choose which agents are available from the home page in the **Agents available from the home page** section of the **General AI** tab: * **Sigma Assistant**: Turn on to make Sigma Assistant available from the home page. * **Warehouse agents**: Turn on to make Snowflake Cortex Agents and Databricks Genie Agents available to chat with on the home page. See [Use warehouse agents with Sigma](/docs/use-warehouse-agents-sigma). To turn specific agents on or off: 1. Go to **Administration > AI settings**: 1. In the Sigma header, click your user avatar to open the user menu. 2. Select **Administration** to open the Administration portal. 3. In the side panel, select **AI settings**. 2. In the **Agents available from the home page** section, turn on or off the **Sigma Assistant** or **Warehouse agents** toggle. If both toggles are off, users in your organization cannot chat with Assistant or warehouse agents from the home page. ## Manage access to AI features Control who can access different AI features by enabling feature permissions on different account types assigned to users: | AI feature | Account type permission that enables use | | :----------------- | :--------------------------------------- | | Sigma Assistant 1 | Use Assistant | | Sigma agents 2 | Manage agents | | Formula assistant | Use AI with formulas | | Explain this chart | Explain charts with AI | 1 Depending on what you want to do with Sigma Assistant, the ability to use it can require additional account type permissions and document access. For example, to use Assistant to build a dashboard, a user must be able to edit a workbook draft, which requires the **Create, edit, and publish workbooks** permission and **Can edit** workbook access. 2 You can only restrict access to Sigma agents by managing access to the workbooks that contain agents. You can restrict access to who can create Sigma agents. For more details, including which license tiers have access to these permissions, see [License and account type overview](/docs/account-type-and-license-overview). ## Choose data sources for Sigma Assistant You can configure Sigma Assistant to use only specific data sources or any data sources available to users by default. Users can always manually choose a source for Assistant to use from the sources that they have access to. #### [All sources](#select-all-data-sources-for-sigma-assistant) Assistant uses all available data sources. When a user asks a question, Assistant selects from any data source that the user has access to. Recommended when your data sources are governed through data and document access, and you want Assistant to use any data source that a user can already query. #### [Specific sources](#select-data-sources-for-sigma-assistant) Assistant uses only the data sources that you configure. When a user asks a question, Assistant evaluates the configured sources and selects a data source. Recommended when you want Assistant to answer from a curated set of sources by default, such as endorsed data models with descriptions and metrics. With either option, Assistant respects each user's existing access to data. See [Review data access for AI features](#review-data-access-for-ai-features). > **Info** > > These data source settings only apply to Sigma Assistant when used from Sigma Home. When you use Sigma Assistant in a workbook, whether to [explore and analyze workbook data](/docs/sigma-assistant-in-the-workbook) or to [build dashboards and apps](/docs/use-ai-to-build-dashboards-and-apps), Assistant can access any data source that the user can access. ### Select all data sources for Sigma Assistant You can choose which data sources Sigma Assistant uses to answer questions. By default, Sigma Assistant has access to all data sources that a user has access to. Unless you configure specific data sources, Sigma automatically indexes up to 2,000 of your organization's most-used data sources for Assistant to search. If you previously [selected specific data sources](#select-data-sources-for-sigma-assistant) and want to switch back to using all sources, select **All sources**. Sigma Assistant immediately searches all available data sources. Your previously selected sources are retained but no longer determine what Assistant searches, and the **Selected sources** section is hidden while **All sources** is selected. 1. Go to **Administration > AI settings**: 1. In the Sigma header, click your user avatar to open the user menu. 2. Select **Administration** to open the Administration portal. 3. In the side panel, select **AI settings**. 2. In the **Agents available from the home page** section, make sure the **Sigma Assistant** toggle is on. 3. Under **Sigma Assistant**, select **All sources**. For more details about how Assistant chooses sources from within all sources, see [How Sigma Assistant selects data sources when answering user questions](#how-sigma-assistant-selects-data-sources-when-answering-user-questions). ### Select data sources for Sigma Assistant You can limit Sigma Assistant to use only sources that you specify. Users can choose specific data sources that they have access to when asking natural language queries, but if no source is specified by the user, Assistant only uses the configured sources. Select data models to take advantage of semantic modeling, relationships, and metrics. You can also select tables from connected data platforms. To select specific data sources for Assistant: 1. Go to **Administration > AI settings**: 1. In the Sigma header, click your user avatar to open the user menu. 2. Select **Administration** to open the Administration portal. 3. In the side panel, select **AI settings**. 2. In the **Agents available from the home page** section, make sure the **Sigma Assistant** toggle is on. 3. Under **Sigma Assistant**, select **Specific sources**. 4. Select **Add source**. 5. In the **Add sources** modal, search for and select one or more data models or tables. > **Info** > > When you select a data model as a source, only the published version of the data model is selected. You cannot select the tagged version of a data model. 6. Click **Add** to configure the selected sources for Assistant. The selected data sources are automatically synced and added to the semantic search index used by Assistant to select data sources. > **Info** > > If you change data sources or metadata in your data platform after you select those data sources, updates are available to Assistant within 2 hours. If you want the updates to be available immediately, return to this page and select **Sync all data sources now** to update the representation of your data sources in the semantic search index. ## Configure chat history and AI usage tracking In the **Chat history and usage data** section of the **General AI** tab, choose what Sigma keeps from AI conversations and usage, and where it is stored: * **Store chat history**: Control whether users can view, resume, and manage their recent chats, and where chats are stored. See [Configure chat history](/docs/configure-chat-history). * **Track AI usage**: Set up the table that stores AI usage data for the [AI usage](/docs/ai-usage) dashboard. See [Configure the AI usage dashboard](/docs/configure-ai-usage-dashboard). ## Review data access for AI features AI features such as Sigma Assistant respect the access granted to users for data sources. Each user can see and query only the data sources that they have access to. If you want to restrict what Assistant uses as a data source for answers for a specific user or team, restrict user or team access to the data source at the data source, schema, or table level. To manage user access to data, review the access set on a specific connection or data model: * [Manage access to data and connections](/docs/manage-data-permissions). * [Manage document access](/docs/folder-and-document-permissions) for data models. * Within a data model, you can also control visibility of a source: [Enable or disable an element as a data source](/docs/create-and-manage-data-models#enable-or-disable-an-element-as-a-data-source). ### How Sigma Assistant selects data sources when answering user questions If a user asks a question of Sigma Assistant and a source is not specified, Assistant selects a source based on the following factors: * **Whether sources are configured**: If Assistant is accessed from Sigma Home and Assistant is limited to only selected sources, Assistant only chooses sources from the list of configured sources. * **The user's access to the data source**: Assistant respects the access granted to the user asking the question and does not expose data they are not authorized to use. * **The relevance of the data to the question**: Assistant uses any metadata that exists to describe data sources and data columns, such as data model descriptions or column descriptions. If no other metadata has been defined, Assistant can infer relevancy from column names. * **The known validity of the data**: For example, if a data model has an "endorsed" badge applied, Assistant is more likely to use that data source. Similarly, if someone in your organization has created and shared metrics and data models, Assistant is more likely to select one of those when answering rather than using a table directly from your connected data platform. * **The frequency of usage of the data source**: Assistant is more likely to reference frequently used data sources in its answers. Adding metadata to your data sources for Assistant is not required, but it is recommended. See [Data modeling best practices](/docs/data-modeling-best-practices). Assistant uses any available metadata, such as certification badges, source descriptions, table descriptions, and column descriptions, to determine relevancy to a user's question, but can also determine relevancy using column names alone. To add metadata to data sources, see the following: * Add badges and descriptions to connection tables. See [Annotate tables with metadata](/docs/manage-data-catalog#annotate-tables-with-metadata). * Add badges and descriptions to data models. See [Edit a data model description](/docs/create-and-manage-data-models#edit-a-data-model-description) and [View and manage document badges](/docs/view-and-manage-document-badges). * Add AI context to data models to provide data-model-specific instructions. See [Manage AI context for a data model](/docs/manage-ai-context-for-data-models). ## Related resources * [Ask natural language queries with Sigma Assistant](/docs/ask-natural-language-queries-with-assistant) * [About Sigma agents](/docs/sigma-agents) * [Use AI with formulas](/docs/use-ai-with-formulas) * [Explain charts with AI](/docs/explain-visualizations-with-ai) * [Configure an external AI provider](/docs/manage-external-ai-integrations) * [Configure a warehouse-hosted model as AI provider](/docs/configure-warehouse-ai-model-integration) * [Supported AI models](/docs/supported-ai-models) * [Notice for enabling AI-enabled features in Sigma](/docs/notice-for-enabling-ai-enabled-features-in-sigma) > Official documentation and guidance for using Sigma to build AI apps, dashboards, and agents on governed warehouse data. ## Docs - [Supported AI models](https://help.sigmacomputing.com/docs/supported-ai-models.md): Reference the reasoning and embeddings models that Sigma uses for each supported AI provider, including deprecated and planned models. - [Configure a warehouse-hosted model as AI provider](https://help.sigmacomputing.com/docs/configure-warehouse-ai-model-integration.md): Use warehouse-hosted AI models from your connected data platform as the AI provider for Sigma organization features. - [Configure an external AI provider](https://help.sigmacomputing.com/docs/manage-external-ai-integrations.md): Set up external AI providers like OpenAI, Anthropic, Gemini, or Amazon Bedrock to power Sigma organization AI features. - [Configure the AI usage dashboard](https://help.sigmacomputing.com/docs/configure-ai-usage-dashboard.md): Monitor Sigma AI token usage and interactions across Assistant, agents, and other AI-powered features with the AI usage dashboard. - [Notice for enabling AI-enabled features in Sigma](https://help.sigmacomputing.com/docs/notice-for-enabling-ai-enabled-features-in-sigma.md): Required information disclaimer for enabling AI features in Sigma Services, including settings, risks, and authorization guidance. - [Configure token usage limits for AI columns (Beta)](https://help.sigmacomputing.com/docs/configure-ai-column-token-limit.md): Set monthly token limits in Sigma to control AI column usage costs and manage organization-wide AI spending for AI columns. - [Add MCP connectors to Sigma](https://help.sigmacomputing.com/docs/configure-mcp-connectors.md): Integrate MCP servers with Sigma agents to extend context, fetch ad hoc data, and trigger actions in third-party tools. - [Use warehouse agents with Sigma](https://help.sigmacomputing.com/docs/use-warehouse-agents-sigma.md): Use Snowflake Cortex Agents and Databricks Genie Agents in Sigma Assistant and Sigma agents for direct warehouse AI interaction. - [Configure chat history](https://help.sigmacomputing.com/docs/configure-chat-history.md): Configure chat history for your organization to control whether or not recent chats with Sigma Assistant and agents are stored and made available for users to access and manage. - [Manage Sigma agents for your organization](https://help.sigmacomputing.com/docs/manage-agents-for-your-organization.md): Review usage and monitor agents with observability across your organization.