Ask natural language queries with Sigma Assistant

Sigma Assistant is a natural language query (NLQ) interface that allows you to ask questions about your data and interact with AI-generated responses. Extract factual information from your data, ask questions that generate charts that you can explore in a workbook, or have a conversation with Sigma Assistant to iterate on a specific data analysis task.

🚩

The use of AI features is subject to the following disclaimer.

Sigma Assistant can answer questions about any data source that you have access to. By default, Sigma Assistant answers questions using data sources configured by your admin, but you can select another data source that fits your analysis before asking your question. Sigma Assistant also supports conversations, so you can ask follow-up questions about the data or the analysis steps performed by Sigma Assistant.

System and user requirements

The ability to use Sigma Assistant requires the following:

Limitations

  • You cannot ask questions of tagged versions of data models in Sigma Assistant. If a data model is configured or selected by a user, only the published version of that data model is used to answer questions, and only users who have access to the published version to the data model can get answers from Sigma Assistant that reference that data model.
  • Sigma Assistant can't perform ad hoc joins to combine data sources, but if a relationship is defined in a Snowflake semantic view or a data model between two data sources, Sigma Assistant can use the relationship to join data sources to answer a question.

Ask natural language queries with Sigma Assistant

To use Sigma Assistant to ask questions about your data:

  1. From Sigma Home, click Assistant in the left navigation.

  2. In the Ask a question about your data box, enter your question.

    Sigma Assistant interprets your question and searches the configured data sources and selects what it determines to be the best source to answer your question. Assistant uses semantic relevance, data source metadata, and data source usage to select the best data source from the configured data sources you have access to. You can optionally select a specific data source.

  3. Sigma Assistant provides a response.

    A screenshot of an Assistant response to the question What are our ten most profitable stores in the East region, with the result as a bar chart of the top ten stores by profit, with Argyle Store in first by about 1 million dollars.

    If you want to review the step-by-step decision logic it used to determine the answer, select Analysis breakdown and review the steps that Sigma Assistant took.

    A screenshot of an Assistant response to the question What are our ten most profitable stores in the East region, with analysis breakdown expanded and showing steps like filtered by store region and calculating profit as revenue minus cost times quantity grouped by store name, then sorted by total profit.
  4. You can continue to ask follow-up questions to refine your analysis or understanding of the data source. For example, you might follow up and ask "What about the West region?" to discover the top 10 most profitable stores in the West region.

    Part of the East region answer visible while the text What about the West region is visible, with an answer from Assistant with a nearly identical bar chart as the East region but for the West region. Church store is the top performing store in the West region.
  5. If you have an account type with the Create, edit, and publish workbooks permission enabled, you can continue analysis in a workbook. Hover over a chart or table and click (Explore) to open an exploration in a new tab with the selected output and any underlying data tables.

    For the bar chart with the top performing stores in the West region, hovering over an open icon with hover text and aria label Explore.
  6. If you want to start a new conversation without leaving Sigma Assistant, click () Reset.

Search and explore data sources

Sigma Assistant has access to configured data sources by default. If you know exactly which data source you want to ask questions of, you can select it before asking questions with Sigma Assistant:

  1. From Sigma Home, click Sigma Assistant in the left navigation.

  2. Select +, then search for any data source that you have access to in your organization:

    • Table in your data platform
    • Snowflake semantic view
    • Data model
    • Dataset (deprecated)

    Sigma returns all matching tables, data models, Snowflake semantic views, and datasets that you have access to use, each with an indicator of whether it is configured for Sigma Assistant.

    📘

    Your admin configures sources to be used by Sigma Assistant by default.

    All data access grants that apply elsewhere in Sigma also apply in Sigma Assistant. For example, if row-level security or column-level security is applied to a data source, Sigma Assistant only works with data that you have access to. For a data model, you must have access to the published version.