Assistant usage dashboard (Removed)

As of September 15, 2026, the Assistant usage dashboard is removed. Use the AI usage dashboard instead. If you set up the Assistant usage data before it was removed, you can migrate that historical data to the AI usage dashboard. See Migrate Assistant usage data to AI usage.

The Assistant usage dashboard displays usage data about Sigma Assistant, including questions asked, users using Assistant, sources accessed by Assistant, and performance metrics like response time, tokens consumed, and number of LLM calls.

For example, if you want to evaluate changes that you make to the AI context for data models configured for Sigma Assistant or the configured AI provider, use the Assistant usage dashboard to review the resulting effects on usage and token consumption.

The dashboard contains the following tabs:

Tab name	Description
Questions	Details about questions asked of Sigma Assistant.
Users	Details about users of Sigma Assistant.
Sources	Details about sources used to answer questions asked of Sigma Assistant.
Performance	Details about total response time for Sigma Assistant, for the LLM associated with the AI provider, and tokens consumed.

Assistant usage table in connection browser

If you are granted access to the relevant schema, you can still explore any historical Assistant usage data in the relevant table in the connection browser.

Assistant usage was stored in a table called ASK_<ORGANIZATION_NAME> in the location you configured. To migrate this historical data to the AI usage table, see Migrate Assistant usage data to AI usage.

Column name	Description
Timestamp	Time when the question was asked.
User Question	Natural language question asked.
User Id	Unique user identifier for the user in Sigma.
Data Classification	LLM classification of the data needed to answer the question.
Selected Source	Source used to answer the question.
Question Id	Unique ID for the question.
User Name	Name of the user who asked the question.
Agent	What agent was used to answer the question: source selection, docs, or analysis.
Improvement	N/A
Warehouse Runtime Ms	How long the query ran to return the data for the question, in milliseconds.
Llm Runtime Ms	How long the LLM ran to process the question and response, in milliseconds.
Teams	Sigma teams that the user who asked the question is a member of.
Model	LLM model used. Should match the supported model for the configured AI provider.
Error	If present, the error message.
Result	Description of the result or result type. For example, `chart`.
Tokens	Total tokens consumed for the input (question) and output (response).
Call Count	Number of LLM calls required to answer the question.