AI usage dashboard
The AI usage dashboard displays AI token usage across the entire organization for all relevant product surfaces that use AI, such as Sigma agents and Sigma Assistant.
For example, if you want to evaluate changes that you make to agent instructions or configured AI provider, use the AI usage dashboard to review the resulting effects on usage and token consumption.
User and system requirements
- You must be assigned the Admin account type.
- The dashboard must be configured. See Configure AI usage dashboards.
Review AI usage dashboard
The AI usage dashboard includes the following tabs:
| Tab name | Description |
|---|---|
| Overview | Details about AI token usage for the organization, such as usage by day by product surface, token usage per day, and total input and output tokens by product surface. Filter by user, product surface, sentiment of the conversation, or date. |
| Agents | Details about agent usage for the organization, such as token usage per agent, agent popularity, token consumption per day, and requests per day. Filter by user, agent name, conversation sentiment, or date. |
AI usage table in connection browser
If you are granted access to the relevant schema, you can also explore the AI usage data in the relevant table in the connection browser.
AI usage is stored in a table called AI_USAGE_<ORGANIZATION_NAME> in the configured location.
| Column name | Description |
|---|---|
| Trace Created At Utc | Time when the AI feature was used. |
| Trace Id | Unique identifier for each turn in a conversation, per user. For example, if a user asks a question and sees a response, that is one turn and is grouped with one Trace ID. |
| Span Id | Unique identifier for each call made by the LLM. For example, an API call, a tool call, or an MCP call each result in a different Span ID as part of a chat session. |
| Parent Id | Unique identifier of the Span Id that caused the activity. |
| Span Type | Type of usage. generation indicates a response, span indicates a call made by an LLM, tool indicates a tool call performed by an agent, such as an action or MCP server, or score to indicate user feedback about an agent response. |
| Trace Name | Type of usage associated with the Span Type. For example, chat for a Sigma agent interaction in a chat associated with a Span Type of generation, or database_execute_query for a tool call performed by a Sigma agent for a Span Type of tool. |
| Agent Name | If a Sigma agent, the name of the Sigma agent, otherwise null. |
| Agent Id | Unique identifier of the Sigma agent. |
| User Name | Full name of the user. |
| Session Id | Unique identifier for associated conversations or interactions with an AI feature. For example, one chat session with a Sigma agent. |
| Ai Provider | Type of AI provider configured for the organization. |
| Model | LLM model used. Should match the supported model for the configured AI provider. |
| Tokens Input | Total tokens consumed for the input (question). |
| Tokens Output | Total tokens consumed for the output (response). |
| Tags | Not yet used. Array of strings for filtering. |
| Tool Calls | Details about tool calls used for generation. If Span Type is generation, JSON array of results from a previous tool call, otherwise null. |
| Input | Input for the LLM. If Span Type is tool, JSON array of tool call details. For example, for a Trace Name of database_execute_query, includes the SQL statement run for the tool call and the title shown to the user in the chat (if applicable) during the tool call. If Span Type is custom-agent, includes a string of the message sent to the agent. If Span Type is generation, includes all details sent to the LLM. |
| Output | Output from the LLM. If Span Type is tool, JSON object with the name, output, role, and toolCallId of the tool call performed. If Span Type is custom-agent, includes a string of the message sent by the agent. If Span Type is generation, includes a JSON object with the organizationId, sigmaRequestId, and system. |
| Metadata | JSON object with metadata about the AI usage. For usage associated with a Sigma agent, includes metadata like the agentId, agentName, and agentToolConfig. For usage associated with Sigma Assistant, includes a JSON object with the organizationId, sigmaRequestId, and system. |
| Trace Created at Utc | Timestamp when the interaction was started, in UTC. |
Updated 29 minutes ago
Related resources