This article is auto-synced from its in-app version in Tai.
Analytics shows how your agents are being used — token consumption, request counts, cost, and performance — across a configurable time window.
When you'd use this
Use Analytics to understand which agents are running most, how much they cost, and whether requests are succeeding. For example: review last week's token usage by agent to see where most activity is coming from, or check the events table to investigate a failed session.
Steps
View usage charts
In the Workbench sidebar, click Analytics (under the Monitoring section).
Set the date range using the start and end date pickers. The default is the last 30 days.
Choose a granularity — hourly, daily, weekly, or monthly — to control how the time-series chart buckets data.
The summary cards at the top show totals for the selected period: tokens in, tokens out, estimated cost, and request count.
The charts below break usage down by model, by agent, and by tool (skills and connectors).
Filter by agent
On the Analytics page, use the Agent multi-select to show data for specific agents only.
The charts and summary cards update immediately.
The events table below the charts also filters to the selected agents.
Inspect individual events
Scroll to the events table at the bottom of the Analytics page.
Each row is one agent invocation — timestamp, agent, session, operation, model, token counts, cost, and processing time.
Click the Timestamp or Total Out column headers to sort ascending or descending.
Tips and limits
Token and cost figures are estimates based on LLM provider data. Not all providers report cost in real time.
The events table paginates — use Load more to see older entries.
Sorting the events table resets the pagination cursor to page one.
Changing the date range or granularity updates the charts but not the events table (the table uses its own filter set).
Related