Skip to main content
Monitor agent performance and usage across AI for Work.

​
Overview

Analytics provides a history of all administrative tasks through two views: the Dashboard view and the Data view. Switch between them using the toggle at the top right of the Analytics page. The views display key performance metrics, trends, and reports, enabling you to gauge real-time usage and performance. dashboard

​
Dashboard View

The Dashboard view provides graphical reports on usage, performance, and feedback. At the top, you can see the total queries, total tokens, and total active users for the day. dashboard top view The following reports are available: All graphical reports support Day, Week, and Month views with left-right navigation for detailed metrics at each time point. Time averaging: 30-minute average (daily), 6-hour average (weekly), daily average (monthly).

​
Tokens Used

Displays token usage trends across models. token used token used detail

​
Tokens Per Agent

Displays token consumption broken down by agent. tokens per agent tokens per agent detail

​
Queries Per Agent

Displays query volume by agent, categorized by agent type: AI for Service, GPT, Data, Search, and Workflow. queries per agent queries per agent detail

​
Top Agents

Displays agents ranked by query volume in descending order. top agents

​
Top Users

Displays the top 10 users by query count. top users

​
Users

Displays unique users interacting with the system, comparing web vs. native platforms. users users detail

​
Average Response Time

Displays the average response time of the service over time. average response time average response time detail

​
Errors

Displays the number of queries that resulted in errors over time. errors errors detail

​
Feedback

Displays end-user feedback on responses. feedback

​
Trace Logs

Trace logs list individual query records. Each record corresponds to one user utterance and captures how the platform processed it from request to response. A trace log shows you:
  • Who asked and where — the user, the channel, the thread, and whether the query used prior context.
  • What was asked — the user utterance and the key query points extracted from it.
  • How the platform responded — the agent type, response status, and response time.
  • What it cost — the LLM model used and the request, response, and total token counts.
  • How the user rated it — the feedback type and any feedback comments.
  • What happened at each step — the prompt sent to the model and the model’s response for every background step, through the Execution Analyzer.
data view Click More on any record to open a detailed view. At the top of the detail panel, you can see the Response Status, Response Time, and Feedback Type for that record.

​
Record Details

Request Information Query Details LLM Usage Execution Analyzer execution analyzer Expand the Execution Analyzer to examine each background step. For each step, you can:
  • View the exact prompt sent to the model
  • Review the model’s response
  • Debug individual steps to identify issues

​
Trace Log API

You can also retrieve trace log records programmatically through the Trace Log API. Each record the API returns includes response time, token consumption, the models used at each LLM step, the identified intent, and user feedback. Use the API to pull trace log data into your own reporting tools, data warehouses, or dashboards. For the endpoint, parameters, and response reference, see Trace Log API.

​
Feedback Management

Feedback Management gives administrators visibility into user feedback submitted across the platform, with configurable email notifications and scoped access by role. Navigation: Admin Console → Usage → Feedback

​
Accessing the Feedback Page

Access to the Feedback page is role-based:

​
Feedback Detail View

Click any feedback entry to open its detail view. The view displays the associated trace log and the submitted feedback — type, category, and any additional comments.

​
Notify Feedback

Click Notify Feedback on the Feedback page to configure email notifications. Select which feedback types should trigger notifications and add recipients. Recipients can be any valid email address or distribution list and do not need to belong to the account. Notification scope follows the level at which it is configured — account-level covers all workspaces and agents, workspace-level covers all agents in that workspace, and agent-level covers only that specific agent. Email notifications include: user email, query, agent name, workspace, feedback type, feedback category, and additional comments (if provided).