# Observability

Once a Coworker is running, three tabs give live visibility into its behaviour and cost. They mirror the views in the [Command Center](../11_command_center/index.html), scoped to this Coworker.

[![Coworker Analytics tab — cost, tokens, conversations, latency, and agent runs](../images/coworker-analytics-v2.png)](../images/coworker-analytics-v2.png)

| Tab | What it shows |
| --- | --- |
| **Analytics** | A live dashboard: Total Cost, Total Tokens, Total Conversations, and Average Latency, plus input and output token counts. An **Agent Runs** table links to the traces for each run, and cost and token usage are broken down by user and by model. Filter by email, model, and time range; refresh, auto-refresh, or export to PDF. |
| **Traces** | A paginated trace log. Open a trace to see the execution flow as a timeline of steps (spans), each with its input, output, metadata, duration, tokens, and cost. Skill invocations appear here as spans. Use **Add to Dataset** to capture a trace for [evaluation](evaluating.html). |
| **Conversations** | A list of sessions with their status and duration. Use the **Search by Conversation ID** box to find a session in the current page of results. Open one to see the chat history, any KPI results, the session metadata, and a translate option. |

The Analytics dashboard is where per-Coworker **cost tracking** lives — use it to monitor spend by user and model before and after a wider rollout.

## Feedback from Users (Microsoft Teams)

On Microsoft Teams, when a user reacts to one of the Coworker’s messages — for example with a thumbs-up — the Coworker notices and uses it to adjust the tone of its next reply in the same conversation. The reaction shapes that one reply. This requires **Reflection** to be enabled on the [Memory](memory.html) tab (it is on by default).

> **Note**
>
> **Coming soon.** How this feedback is surfaced in the interface is being finalised. Today the reaction influences the next reply; it is not yet shown as a separate score.