> For the complete documentation index, see [llms.txt](https://docs.poweromni.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.poweromni.ai/en/administration-and-configuration/monitoring.md).

# Monitoring

The **Monitoring** section provides a real-time overview of **Token Usage Metrics** within your organization. It is the primary tool for administrators to track consumption, audit activity, and manage AI-related costs.

<figure><img src="/files/HCSe7tIKme2WsilciLUl" alt=""><figcaption></figcaption></figure>

You can adjust the analysis period (**Last 24h, Last 7 days, Last 30 days, or Earlier**) in the upper-right corner.

#### Overview

The first row of the dashboard displays the financial and volume summary:

* **Total Questions:** The total number of interactions processed by the AI during the selected period.
* **Average Cost / Question (USD):** The average token cost required to generate a response. Helps assess the efficiency of Agent usage.
* **Total Cost (USD):** The total token consumption cost (billed to your Azure account) during the selected period.

### Detailed Usage Metrics

Below the overview, the metrics are segmented to enable granular consumption auditing, ensuring full transparency and governance:

<table><thead><tr><th width="210">Metrics Table</th><th width="301">Purpose</th><th>Key Fields</th></tr></thead><tbody><tr><td>Usage by Agent</td><td>Shows which Agents (AI assistants) are being used the most. Essential for identifying costs by specific area or function.</td><td><p></p><ul><li>Agent</li><li>Questions</li><li>Cost per Question</li><li>Total Amount (USD)</li></ul></td></tr><tr><td>User by Number of Questions</td><td>Identifies the users generating the highest volume of interactions with the AI. Helps monitor adoption and identify users who may need additional training.</td><td><p></p><ul><li>User</li><li>Total Questions</li><li>Total Amount (USD)</li></ul></td></tr><tr><td>Usage by Model</td><td>Provides a breakdown of usage across the different registered AI Models. Enables administrators to make cost-related decisions by prioritizing more efficient models.</td><td><p></p><ul><li>Model</li><li>Questions</li><li>Total Amount (USD)</li></ul></td></tr><tr><td>Agent by User</td><td>Displays cross-referenced data, showing which user is using which Agent and the specific cost of that interaction.</td><td><p></p><ul><li>Agent</li><li>User</li><li>Questions</li><li>Cost per Question</li></ul></td></tr></tbody></table>

{% hint style="info" %}

### Governance and Cost

The Monitoring dashboard is your governance tool. By auditing **Cost per Agent** and **Usage by Model**, you can adjust Agent configurations and apply usage limits to control total token spending.
{% endhint %}