> For the complete documentation index, see [llms.txt](https://comunity.gitbook.io/learning.comunitynexus/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://comunity.gitbook.io/learning.comunitynexus/26.2/toolkit-guides/intelligence/monitor-agent-activity.md).

# Monitor agent activity

**Overview** is the first screen in the Intelligence menu and the one place that shows the whole picture at once: what the project has configured, and what that configuration has actually been doing.

It is found under **Intelligence (Preview)**, then **Overview**. The screen is titled **Intelligence Overview**, followed by the provider scope it is reporting on, for example **All Providers**.

## Before you start

A provider. Until one exists, Overview reports that none are configured and the graph has nothing to draw. See [Set up a provider and deploy a model](/learning.comunitynexus/26.2/toolkit-guides/intelligence/set-up-a-provider-and-deploy-a-model.md).

## The activity window

Overview is a configuration graph with live activity overlaid on it, and the **Activity window** selector sets the period that activity is drawn from. The default is the last 24 hours, and the metrics that are period-bound say so in their labels.

## What the metrics report

| Metric                     | Reports                                                                |
| -------------------------- | ---------------------------------------------------------------------- |
| **Overall Service Health** | The health of the underlying provider resources, across all providers. |
| **Used Models**            | Models actually in use, as distinct from models available.             |
| **Tools**                  | Tools registered.                                                      |
| **Agents**                 | Agents defined.                                                        |
| **Trigger Instances**      | Triggers in place.                                                     |
| **Sessions**               | Sessions over the activity window.                                     |
| **Tool Runs**              | Tool calls over the activity window.                                   |

Where health cannot be established for a provider, Overall Service Health reads **Unknown** and the screen notes that service health could not be determined for one or more providers. See [Set up a provider and deploy a model](/learning.comunitynexus/26.2/toolkit-guides/intelligence/set-up-a-provider-and-deploy-a-model.md) for what that state means on an individual provider.

## Reading the graph

The graph draws the relationships between the parts, and the link colour tells you which relationship you are looking at:

| Link             | Colour |
| ---------------- | ------ |
| Model to agent   | Blue   |
| Tool to agent    | Green  |
| Agent to trigger | Purple |

That is the shape of the model itself: an agent draws on a model and on tools, and a trigger is what runs the agent.

Activity is layered on top. Brighter and thicker lines, and the badges on them, indicate higher activity, and moving dots show the direction of live flow on active links. Hovering a node or a line focuses the flow connected to it, which is the quickest way to answer which tools a particular agent is actually calling.

## Keeping the view current

Traffic refreshes on its own every five seconds, and **Refresh Activity** forces an immediate update. **Zoom In**, **Zoom Out** and **Reset View** control the graph itself and do not change what is being measured.

## Where to go next

* [Set up a provider and deploy a model](/learning.comunitynexus/26.2/toolkit-guides/intelligence/set-up-a-provider-and-deploy-a-model.md): provider health and the model sync this screen reports on
* [Create an agent](/learning.comunitynexus/26.2/toolkit-guides/intelligence/create-an-agent.md): each agent's own run history, in more detail than the graph gives