> For the complete documentation index, see [llms.txt](https://atlas.anywhere.now/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://atlas.anywhere.now/use/monitor-and-report/dialogue-workspace/agents.md).
# Monitor agents in Dialogue Workspace
Monitor agent availability and current activity in Dialogue Workspace.
The **Agents** page provides a real-time view of agent availability and current activity. Use it to confirm staffing levels, identify who is available, and see which skills agents can handle.
Use the **Contact centers** selector to switch between one contact center and **All** contact centers.
## Agent presence metrics
The summary widget shows:
* **Total agents**: Number of agents included in the current view.
* Distribution of agents by presence state, such as **Available**, **Busy**, **Away**, **Offline**, and **Unknown**.
## Agent table
Use the **Filter** field above the table to search for an agent by name. Select **Customize columns** to show or hide columns based on your operational needs.
| Column | What it shows |
| ------------------ | ----------------------------------------------------------------------------------------------- |
| **Agent** | Agent name. |
| **Availability** | Presence, such as Available, Busy, Away, Offline, or Unknown. |
| **Activity** | What the agent is doing, such as Available, Idle, In a call, In a meeting, Offline, or Unknown. |
| **Skills** | Skills the agent can handle, shown as tags or pills. |
| **Contact center** | Contact centers associated with the agent, shown as tags or pills. |
## Agent details panel
To view more details for an agent, select the agent row in the table. A details panel opens on the right side of the screen.
To close the panel, select the **X** in the top-right corner of the panel.
| Area | What it shows |
| ----------------------------- | -------------------------------------------------------------------------------------------------------------------------- |
| **Agent header** | Agent name and current availability status. |
| **Active call** | When the agent is in an active call, call details such as customer identifier and current state. |
| **Monitor** | Shows dialogue details for the selected active conversation. Does not join call audio or start a WebAgent supervisor mode. |
| **Contact centers** | Contact centers associated with the agent. |
| **Skills per contact center** | Skills relevant for that agent in that contact center. |
See [Monitor details without joining a call](/use/monitor-and-report/dialogue-workspace.md#monitor-details-without-joining-a-call) for the workflow and the separate WebAgent call-supervision path.
## Use the contact center list
* Select the expand/collapse control next to a contact center to show or hide its skills.
* Use the contact center toggle to focus the panel on specific contact centers for that agent.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://atlas.anywhere.now/use/monitor-and-report/dialogue-workspace/agents.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
