> 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/dialogues.md).

# Monitor dialogues in Dialogue Workspace

Monitor active and recent dialogues in Dialogue Workspace.

The **Dialogues** page lists live and recently handled dialogues so supervisors can monitor what is happening now, including duration, state, assigned agent, and contact center context.

Use the **Contact centers** selector to switch between one contact center and **All** contact centers.

![Dialogue Workspace dialogues](https://67037690-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkDTnqL8OqnJFQgFg9eQ6%2Fuploads%2Fgit-blob-b96ac23ec52815cd0532608c87027bd0e5f5772d%2Fdialogue-workspace-dialogues.png?alt=media)

## Summary card

**Longest talk time** highlights the longest active talk duration in the current view, including the customer identifier associated with that dialogue.

## Dialogue table

Use the **Filter** field above the table to search for a dialogue, for example by customer, agent, or another visible field.

Select **Customize columns** to show or hide columns.

| Column             | What it shows                                           |
| ------------------ | ------------------------------------------------------- |
| **Channel**        | Channel icon for the dialogue, for example voice.       |
| **Start time**     | Timestamp when the dialogue started.                    |
| **Customer**       | Customer identifier, for example a phone number.        |
| **Agent**          | Agent handling the dialogue, if assigned or connected.  |
| **Type**           | Direction of the dialogue, such as Inbound or Outbound. |
| **State**          | Current state of the dialogue.                          |
| **Duration**       | Elapsed time of the complete dialogue.                  |
| **Skill**          | Skill associated with the dialogue, when available.     |
| **Contact center** | Contact center where the dialogue is handled.           |

## Dialogue states

Dialogue Workspace can show states such as:

* **Started**
* **In IVR**
* **In queue**
* **Connecting**
* **Connected**
* **Transferring**
* **In quality monitor**
* **Disconnected**

## Dialogue details panel

To view more information for a specific dialogue, select the dialogue 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.

<figure><img src="https://67037690-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkDTnqL8OqnJFQgFg9eQ6%2Fuploads%2Fgit-blob-c8e35d4f1c8c9858cc594aab2da5952a5f17186e%2Fdialogue-workspace-dialogue-details-panel.png?alt=media" alt="Dialogue Workspace dialogue details panel"><figcaption></figcaption></figure>

### Active call

If the selected dialogue is active, the panel shows an **Active call** card with the customer identifier and current state, such as **Connected**.

When an active conversation is selected, Dialogue Workspace can show a **Monitor** action. It shows dialogue details only; it does not join call audio. Close the panel with **X** when finished. See [Monitor details without joining a call](/use/monitor-and-report/dialogue-workspace.md#monitor-details-without-joining-a-call) for the separate WebAgent call-supervision path.

### Conversation details

The **Conversation details** section summarizes the key fields for the selected dialogue:

* **Start time**: When the dialogue started.
* **Customer**: Customer identifier.
* **Agent**: Agent handling the dialogue.
* **Type**: Inbound or Outbound.
* **State**: Current state of the dialogue.
* **Duration**: Elapsed time of the complete dialogue.
* **Skill**: Skill associated with the dialogue.
* **Contact center**: Contact center where the dialogue is handled.

## Tips

* Sort by **Duration** to find unusually long dialogues.
* Use this page together with **Agents** to understand workload and active engagement.
* If **Monitor** is not available, confirm the dialogue is active and ask your administrator to check your Workspace access. Monitor availability does not establish permission to listen through WebAgent.


---

# 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/dialogues.md?ask=<question>&goal=<user_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.