> 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/handle-conversations/webagent/manage-dialogues-and-history.md).

# Manage dialogues and call history

Work with waiting dialogues, customer context, classifications, and call history in WebAgent.

Use **Dialogues** to review your conversations. In the classic layout, waiting work and conversations connected to other agents are also available here; in the new layout, waiting work has a separate **Queue** item in the left navigation. The details shown depend on your UCC, connected services, and access.

## Take a waiting dialogue

1. In the classic layout, open **Dialogues** and select **Waiting**. In the new layout, open **Queue** from the left navigation.
2. Check the sender, skill, and time in the queue before selecting a dialogue.
3. Select **Take** to have the conversation offered to you, then answer it using the controls for its channel.

In the classic layout, the explicit **Preview** button is for text content and is not shown for phone calls. Where the new-layout phone-details preview is available, selecting a phone item in **Queue** shows the caller, skill, received time, duration, UCC, and status. Opening these details does not listen to or answer the call; **Take** remains a separate action. Use the controls available in your deployed layout.

In the Waiting and Connected views, use the available sort, group, and view controls to focus the list. For example, sort by duration or skill, group by channel or UCC, or switch text items between compact and extended details. Connected-only options can include the assigned agent.

## Find text-dialogue controls

In the **classic layout**, open **Dialogues**, choose your dialogue from **Personal**, and select its **Conversation** tab. The dialogue header above the tabs has actions such as **Accept**, **Decline**, **Reply**, and **Handled**, according to the dialogue's state. The message list and reply editor are in the **Conversation** tab.

In the **new layout**, select **Dialogues** in the left navigation and choose your dialogue from the left-hand panel. The header above the message thread contains the available actions; the reply editor is below the messages. If you take a waiting text dialogue from **Queue**, it is offered to you before you accept it.

After accepting, type in the reply editor and select **Send** below it. **Reply all**, **Forward**, attachments, and other actions appear only for channels and dialogues that support them. To complete the dialogue, select **Handled** in its header; if classification is enabled and none has been saved, WebAgent may prompt for it before finishing. **Handled** is not the **Send** button.

For available text-search results, open **Text Search** from the WebAgent navigation. In the new layout it is a separate left-navigation item; select a result to see its preview. Search availability and results depend on your configuration.

## Review customer context

During a dialogue, find **Contact information** in the left column of the classic layout. In the new layout, use its button beside the conversation to open the side panel (or look for its visible widget, if configured). If the contact is missing or the wrong record is selected, search by name or phone number, select the matching record, or deselect the wrong one. CRM fields and cases depend on your organization's connected service.

Use **Previous Contacts** or **Timeline** when available to review earlier customer interactions. In the classic layout, find **Previous Contacts** with the contact details or open the **Timeline** tab. In the new layout, look for a widget or side-panel button beside the conversation. The timeline shows previous contact moments, not the current conversation; select an entry to inspect its details. History may be incomplete if it was not collected for the UCC. If **Cases** is available, open its tab in the classic layout or its widget or side-panel button in the new layout to view a case or its back-office link.

## Classify a dialogue

If your UCC has classifications:

1. Open the dialogue. In the classic layout, select the **Classification** tab beside **Conversation** and **Timeline**. In the new layout, look for the **Classification** widget in the conversation or select its button beside the conversation to open the side panel. The position depends on your screen size and widget settings.
2. Select the appropriate classification from the available options and select **Save**.

You can also classify a phone dialogue **after the call disconnects**, while the dialogue remains open for handling. When you select the conversation's **Finish / End conversation** control without a saved classification, WebAgent may prompt you to classify before completing it. Choose a classification and select **Save and handle**, or select **Cancel** to return to the dialogue. **Finish without classify** is shown only when your UCC permits it. Do not assume you can reopen a completed dialogue to classify it later.

After a transfer or requeue, the conversation can leave your workspace and classification may no longer be available to you. Classify before handing it over if your organization's process requires that.

## Review your call history

Open **Call History** from the navigation in either layout to see available historical audio conversations. Select a call in the history list to see its details; where available, open **Timeline** beside those details. Filter by **All**, **Incoming**, **Outgoing**, or **Missed**. **Incoming** includes calls you accepted, not every UCC hunt; **Missed** covers missed direct inbound calls, not regular UCC hunts. Where available, use a history entry to call the contact back.

Call History, Previous Contacts, Timeline, and Frequent Transfers depend on the history configured for your UCC. For current Dialogue Cloud Neo deployments, history can come from Dialogue Insights; availability begins only after that history is collected. Some existing Connect environments continue to use an approved Universal Timeline Service configuration. Ask your administrator if a history area is missing or unexpectedly empty.


---

# 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/handle-conversations/webagent/manage-dialogues-and-history.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.
