> 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/handle-webchat-dialogues.md).

# Handle WebChat dialogues

Handle WebChat dialogues in WebAgent.

Use WebAgent to accept, reply to, classify, and search WebChat dialogues when WebChat handling is enabled for your environment. For the location of the dialogue header, message editor, and search controls in each layout, see [Find text-dialogue controls](/use/handle-conversations/webagent/manage-dialogues-and-history.md#find-text-dialogue-controls).

## Start from WebAgent

Sign in to WebAgent and, when needed, sign in to your Unified Contact Center (UCC).

{% content-ref url="/pages/BMdIFYECjbXP70y88EAT" %}
[Sign in and manage your profile](/use/handle-conversations/webagent/sign-in-and-profile.md)
{% endcontent-ref %}

## Handle an incoming WebChat dialogue

1. When WebAgent offers the WebChat dialogue, open it in **Dialogues**. In the classic layout, choose it from **Personal** and open **Conversation**; in the new layout, choose it from the **Dialogues** panel on the left.
2. Select **Accept** in the dialogue header, or **Decline** if you cannot handle it. If you take a waiting chat from **Queue**, accept it when offered.
3. Read the customer's messages in the thread. Type your response in the editor below the messages and select **Send** below the editor. If available, use **Attachment** beside the editor to add a file.
4. When the conversation is complete, [classify the dialogue](/use/handle-conversations/webagent/manage-dialogues-and-history.md#classify-a-dialogue) if needed, then select **Handled** in the dialogue header. WebAgent may ask for a classification before finishing.

## Use timeline and classification details

When available, open **Timeline** or **Classification** beside the conversation: use their tabs in the classic layout, or a widget or side-panel button in the new layout.

If the customer disconnects and the dialogue remains open in wrap-up, you can still classify it before selecting **Handled**. Once it leaves your workspace, do not assume you can reopen it to classify it. The fields and actions shown depend on your environment.

## Customer connection state

WebAgent may show whether the customer is connected, has left the WebChat page, or has disconnected the conversation. The exact state names and reconnect behavior depend on your WebChat configuration.

## Search WebChat dialogues

Open **Text Search** from the WebAgent navigation to find available archived WebChat conversations; in the new layout, it has its own left-navigation item. For waiting chats, use **Waiting** in the classic **Dialogues** area or **Queue** in the new layout. Search availability and filters depend on your configuration.

## Settings

Open [WebAgent preferences](/use/handle-conversations/webagent/set-webagent-preferences.md) for notification and text-alert settings. Settings can differ between organizations and dialogue channels.


---

# 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/handle-webchat-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.