# Human Handoff

{% hint style="info" %}
A human handoff requires at least one [Team](/docs/settings/workspace/teams.md) with a live agent signed-in and available to inherit chats from the AI agent.
{% endhint %}

The Human Handoff action transfers a chat from the AI agent to a live agent, who replies to chats from the [Inbox](/docs/modules/inbox.md) helpdesk dashboard. Once a live agent is handling a chat, it's referred to as a [livechat](/docs/modules/livechats.md).

***

## Configuration

Select a **Human Handoff** action from the tree to open its settings:

* **User availability check** — when enabled, chats are only transferrable to a live agent who's [online](/docs/settings/user-account/online-status.md).
* **Assign chat** — determines where the chat gets transferred:
  * **Assign to all users in the teamspace** — all live agents in the same teamspace as the AI agent will see the pending chat and be able to claim it.
  * **Assign to specific users or teams** — only the specified teams or live agents will see the chat.
    * **Assign by language (optional)** — if the AI agent supports multiple languages defined in its [General settings](/docs/modules/ai-agents/manage-ai-agents.md#general), you can further concentrate the team/live agent assignments by language.

See [Chat Assignment](/docs/settings/teamspaces/chat-assignment.md) to configure how chats get assigned to specific live agents.

***

## Handing Back to AI Agent

A chat is automatically returned from a live agent back to the AI agent when the chat's **status** is marked as **Closed**. This initiates the [Chat Closed by Live Agent](/docs/modules/ai-agents/workflows-and-actions.md) trigger, and any enabled subsequent actions like [Collect Feedback](/docs/modules/ai-agents/workflows-and-actions/collect-feedback.md) will take place.

Then, the chat flow will immediately resume from the original Human Handoff action, running through any subsequent actions in the nested ***When live agent closes chat*** tree.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://documentation.proto.cx/docs/modules/ai-agents/workflows-and-actions/human-handoff.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.