# Handoff

Handoff card utility card allows you to transfer the conversation to an agent or group of agents. You can configure the handoff destination, message, and fallback option. You can use a Handoff card to escalate the conversation to a human agent.

## Using Human Handoff Card

### Assign

* You need to choose how you want to assign the conversation to a human agent. You can choose from three options: by queue, to agent, or to group. 
* By queue means that the conversation will be added to a queue of pending conversations and assigned to the next available agent. 
* To agent means that the conversation will be directly assigned to a specific agent that you select. 
* To group means that the conversation will be assigned to a group of agents that share a common skill or role. 

For example, you can choose to assign the conversation by queue if you have a large number of agents and customers, or to agent if you have a dedicated agent for a particular customer, or to group if you have a specialized team of agents for a certain topic or issue.

### Internal Message (Optional) 

* You can also enter an internal message that will be sent to the human agent along with the conversation. The internal message can be up to 1024 characters long and can include emojis. You can use the internal message to provide some context, information, or instructions to the human agent. 

For example, you can write: “This customer is asking for a refund. Please check their order history and follow the refund policy.”

<figure><img src="/files/CzWRmvYVfIle66QpOzf2" alt=""><figcaption></figcaption></figure>


---

# 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://docs.makerobos.com/chatman-enterprise-whatsapp-platform/chatman-functions/journeys/utility-cards/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.