> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/stackai-tools/communication-and-human-input/ask-human-in-chat-interface.md).

# Ask Human in Chat Interface

Pause a conversation to ask for missing information or a decision. Use it when the next step needs a response from the person using the chat.

## Before you start

Use a chat interface that supports the human-input prompt.

## Ask for a response

1. Write a clear **Question** and use **Context** to explain why the answer is needed.
2. Choose **Response Type**. For a choice response, supply the allowed **Choices**.
3. Run the workflow through the chat interface and submit a response to the prompt.
4. Use the resumed response to decide what the workflow does next. Include a path for a rejected or unsuitable response.

**Result:** The run continues with the human response after the person submits it.

## Behavior and troubleshooting

Showing a question is not the same as receiving approval. Keep actions that depend on the decision after the response is received. This is an interactive chat step; an unattended schedule cannot supply a human response on its own.

## Inputs

| Field               | Parameter       | Description                                                      |
| ------------------- | --------------- | ---------------------------------------------------------------- |
| Question (required) | `question`      | The question or request to present to the human.                 |
| Context             | `context`       | Additional context to help the human understand the question.    |
| Response Type       | `response_type` | The type of response expected from the human. Default: `"text"`. |
| Choices             | `choices`       | List of choices when response\_type is 'choice'.                 |

## Outputs

| Field         | Parameter       | Description                                      |
| ------------- | --------------- | ------------------------------------------------ |
| Question      | `question`      | The question asked to the human.                 |
| Context       | `context`       | Additional context provided.                     |
| Response Type | `response_type` | The type of response expected.                   |
| Choices       | `choices`       | The choices available for selection.             |
| Resume Output | `resume_output` | The human's response data when workflow resumes. |

## Related guidance

[Human Input and Approval Controls](/technical-reference/interfaces-and-conversations/human-input-and-approval-controls.md)


---

# 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://docs.stackai.com/stackai-tools/communication-and-human-input/ask-human-in-chat-interface.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.