> 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/guides-and-quickstarts/interfaces-and-end-user-experiences/interface-branding-and-feedback.md).

# Interface branding and feedback

Interface branding explains who the assistant is and what it can help users do. Feedback controls let people report whether a response met their needs.

{% embed url="<https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSQ1Sgy933krTyK0S4JpP%2Fuploads%2FLe65x9SVeoAJCUjnYffY%2FG061.mp4?alt=media&token=29801536-0c33-4ec5-9f57-3958e03da2c9>" %}

## Before you start

Open an existing interface with permission to edit and publish its settings. Use [Publish a Chat Assistant](/guides-and-quickstarts/interfaces-and-end-user-experiences/publish-a-chat-assistant.md) to create the chat interface first.

## Set the welcome content

Set the interface Name, Description, and input hint.

![Interface welcome content fields](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/0xQ3CL2x0NfX8f4bR46O/assets/g061-g061-01-general.png)

Use these fields to explain the assistant's purpose and guide the user's first request.

## Choose an avatar

Under Style, use Change to choose an appropriate avatar.

![Interface avatar selection controls](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/HcAe91RBfkFJRkHtOEso/assets/g061-g061-02-avatar.png)

Check that it remains recognizable at the size shown in the chat preview.

## Enable feedback

Enable User feedback in Configuration and set a useful Feedback placeholder.

![Response feedback configuration controls](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/MwL8BpWNLhevekPG8RS9/assets/g061-g061-03-configuration.png)

The prompt should help users explain what was helpful or what needs correction.

## Add conversation starters

Enable Conversation Starters and enter common requests the assistant can handle.

![Conversation starter configuration fields](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/9Iqm8bsHwhVF2c1LEqX0/assets/g061-g061-04-starters.png)

Save the interface after editing the starters.

## Publish and review the interface

Publish the saved changes and open the interface.

![Published interface appearance check](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/hT7vyReqSEAdofkQL9AI/assets/g061-g061-05-welcome.png)

Check the name, description, avatar, placeholder, and conversation starters together.

Select a conversation starter and inspect the response.

![Published interface appearance check](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/VUWQ6fdx6k5b88koGfqK/assets/g061-g061-06-answer.png)

Confirm that the suggested request is supported by the workflow behind the interface.

## Read response feedback

Use the feedback control on a response and submit a useful comment where available.

![Response feedback and Analytics review](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/PcEIU3vfuj9E5WixyFYn/assets/g061-g061-07-feedback.png)

Check that the interface reflects the submitted feedback.

Locate the corresponding run in Analytics and inspect its feedback indicator.

![Response feedback and Analytics review](https://content.gitbook.com/content/SQ1Sgy933krTyK0S4JpP/blobs/JdTUMm4BZZSrGFSIuv6S/assets/g061-g061-08-analytics.png)

Open Run Details to review the feedback in the context of the request and response.

## Important behavior

Conversation starters submit predefined requests. Use requests that the connected workflow can handle.

Feedback is associated with the response and can be reviewed with the corresponding run.

## Continue

* [Use a published chat](/guides-and-quickstarts/interfaces-and-end-user-experiences/use-a-published-chat.md)
* [Inspect project analytics](/guides-and-quickstarts/evaluations-and-observability/inspect-project-analytics.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/guides-and-quickstarts/interfaces-and-end-user-experiences/interface-branding-and-feedback.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.