# Enable/Disable Features

#### Using Attributes on the `<hallway-embed>` Tag

You can easily configure your embed by adding attributes directly to the `<hallway-embed>` HTML element. Here's a breakdown of how the example code works:

```
<hallway-embed
    ref={hallwayEmbedRef}
    character-id="a0a6b76d-9237-4114-9623-d8ee86de1233"
    disable-navigation="true"
    mode="voice, text"
/>
```

* \
  \
  \
  `disable-navigation="true"`: By including this attribute, you are telling the embed to not automatically handle navigation. This means if the AI character provides a link, the embed will not navigate the user to a new page. This is useful for custom applications where you want to handle all navigation manually.
* `mode="voice, text"`: This attribute sets the available interaction modes for the chat. With a value of `"voice, text"`, the user will have the option to interact with the AI using either their voice or by typing.\
  \
  \&#xNAN;*Note 1: Order does matter! (i.e. "text, voice" will make text input default.)*\
  \
  \&#xNAN;*Note 2: we save each users last input, so if a user finishes a conversation in text mode, they will return with text mode as the default input method.*
* `disable-mobile-styling="true"`: This attribute will prevent hallway from making the mobile view be full screen on window sizes < 768px
* `force-layout="mobile"` or `force-layout="desktop"`: Forces the embed to render in a specific layout mode regardless of the user's screen size. Omit this attribute to let the embed auto-detect.
* `display-only`: When present, the embed renders in display-only mode with no user interaction (no voice or text input).


---

# 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://hallway.gitbook.io/embed/advanced/enable-disable-features.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.