> ## Documentation Index
> Fetch the complete documentation index at: https://developers.webai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Chat

> Ask questions, use voice input, switch between Offline and Online mode, manage threads, apply skills, and get streamed replies in Chat.

export const ChatFaq = () => <AccordionGroup>
    <Accordion title="What is a skill and how do I use one?">
      A <strong>skill</strong> is a reusable add-on that shapes how the assistant approaches a request, so you don't have to repeat the same instructions. Click <strong>+</strong> in the Chat prompt window and choose a skill from the <strong>skills dropdown</strong>; it applies to that message.
    </Accordion>
    <Accordion title="What's the difference between Offline and Online mode?">
      <strong>Offline</strong> is the default. Chat uses your local setup, and when you have a downloaded model, replies are generated on your machine. <strong>Online</strong> turns on web search for that message so webAI can pull in current information from the internet. Switch modes with the <strong>Offline / Online</strong> dropdown in the prompt bar.
    </Accordion>
    <Accordion title="Do Online answers include sources?">
      Yes. When you send a message in <strong>Online</strong> mode, webAI searches the web and includes <strong>citations</strong> to the source websites in the answer.
    </Accordion>
    <Accordion title="Can I speak instead of typing?">
      Yes. Click the <strong>microphone</strong> in the prompt window, speak your message, and webAI transcribes it into the composer. Click <strong>Send</strong> when you're ready. The same control works when you chat with a persona on the <strong>Personas</strong> tab.
    </Accordion>
    <Accordion title="Can I rename or delete a conversation?">
      Yes. From the Chat home or the sidebar you can <strong>rename</strong> or <strong>delete</strong> any thread, so you can tidy up the names you use and clear out the ones you don't.
    </Accordion>
    <Accordion title="Can I get a different answer to the same question?">
      Yes, you can <strong>regenerate</strong> a reply for a fresh take, or use <strong>Answer as</strong> (the dropdown on a reply) to have a <strong>different persona</strong> answer the same message.
    </Accordion>
  </AccordionGroup>;

Chat is the main surface you land on: a prompt composer with your recent conversations close at hand. It's where you ask questions and start and continue threads with the general assistant.

The left sidebar is your main navigation. **Chat** is the headline destination; **Messages**, **Contacts**, **Personas**, and **Artifacts** sit alongside it. Settings lives in the account menu at the bottom.

## What you can do

* **Ask and converse.** Type a prompt and get a streamed reply. Conversations are kept as threads you can return to.
* **Use voice input.** Click the **microphone** in the prompt window to dictate your message, see [Voice input](#voice-input) below.
* **Switch Offline or Online.** Use the dropdown in the prompt bar to choose how Chat answers, see [Offline and Online mode](#offline-and-online-mode) below.
* **Apply a skill.** Click **+** in the prompt window and choose a skill from the dropdown to shape how a run behaves.
* **Run locally in Offline mode.** When you use a downloaded model in **Offline** mode, replies are generated on your machine, not in the cloud.
* **Manage a reply.** Regenerate an answer, or use **Answer as** to have a different persona respond to the same message.

## Answer as, choose which persona responds

Every reply has an **Answer as** control in its toolbar (the dropdown next to the regenerate and copy buttons). Open it and pick any of your personas, the **General Assistant**, a specialist you've built, or any other, and that persona answers the conversation. It's the quickest way to get a second perspective, or to hand a question to a more suitable persona, without starting a new thread.

<Note>
  For dedicated conversations with a specific persona, open the **Personas** tab and click a persona card, see [Personas](/using-webai/personas).
</Note>

## Offline and Online mode

Use the **Offline / Online** dropdown in the prompt bar to choose how Chat answers your next message.

**Offline** is the default. Chat uses your local setup, when you have a downloaded model, replies are generated on your machine.

**Online** turns on web search for that message. webAI searches the internet for current information and weaves the results into the answer. **Citations** to the source websites appear in the reply so you can see where the information came from.

<Note>
  **Online** mode sends your query off your device for web search. See the [Privacy Policy](https://www.webai.com/privacy) for how that data is handled.
</Note>

## Skills

**Skills** are reusable add-ons that shape how the assistant handles a request, applying one tailors the way that response is approached, so you don't have to spell out the same instructions every time.

To use one, click **+** in the prompt window and select a skill from the **skills dropdown**. It applies to that message, then the assistant replies with the skill guiding how it works.

## Voice input

Click the **microphone** in the prompt window to speak instead of type. webAI listens and transcribes your speech into the composer. When the text looks right, click **Send** to submit the message.

The same microphone control is available when you chat with a persona on the **Personas** tab, see [Personas](/using-webai/personas).

## Recent conversations

* Recent threads appear on the Chat home and in the sidebar. You can **rename** and **delete** them.
* Direct and group conversations with people stay **out** of this list, those live in [Messages](/using-webai/messages).

## Common questions

<ChatFaq />

<Note>
  More answers are in the [FAQ](/support/faq#chat).
</Note>