> ## 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.

# Frequently asked questions

> Answers to common questions about privacy, models, personas, contacts, messages, and settings.

export const SystemFaqItems = () => <>
    <Accordion title="How do I update the app?">
      Go to <strong>Settings → System</strong> and <strong>check for and apply updates</strong>. The same section shows your current version and whether you're on a stable or experimental build.
    </Accordion>
    <Accordion title="What does Factory reset do?">
      Found under <strong>Settings → System</strong>, <strong>Factory reset</strong> clears all app data and returns webAI to defaults, then re-runs first-run onboarding. It's permanent, so only use it when you want a completely clean slate. To find on-disk folders for manual removal, see <a href="/support/faq#models--storage">Where does webAI store data on my Mac?</a> in the FAQ.
    </Accordion>
  </>;

export const DataStorageFaqItems = () => <>
    <Accordion title="How do I free up disk space?">
      Downloaded models are cached on disk and can be large. Go to <strong>Settings → Data & Storage → Model tab → cached models</strong> to see each one's size and when it was last used, reveal it in the file manager, or delete ones you no longer need. You can also clear an individual app's stored data from the same section.
    </Accordion>
    <Accordion title="Where does webAI store data on my Mac?">
      <p>
        For most situations, use the in-app controls: <strong>Settings → Data & Storage</strong> to manage models and per-app data, or <strong>Settings → System → Factory reset</strong> to clear everything and start over. See <a href="/support/faq#settings">What does Factory reset do?</a> for what that covers.
      </p>
      <p>
        If you need to remove files manually(for example, after uninstalling webAI ), <strong>quit the app first</strong>, then look in these folders (<code>~</code> is your home folder):
      </p>
      <ul>
        <li><code>~/.webai</code>, main application data</li>
        <li><code>~/Library/Caches/webai</code>, webAI cache files</li>
        <li><code>~/Library/Caches/com.apogee.shell</code>, app shell cache files</li>
        <li><code>~/.cache</code>, additional cache data; <strong>this folder can be shared with other apps</strong>, so only remove contents here if you understand the impact</li>
      </ul>
      <p>
        In Finder, press <strong>⌘⇧G</strong>, paste a path, and press <strong>Return</strong> to open it. You can move folders to the Trash or delete their contents.
      </p>
      <p>
        <strong>Advanced (Terminal):</strong> After quitting webAI, you can clear the contents of the webAI-specific folders with:
      </p>
      <pre><code>{`for folder in ~/.webai ~/Library/Caches/webai ~/Library/Caches/com.apogee.shell; do
  [ -d "$folder" ] && find "$folder" -mindepth 1 -delete
done`}</code></pre>
      <p>
        To also clear <code>~/.cache</code>, add it to the list, but be aware that folder may contain cache data from other software on your Mac.
      </p>
    </Accordion>
  </>;

export const AppearanceFaqItems = () => <>
    <Accordion title="How do I switch between light and dark mode?">
      Open <strong>Settings → Appearance</strong> and choose a <strong>theme</strong>: System, Dark, or Light. System follows your macOS appearance automatically.
    </Accordion>
  </>;

export const ModelsFaqItems = () => <>
    <Accordion title="Do I have to download a model before I can use the AI locally?">
      Yes, to run AI locally on your machine you first need to download a <strong>local model</strong>. Open <strong>Settings → Model</strong>, pick one from the catalog, and download it. You only do this once per model; you can add or update models anytime.
    </Accordion>
    <Accordion title="Which model should I download?">
      Open <strong>Settings → Model</strong> and browse the <strong>catalog</strong>, each model lists its size and whether it fits your memory. Check your <strong>device profile</strong> (memory, GPU, CPU cores) for guidance. You can always download a different one later.
    </Accordion>
  </>;

export const MessagesFaqItems = () => <>
    <Accordion title="How do I start a group chat?">
      In <strong>Messages</strong>, click <strong>+ New</strong> in the bottom right to open the <strong>New conversation</strong> window, search for and add <strong>two or more contacts</strong>, then click <strong>Start conversation</strong>. Everyone in the group can read and post, and the <strong>creator manages membership</strong>.
    </Accordion>
  </>;

export const ContactsFaqItems = () => <>
    <Accordion title="How do I add someone as a contact?">
      Open the <strong>Contacts</strong> tab and use the <strong>Add Contact</strong> area. Either click <strong>Generate Invite</strong> and share the QR code or link with the other person (it works once), or, if someone sent you a link, paste it under <strong>Paste an invite link</strong> and click <strong>Pair</strong>. Once connected, they appear in your Contacts list.
    </Accordion>
    <Accordion title="What's the difference between a persona and a contact?">
      A <strong>persona</strong> is a custom AI identity you create: a name, role, personality, and model choices. A <strong>contact</strong> is a person you've connected with. Bring a persona into a Chat message with `@`; to reach a contact, start a conversation in <strong>Messages</strong>.
    </Accordion>
    <Accordion title="Why didn't my contact invite connect?">
      Both people must stay on the <strong>Contacts</strong> screen until pairing finishes. If you generated an invite, stay on <strong>Contacts</strong> while the other person uses your link or QR code. If you're accepting an invite, stay on <strong>Contacts</strong> after clicking <strong>Pair</strong> until you're connected. Navigating away interrupts the handshake. Return to <strong>Contacts</strong>, generate or paste a new invite, and try again.
    </Accordion>
  </>;

export const PersonasFaq = () => <AccordionGroup>
    <Accordion title="What's the difference between a persona and a contact?">
      A <strong>persona</strong> is a custom AI identity you create, a name, role, personality, and model choices. A <strong>contact</strong> is a person you've connected with. Click a persona on the <strong>Personas</strong> tab to chat with it; to reach a contact, start a conversation in <strong>Messages</strong>.
    </Accordion>
    <Accordion title="Do I have to write a persona's system prompt myself?">
      No. On a persona's details, fill in the <strong>Description</strong> and click <strong>AI Generate</strong>, the model reads your description and writes a system prompt for you. Use it to start from scratch or to sharpen one you've already begun.
    </Accordion>
  </AccordionGroup>;

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>;

export const GettingStartedFaq = () => <AccordionGroup>
    <Accordion title="Where does my data go: is webAI private?">
      When using local models, replies are generated <strong>on your own machine</strong> and not in the cloud. Some features send data off your device, such as <strong>Online</strong> mode in Chat (web search), network-hosted Personas, cloud models you connect with your own API key, and messaging with your contacts. See the <a href="https://www.webai.com/privacy">Privacy Policy</a> for how each one handles your data.
    </Accordion>
    <Accordion title="What do I need to run webAI?">
      A Mac with <strong>Apple Silicon</strong> running <strong>macOS Tahoe (26) or later</strong>, plus at least <strong>1 GB</strong> of available graphics memory. Running on Apple Silicon enables on-device AI when you use a downloaded model.
    </Accordion>
    <Accordion title="Does this guide cover Windows, the web app, or mobile?">
      No, this guide is for the <strong>webAI desktop app on macOS (Apple Silicon)</strong>. The web build and the mobile clients are separate products with a different set of features.
    </Accordion>
  </AccordionGroup>;

Browse by topic below, or jump to the relevant guide: [Chat](/using-webai/chat), [Personas](/using-webai/personas), [Contacts](/using-webai/contacts), [Messages](/using-webai/messages), and [Settings](/settings/profile).

## Getting started & privacy

<GettingStartedFaq />

## Chat

<ChatFaq />

## Personas

<PersonasFaq />

## Contacts & messages

<AccordionGroup>
  <ContactsFaqItems />

  <MessagesFaqItems />
</AccordionGroup>

## Models & storage

<AccordionGroup>
  <ModelsFaqItems />

  <DataStorageFaqItems />
</AccordionGroup>

## Settings

<AccordionGroup>
  <AppearanceFaqItems />

  <SystemFaqItems />
</AccordionGroup>