> ## Documentation Index
> Fetch the complete documentation index at: https://docs.a2v2.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# FAQ

> Quick answers to the questions customers ask most about building, training, embedding, and billing A2V2.ai agents.

Short answers to the questions that come up most often, grouped by theme. Each one
links to the page that covers it in full. If something here points at a problem you're
actively hitting, jump to [Troubleshooting](/troubleshooting) for symptom-by-symptom
fixes.

## Getting started

<AccordionGroup>
  <Accordion title="What is an agent?">
    An agent is an AI chatbot that answers questions using *your* content. You give it a
    [knowledge base](/knowledge-base/overview), shape its behavior with
    [instructions](/building/instructions), test it, and embed it on your site. See the
    [Quickstart](/quickstart) for the end-to-end path.
  </Accordion>

  <Accordion title="How do I create my first agent?">
    Open the dashboard at [app.a2v2.ai](https://app.a2v2.ai) and follow
    [Create an agent](/building/create-agent). The whole build loop — create, train,
    shape, test, ship — is laid out in the [Quickstart](/quickstart).
  </Accordion>

  <Accordion title="How do I sign in?">
    You sign in with **email** (a one-time passcode is sent to your inbox) or with
    **Google**. Your email is your account identity. See [Profile](/settings/profile).
  </Accordion>

  <Accordion title="What's the difference between an account and an organization?">
    Your **account** is your personal login. An **organization** is the shared workspace
    that holds your agents, knowledge, contacts, billing, and team. You can be a member
    of an organization with a [role](/settings/members-and-roles) that controls what you
    can do. More in [Core concepts](/concepts#accounts--organizations).
  </Accordion>

  <Accordion title="Do I need to know how to code?">
    No. Building and training an agent is entirely no-code. You only touch HTML when you
    [embed](/embed/install) the agent on your site — and even then the simplest option, a
    [Share Link](/embed/install#option-1--share-link), needs no code at all.
  </Accordion>
</AccordionGroup>

## Agents & knowledge

<AccordionGroup>
  <Accordion title="What content can I train an agent on?">
    Five source types: [Text](/knowledge-base/text), [Files](/knowledge-base/upload-files)
    (PDF, DOCX, TXT), [Websites](/knowledge-base/website), [YouTube](/knowledge-base/youtube)
    transcripts, and [Q\&A pairs](/knowledge-base/qa). Mix as many as you need. See the
    [Knowledge Base overview](/knowledge-base/overview).
  </Accordion>

  <Accordion title="Why does a source have to say 'Completed'?">
    Adding a source kicks off background processing — the content is read, chunked, and
    indexed. Only **Completed** sources are used in answers. A source that's still
    **Processing** or that **Failed** is invisible to the agent until it finishes. See
    [Manage & reprocess sources](/knowledge-base/manage-sources).
  </Accordion>

  <Accordion title="I updated a document. How do I get the agent to learn the new version?">
    [Reprocess the source](/knowledge-base/manage-sources#reprocess-a-source) from its
    **Actions** menu (**⋯**). Reprocessing re-reads, re-chunks, and re-indexes the latest
    content. For a website or YouTube source it re-fetches the current content at the URL.
  </Accordion>

  <Accordion title="What are instructions?">
    Instructions are the rules that control how your agent behaves — its persona, tone,
    scope, and how it handles questions it can't answer. Knowledge tells the agent *what
    it knows*; instructions tell it *how to act*. Every save is stored as a version you
    can roll back to. See [Instructions](/building/instructions).
  </Accordion>

  <Accordion title="Which AI model should I choose?">
    Pick a model in the [Sandbox](/testing/sandbox) — each option shows its credit cost per
    message and any HIPAA/Premium badges. Lighter models cost less per message and answer
    well from a strong knowledge base; premium models cost more. Compare options in the
    [Model reference](/building/model-settings#model-reference).
  </Accordion>

  <Accordion title="What does temperature do?">
    Temperature controls how focused versus creative answers are, on a slider from
    **Reserved** to **Creative** (default 0.5). Lower keeps answers tight and predictable;
    higher allows more variation. See [Tune temperature](/building/model-settings#tune-temperature).
  </Accordion>
</AccordionGroup>

## Answers & quality

<AccordionGroup>
  <Accordion title="How does the agent decide what to answer?">
    On every question, the agent searches your indexed sources for the most relevant
    passages and writes an answer grounded in them — this is retrieval-augmented
    generation (RAG). See
    [How answers are generated](/concepts#how-answers-are-generated-rag).
  </Accordion>

  <Accordion title="My agent says it doesn't know something it should.">
    Almost always the source isn't **Completed**, or the wording doesn't match. Confirm the
    source finished in the [Knowledge Base](/knowledge-base/overview), then add a
    closer-matching [Q\&A pair](/knowledge-base/qa). Full walkthrough in
    [Troubleshooting](/troubleshooting#my-agent-says-it-doesnt-know-or-gives-the-wrong-answer).
  </Accordion>

  <Accordion title="How do I make answers more exact?">
    Add a [Q\&A pair](/knowledge-base/qa) — a question paired with the exact answer you want
    returned. Q\&A is the most precise way to control a response word-for-word, ideal for
    pricing, policies, and FAQs.
  </Accordion>

  <Accordion title="The tone is wrong. How do I fix it?">
    Sharpen your [instructions](/building/instructions) (persona, tone, formatting) and
    consider lowering [temperature](/building/model-settings#tune-temperature). Test each
    change in the [Sandbox](/testing/sandbox).
  </Accordion>

  <Accordion title="How do I test before going live?">
    Chat with your agent in the [Sandbox](/testing/sandbox), and compare two full
    configurations side-by-side in the [Playground](/testing/playground). Testing there
    is for your own iteration. Playground testing is free.
  </Accordion>

  <Accordion title="Will the agent make things up?">
    It's designed to answer from your sources, and you can instruct it to say so when it
    can't find an answer rather than guess — telling it *not* to guess is one of the
    highest-impact rules you can add. See
    [Fallback behavior](/building/instructions#what-to-put-in-instructions).
  </Accordion>
</AccordionGroup>

## Embedding

<AccordionGroup>
  <Accordion title="How do I put my agent on my website?">
    Three options on the [Embed/Install](/embed/install) screen: a **Share Link** (no code),
    a floating **chat bubble**, or an **inline iframe**. Each snippet is pre-filled for your
    agent — copy it directly from the screen.
  </Accordion>

  <Accordion title="Which embed option should I use?">
    Use a **Share Link** to send the agent as a URL, the **chat bubble** for a site-wide
    assistant on every page, and the **inline iframe** to place the chat inside a specific
    page or layout. See [Embed & install](/embed/install#which-should-i-use).
  </Accordion>

  <Accordion title="The chat bubble isn't showing up on my site.">
    Check the snippet placement (`chatbotId` present, script not stripped) and clear any
    page or CDN cache. Step-by-step in
    [Troubleshooting](/troubleshooting#the-chat-bubble-or-widget-doesnt-appear).
  </Accordion>

  <Accordion title="Will the widget clash with my site's styles?">
    No. The widget loads inside an isolated container (a Shadow DOM), so it won't affect
    your site's styles and won't be affected by them. See
    [Embed & install](/embed/install#option-2--chat-bubble-recommended).
  </Accordion>

  <Accordion title="Can I control who's allowed to use the embedded agent?">
    Yes. On [Visibility & access](/embed/visibility) you choose **Private** (only you) or
    **Public**, and for public agents you pick **Use for Free**, **Restrict** (only your
    CRM users), or **Pay for Access**.
  </Accordion>
</AccordionGroup>

## Credits & billing

<AccordionGroup>
  <Accordion title="What are credits?">
    Credits are how A2V2.ai meters usage. Instead of counting messages, models, and
    documents separately, everything draws from one balance. See
    [Credits explained](/billing/credits-explained).
  </Accordion>

  <Accordion title="What spends credits?">
    Answering a visitor message (cost varies by model), processing a source into the
    knowledge base, voice transcription, and agent tools/skills. Internal testing in the
    [Playground](/testing/playground) is free. Details in
    [Credits explained](/billing/credits-explained#what-spends-credits).
  </Accordion>

  <Accordion title="What are the two credit pools?">
    **Plan credits** come with your subscription and refill each billing period; **Top-up
    credits** are bought (manually or via auto-recharge) and carry over. They're spent in
    order — plan first, then top-up. See
    [Credits explained](/billing/credits-explained#your-two-credit-pools).
  </Accordion>

  <Accordion title="What happens when I run out of credits?">
    Agents stop generating new answers until you top up or your plan period resets — but
    nothing is deleted. Turn on [auto-recharge](/billing/auto-recharge) so a busy spell
    can't take agents offline. See
    [Credits explained](/billing/credits-explained#what-happens-at-zero-balance).
  </Accordion>

  <Accordion title="How do I add more credits?">
    Use **Top Up Now** for an immediate top-up, or turn on
    [auto-recharge](/billing/auto-recharge) to top up automatically when your balance gets
    low. Manage your payment method through the
    [checkout & billing portal](/billing/checkout-and-portal).
  </Accordion>

  <Accordion title="Can I charge my own visitors to use an agent?">
    Yes — that's [Pay for Access](/billing/paid-agents). You set a price, access duration,
    and message allowance, and the revenue is yours. It's set up with help from the
    A2V2.ai team.
  </Accordion>

  <Accordion title="How do I change my plan?">
    Compare and switch on the [Plans](/billing/plans) page. Billing changes are
    Owner-only. Need capacity beyond credits? See [Add-ons](/billing/add-ons).
  </Accordion>
</AccordionGroup>

## Team & access

<AccordionGroup>
  <Accordion title="How do I invite teammates?">
    Invite from the team list and assign a role. See
    [Members & roles](/settings/members-and-roles).
  </Accordion>

  <Accordion title="What can each role do?">
    **Owner** can do everything, including billing and deleting the organization. **Admin**
    manages agents, knowledge, contacts, and team members. **User** works with agents and
    content without organization-level admin. Full breakdown in
    [Members & roles](/settings/members-and-roles#the-three-roles).
  </Accordion>

  <Accordion title="The invite button says 'Buy more seats'.">
    You've used every team seat on your plan. Add the **Team Member**
    [add-on](/billing/add-ons) or upgrade your [plan](/billing/plans). Seat changes are
    handled by the Owner.
  </Accordion>

  <Accordion title="An invited teammate isn't showing as active.">
    Their invite is pending until they accept it from the email. Check the **Progress**
    column on the team list, and re-send if needed. See
    [Members & roles](/settings/members-and-roles#troubleshooting).
  </Accordion>

  <Accordion title="How do I change the email on my account?">
    Email is read-only on the [Profile](/settings/profile) page because it's your sign-in
    identity. To use a different email, contact
    [support@a2v2.ai](mailto:support@a2v2.ai).
  </Accordion>
</AccordionGroup>

## Data & privacy

<AccordionGroup>
  <Accordion title="Is my content kept separate from other customers?">
    Yes. Everything you do happens inside your **organization**, and your data is isolated
    from every other organization on the platform. See
    [Core concepts](/concepts#accounts--organizations).
  </Accordion>

  <Accordion title="What does my agent actually use to answer?">
    Only the sources you add to its knowledge base, retrieved per question and used to
    ground the answer. See
    [How answers are generated](/concepts#how-answers-are-generated-rag).
  </Accordion>

  <Accordion title="Can I make an agent forget something I added?">
    Yes. Delete the source from its **Actions** menu (**⋯**) and it's removed from the
    agent's index, so it no longer appears in answers. See
    [Manage sources](/knowledge-base/manage-sources#remove-a-source).
  </Accordion>

  <Accordion title="Where can I review who did what in my organization?">
    The [Audit logs](/settings/audit-logs) record activity across your organization.
  </Accordion>

  <Accordion title="Who can I contact about security or data questions?">
    Email [support@a2v2.ai](mailto:support@a2v2.ai) with your organization name and the
    specifics of your question.
  </Accordion>
</AccordionGroup>

## Still stuck?

<CardGroup cols={2}>
  <Card title="Troubleshooting" icon="wrench" href="/troubleshooting">
    Symptom-by-symptom fixes for the most common issues.
  </Card>

  <Card title="Core concepts" icon="lightbulb" href="/concepts">
    How agents, knowledge, RAG, and credits fit together.
  </Card>

  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Build and embed your first agent end-to-end.
  </Card>

  <Card title="Contact support" icon="envelope" href="mailto:support@a2v2.ai">
    Email us with your organization name and the agent involved.
  </Card>
</CardGroup>