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

# Quick Start

> Go from sign-up to a live, deployed AI agent in minutes.

This guide walks you through the essential steps to get your first agent up and running in the RoseRx Platform. By the end, you'll have a fully configured AI chat agent deployed on your website.

<Info>
  You'll need a RoseRx account to follow along. If you don't have one yet, contact [support@roserx.ai](mailto:support@roserx.ai) to get started.
</Info>

<Steps>
  <Step title="Sign up and create your organization">
    Start by signing in to the [RoseRx dashboard](https://app.roserx.ai). If your organization hasn't been set up yet, you'll be guided through creating one.

    Your organization is the top-level account that holds all your agents, widgets, and team members. You can invite colleagues and assign roles once it's created.

    <Tip>
      If your organization already exists, ask a team admin to send you an invite so you can join directly.
    </Tip>
  </Step>

  <Step title="Create your first agent">
    Navigate to **Agents** in the sidebar and click **Create Agent**. You can start two ways:

    * **Create from Product Information** — The fastest path. Link a product (search the DailyMed registry in the United States, or upload a Product Information PDF in Australia) and the platform analyzes it, sets up the agent, and indexes the content as knowledge sources automatically. You choose the audience (HCP or Patient) and region as part of the wizard.
    * **Blank Agent** — Start from scratch and configure everything yourself.

    Either way, you'll work with one of four agent types: **HCP Clinical Decision Support**, **Patient Navigator**, **Medication Navigator**, or **Field Team Co-Pilot**. See [Creating an Agent](/guides/agents/creating-an-agent) for a comparison.

    Once created, configure your agent's general settings:

    * **AI Model** — Select the model tier that powers your agent: **Fast**, **Balanced** (recommended), or **Advanced**.
    * **Tone of voice** — Set how the agent communicates (e.g. professional, empathetic, conversational).
    * **Response length** — Control how detailed or concise the agent's replies are.
  </Step>

  <Step title="Add knowledge">
    Go to the **Knowledge Base** tab within your agent's settings.

    Add your approved content as any of four source types — **PDF documents**, **website URLs**, **Q\&A pairs**, and **text snippets** — and the RoseRx Platform will automatically process them. Documents are chunked, embedded, and indexed so your agent can retrieve the most relevant information when responding to questions, while Q\&A pairs return your approved answer verbatim when a question matches.

    <Note>
      This is your agent's internal knowledge. Only content in the Knowledge Base is used to generate responses. The more comprehensive and up-to-date your sources, the better your agent performs.
    </Note>
  </Step>

  <Step title="Configure guardrails">
    Navigate to the **Guidance** tab to set up your agent's regulatory compliance settings.

    * **Jurisdiction** — Choose the regulatory framework that applies (e.g. TGA for Australia, FDA for the United States).
    * **Therapy type** — Specify whether the treatment is a prescription medicine, OTC, medical device, or other classification.
    * **Prohibited terms** — Define words or phrases the agent must never use.
    * **Off-label policies** — Configure how the agent handles questions about unapproved uses.

    <Warning>
      Guardrails are essential for regulatory compliance. Take the time to configure them thoroughly before deploying your agent to a live environment.
    </Warning>
  </Step>

  <Step title="Create and deploy a widget">
    Navigate to **Deploy → Widget** in the sidebar and click **Create Widget**.

    * **Assign your agent** — Link the widget to the agent you just configured.
    * **Customize appearance** — Set the theme, brand colors, widget type (popup, slider, or fullscreen), and configure which tabs are visible (Chat, Resources, etc.).
    * **Activate the widget** — Toggle the widget status to **Active**.
    * **Copy the embed code** — Grab the embed snippet and paste it into your website's HTML.

    ```html theme={null}
    <!-- Example embed snippet -->
    <script src="https://app.roserx.ai/embed.js" data-widget="YOUR_WIDGET_ID"></script>
    ```

    <Tip>
      You can restrict which domains your widget appears on for added security. Configure this in the widget's domain settings.
    </Tip>
  </Step>

  <Step title="Monitor conversations">
    Once your widget is live, use the monitoring tools to track how your agent is performing:

    * **Activity** — View conversation volumes, usage trends, and key metrics at a glance.
    * **Conversations** — Review individual conversations to check response quality and accuracy.
    * **Adverse Events** — Monitor for potential adverse drug reactions detected automatically by the platform's pharmacovigilance system.

    <Info>
      Regularly reviewing conversations and adverse events helps you refine your agent's knowledge base and guardrails over time.
    </Info>
  </Step>
</Steps>

## Next steps

Now that your first agent is live, explore these guides to get the most out of RoseRx:

<CardGroup cols={2}>
  <Card title="Agent Settings" icon="gear" href="/guides/agents/general-settings">
    Fine-tune your agent's AI model, tone, and behavior.
  </Card>

  <Card title="Guidance & Guardrails" icon="shield-check" href="/guides/agents/guidance-and-guardrails">
    Deep dive into regulatory compliance configuration.
  </Card>

  <Card title="Widget Customization" icon="palette" href="/guides/widgets/customization">
    Tailor your widget's look and feel to match your brand.
  </Card>

  <Card title="Adverse Event Monitoring" icon="triangle-exclamation" href="/guides/agents/adverse-event-monitoring">
    Set up pharmacovigilance and adverse event detection.
  </Card>

  <Card title="Batch Testing" icon="vial" href="/guides/testing/batch-testing">
    Validate your agent's responses before going live.
  </Card>

  <Card title="Team Management" icon="users" href="/guides/organization/team-management">
    Invite colleagues and manage roles within your organization.
  </Card>
</CardGroup>