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

# Quickstart

> Create your first AI agent and have a conversation with it in under ten minutes

This guide takes you from a fresh account to a working agent you can actually talk to. No phone number or API key needed — you'll test the agent right in your browser first.

<Steps>
  <Step title="Sign up and log in">
    Create an account at [app.osvi.ai](https://app.osvi.ai) using your email or Google. If your organisation already uses OSVI, ask an admin to [invite you](/platform/team-management) instead so you join the existing workspace.
  </Step>

  <Step title="Create an agent">
    Go to **Agents** and click **Create Agent**. You'll choose:

    * **Agent mode** — *Voice Agent* (phone and web calls) or *Chat Agent* (text conversations). Pick **Voice Agent** for this guide.
    * **Prompt structure** — *Single Prompt* (one system prompt drives the whole conversation) or *Multi Prompt* (a graph of prompts for branching flows). Start with **Single Prompt**.
    * A **name** and optional description.

    See [Agents](/platform/agents) for everything an agent can do.
  </Step>

  <Step title="Write the prompt">
    On the agent's **Agent** tab, set two things:

    * **First message** — what the agent says when the call connects. Leave it empty to have the agent wait for the other person to speak first.
    * **System prompt** — the agent's identity, goal, rules, and tone.

    A minimal example:

    ```
    You are Priya, a friendly assistant for Acme Clinic.
    Your goal is to confirm the caller's upcoming appointment.
    Keep sentences short. If asked anything unrelated, politely steer back.
    Once the appointment is confirmed, thank them and end the call.
    ```

    The [prompt writing guide](/platform/prompt-writing) covers this in depth — it's the single highest-leverage thing you can read.
  </Step>

  <Step title="Pick a voice and language">
    On the **Advanced** tab, choose the agent's **Text-to-Speech** voice (use the preview button to listen before committing) and the **Speech-to-Text** language. OSVI supports English plus major Indian languages including Hindi, Tamil, Telugu, Kannada, Malayalam, Bengali, Gujarati, Marathi, and Punjabi. Browse the full catalogue under [Voices](/platform/voices).
  </Step>

  <Step title="Test it in the playground">
    Use the test panel on the agent page to start a **web call** straight from your browser — no phone involved. You'll see a live transcript as you talk. Switch the test mode to **chat** to try the same agent over text.

    Iterate here: tweak the prompt, test again, repeat. This loop is much faster than real phone calls.
  </Step>

  <Step title="Go live">
    When the agent behaves the way you want, pick a path:

    <CardGroup cols={2}>
      <Card title="Receive calls" icon="phone-arrow-down-left" href="/platform/phone-numbers">
        Attach a phone number so the agent answers inbound calls.
      </Card>

      <Card title="Run a campaign" icon="list-check" href="/platform/campaigns">
        Upload a CSV of contacts and let the agent work through the list.
      </Card>

      <Card title="Trigger calls via API" icon="code" href="/api-reference/endpoint/call_v1">
        `POST /v1/call` with a phone number and your agent's UUID.
      </Card>

      <Card title="Get results back" icon="webhook" href="/platform/call-analysis">
        Set up post-call analysis and webhooks to receive summaries and extracted data.
      </Card>
    </CardGroup>
  </Step>
</Steps>

<Tip>
  Before going live, run through the [prompt testing checklist](/platform/prompt-writing#prompt-testing-checklist): wrong person answers, off-topic questions, interruptions, and the "I want a human" case.
</Tip>