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

# Quickstart

> Create your first assistant and test it with a web call

This guide takes you from an empty account to a live conversation with your own AI assistant — no phone number required for the first test.

## 1. Create an assistant

<Steps>
  <Step title="Open Assistants and click 'New assistant'">
    The **Create assistant** modal opens. Enter a name your team will recognize, e.g. `Reception EN`.
  </Step>

  <Step title="Choose the agent type">
    * **Single prompt** — free-form conversations from one system prompt (best for most first assistants).
    * **Conversational flow** — visual flow builder for branches, data collection, and transfers.
  </Step>

  <Step title="Pick a template (or build from scratch)">
    Use **Build from scratch**, or apply a catalog template (filter by theme). Templates copy into the system prompt and optional first message — they are not live-linked.
  </Step>

  <Step title="Edit greeting and instructions">
    In the editor:

    * **Prompt mode:** greeting + system prompt on the canvas. Use **Choose template** anytime.
    * **Flow mode:** open the flow builder; the base instructions live under Settings → General → **Advanced prompt** (also collapsed on the canvas).

    A solid starting prompt:

    ```text theme={null}
    You are Anna, the friendly phone assistant of Example GmbH.
    You answer questions about opening hours, services, and pricing.
    Keep answers short and conversational — you are on a phone call.
    If the caller wants an appointment, collect their name and phone
    number and confirm you will call back. Never invent information.
    ```
  </Step>

  <Step title="Pick a voice and models — or keep the defaults">
    The defaults (a low-latency pipeline with a recommended voice) work well out of the box. You can browse the [voice library](/assistants/models-and-voices) later and preview voices before switching.
  </Step>

  <Step title="Save">
    Your assistant is now ready to take calls.
  </Step>
</Steps>

## 2. Test it in the browser

Every assistant can be tested directly from the editor — same engine, same models, no telephony involved. Click the **Test** button in the editor header and pick a channel:

* **Call** — a live voice call in the browser:
  1. Allow microphone access.
  2. Talk to your assistant. Interrupt it mid-sentence — it should stop and listen.
  3. End the call, then open **Calls** to review the transcript.
* **Chat** — a text-only session with the same prompt, flow, tools and knowledge base. Perfect for quickly iterating on prompts without speaking out loud.

<Tip>
  Iterate on the prompt between test calls. Short prompts with concrete rules ("keep answers under two sentences", "always confirm the phone number by reading it back") beat long essays.
</Tip>

## 3. Put it on a phone number

When the web call sounds right:

* **Buy a number** in [Phone numbers](/telephony/phone-numbers) and assign the assistant to it — inbound calls are answered immediately.
* Or **connect your own SIP trunk** ([BYO SIP](/telephony/sip-trunks)) to use existing numbers.
* For outbound, start a single test call from the assistant page or set up a [campaign](/campaigns/overview).

## Next steps

<CardGroup cols={2}>
  <Card title="System prompt vs. flow builder" href="/assistants/overview" icon="pen">
    When a single prompt is enough — and when to switch to a visual flow.
  </Card>

  <Card title="Conversation quality" href="/assistants/conversation-quality" icon="waveform-lines">
    Background audio, interruption handling, filler phrases, guardrails.
  </Card>

  <Card title="Knowledge base" href="/assistants/knowledge-base" icon="book">
    Let the assistant answer from your documents.
  </Card>

  <Card title="Engine modes" href="/assistants/engine-modes" icon="gears">
    Pipeline, realtime, and half-cascade explained.
  </Card>
</CardGroup>