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

# Quickstart

> Connect your voice agent to Tuner and get your first call analyzed and scored.

<Info>
  **Prerequisites:** an active Tuner account. [Sign up here](https://app.usetuner.ai/) if you haven't already.
</Info>

Creating an agent in Tuner is a guided flow. By the end you'll have a call in **Call Logs** with its transcript, per-turn timing, and eval results — not just proof that data arrived, but proof that Tuner is judging it.

**Estimated time:** 5 minutes

***

## Step 1: Choose Your Provider

Click **Add New Agent** in the sidebar. The first thing you pick is your provider, and that determines the rest of the flow.

<Tabs>
  <Tab title="Retell or Vapi">
    These platforms already hold your agent's configuration, so Tuner reads it from them.

    <Steps>
      <Step title="Add your platform API key">
        Paste in your Retell API key, or your Vapi **Private** key — not the public one. Tuner uses it to fetch your agents and to receive their calls.
      </Step>

      <Step title="Pick your agent from the list">
        Tuner loads your agents and pulls in each one's details. Select the one you want to monitor.
      </Step>
    </Steps>

    No webhook setup needed — Tuner configures that side for you in the background.
  </Tab>

  <Tab title="LiveKit, Pipecat, Dograh, or Custom API">
    Your agent runs on your own infrastructure, so you describe it to Tuner and then add the SDK in Step 3.

    <Steps>
      <Step title="Name the agent and set its direction">
        A display name, and **Inbound** or **Outbound** to match production.
      </Step>

      <Step title="Optionally paste your system prompt">
        Worth doing. Tuner treats it as the reference for what the agent is *supposed* to do — [MCP diagnosis](/docs/mcp/diagnose) works by comparing failing calls against it to find root causes. You can add it later in **Agent Settings**.
      </Step>
    </Steps>

    Tuner generates an **Agent Remote ID** for this agent. Step 3 gives you the code with it already filled in.
  </Tab>
</Tabs>

***

## Step 2: Pick a Template

Templates are what get you eval results on your very first call, rather than an unscored transcript. Each one pre-configures call outcomes, user intents, evals, red flags, alerts, and data-extraction fields for a common use case.

Pick the closest match — it doesn't have to be exact. A template is a starting point you shape, and everything it adds stays editable in **Agent Settings**.

<Accordion title="Available Templates">
  | Template                   | Direction | Use case                                                                                      |
  | -------------------------- | --------- | --------------------------------------------------------------------------------------------- |
  | Inbound Customer Support   | Inbound   | Questions, complaints, and issues the agent resolves or escalates.                            |
  | Appointment Booking        | Inbound   | Booking, rescheduling, cancelling, or checking availability.                                  |
  | Medical Receptionist       | Inbound   | Patient scheduling, prescription refill routing, insurance queries, and emergency escalation. |
  | General Receptionist       | Inbound   | Answering, routing callers, taking messages, and light scheduling.                            |
  | Food & Restaurant Ordering | Inbound   | Placing, modifying, or cancelling orders and answering menu questions.                        |
  | Real Estate                | Inbound   | Buyer, seller, and renter inquiries, listing questions, and viewing bookings.                 |
  | Payment Reminders          | Outbound  | Reminding a customer of a payment and confirming or arranging it.                             |
  | Lead Qualification         | Outbound  | Qualifying a prospect, gathering key details, and booking a next step.                        |
  | Recruitment / HR Screening | Outbound  | Screening candidates against job criteria before a recruiter takes over.                      |

  The library changes over time, so what you see may differ from this list.
</Accordion>

<Tip>
  Prefer to define everything yourself? **Configure via MCP** lets you describe your agent to Claude, Cursor, or ChatGPT and have the [Tuner MCP server](/docs/mcp/setup) generate the configuration. **Configure manually** starts from a blank slate.
</Tip>

***

## Step 3: Add the SDK

<Note>
  On Retell or Vapi? Skip to Step 4 — nothing to install.
</Note>

Tuner shows you a code snippet with your API key, workspace ID, and Agent Remote ID already filled in. Copy it into your agent, restart, and you're capturing.

That snippet is the minimal integration. Everything beyond it — cost calculation, recording URLs, disconnect reasons, agent versioning, SIP correlation for simulation — is on your integration guide:

<CardGroup cols={2}>
  <Card title="LiveKit" icon="puzzle-piece" href="/docs/integrations/livekit">
    Python and Node plugins for LiveKit Agents.
  </Card>

  <Card title="Pipecat" icon="puzzle-piece" href="/docs/integrations/pipecat">
    Observer SDK for Pipecat pipelines.
  </Card>

  <Card title="Dograh" icon="diagram-project" href="/docs/integrations/dograh">
    The Tuner node inside your Dograh workflow.
  </Card>

  <Card title="Custom Stack" icon="code" href="/docs/integrations/custom-stack/overview">
    Python observers for your own STT, LLM, and TTS, or the API directly.
  </Card>
</CardGroup>

***

## Step 4: Get Your First Call In

Two ways to finish, and the wizard offers both.

### Take a Real Call

Tuner is already listening. Call your agent as you normally would, have a short conversation, and hang up — the call appears in Tuner within seconds of ending.

### Or Run a Simulation

No call to make right now? Tuner can place one for you. The wizard has already configured the SIP connection, so the **Run simulation** button drops you straight into the simulation dialog — adjust the mix if you like, or just click **Run**.

Tuner dials your agent with an AI caller, holds a conversation, and scores the result against the same evals as production traffic. See [Call simulation](/docs/simulation/overview) for what you can configure.

***

## What You Should See

Open **Call Logs** and click into the call:

* **Transcript** — the conversation turn by turn, with tool calls inline
* **Eval results** — pass, fail, or a score for each eval your template added
* **Voice metrics** — per-turn latency, and where in the pipeline time went
* **Outcome and intent** — how Tuner classified the call

If the call is there but nothing is scored, the template didn't apply — check **Agent Settings → Evaluation Rules**. If the call never arrives, your integration guide's troubleshooting section covers the usual causes.

***

## What's Next?

<CardGroup cols={2}>
  <Card title="The Overview Dashboard" icon="chart-line" href="/docs/observability/overview">
    What the metrics, breakdowns, and red flag queue are telling you.
  </Card>

  <Card title="Call Simulation" icon="flask" href="/docs/simulation/overview">
    Test your agent before launch and after every change.
  </Card>

  <Card title="Monitoring Routine" icon="lightbulb" href="/docs/guides/agent-monitoring">
    What to check, and how often, once calls are flowing.
  </Card>

  <Card title="Custom Evals" icon="list-check" href="/docs/evaluation/custom-evals">
    Add checks the template didn't cover.
  </Card>
</CardGroup>