> ## 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.

# Welcome to Tuner

> Simulation, analytics, and observability for voice AI agents — from pre-launch testing to production monitoring.

Tuner is where voice agents get tested, watched, and improved. You send it your calls; it scores them against criteria you define, surfaces the ones that went wrong, and places test calls against your agent so you find failures before your customers do.

## What problem it solves

Running voice agents in production without the right tools means:

* **Scattered logs** — parsing endless unstructured output to find one issue
* **Manual call reviews** — listening to calls by hand to judge quality
* **Manual self-testing** — calling your own agent over and over, never sure you covered the edge cases
* **No real-time visibility** — hearing about problems from angry users instead of your own systems
* **Guesswork** — changing your agent without knowing whether it got better

## The loop

Tuner is built around a continuous loop. You don't just monitor production and react — you simulate, ship, observe, fix, and simulate again.

<Steps>
  <Step title="Simulate">
    Stress-test your agent with [Call Simulation](/docs/simulation/overview) before launch and after every change. The same Evals that score production calls score every simulated call.
  </Step>

  <Step title="Observe">
    Every call arrives as structured data — transcript, per-turn timing, tool calls, eval results. Dig into individual calls in **Call Logs** to find what went wrong.
  </Step>

  <Step title="Monitor">
    Track performance in real time on the [Overview dashboard](/docs/observability/overview), with [real-time alerts](/docs/observability/alerts) for the things you can't afford to miss.
  </Step>

  <Step title="Optimize">
    Fix the agent, confirm the fix against production data, and re-simulate to catch regressions. [Diagnose with MCP](/docs/mcp/diagnose) finds root causes across every affected call at once.
  </Step>
</Steps>

<img src="https://mintcdn.com/tuner/tFS1DAQs-KSnIeEa/images/overview_dashboard.png?fit=max&auto=format&n=tFS1DAQs-KSnIeEa&q=85&s=7a15b794bd6053d8b35899b237260f49" alt="Overview Dashboard" width="1024" height="611" data-path="images/overview_dashboard.png" />

## Three ways to connect

<CardGroup cols={3}>
  <Card title="No-code platforms" icon="plug">
    Retell, Vapi, Dograh. Add a key, create an agent, done. Calls sync automatically.

    **\~5 minutes**
  </Card>

  <Card title="SDKs" icon="cubes">
    LiveKit, Pipecat, or your own Python stack. The SDK captures per-turn timing and latency your platform never exposes.

    **\~2–10 minutes**
  </Card>

  <Card title="Direct API" icon="code">
    Any language. You build the call timeline and POST it after the call ends.

    **\~30 minutes**
  </Card>
</CardGroup>

SDK-level capture is the difference between knowing a call went badly and knowing which pipeline stage was slow. Where a platform hands you a finished transcript, the SDKs record what happened turn by turn — end-of-utterance delay, time to first token, time to first audio byte.

## Vocabulary

The six things Tuner is built from. Each links to the page that covers it properly.

| Concept                | What it is                                                                  | Learn more                                               |
| ---------------------- | --------------------------------------------------------------------------- | -------------------------------------------------------- |
| **Evals & guardrails** | Criteria that judge a call; rules that define what "bad" looks like         | [Evals & guardrails](/docs/evaluation/overview)          |
| **Metrics**            | Quantitative measurements computed on every call                            | [Pre-defined metrics](/docs/evaluation/predefined-evals) |
| **Red flags**          | Tags applied to a call when a rule you define matches                       | [Red flags and labels](/docs/evaluation/red-flags)       |
| **Alerts**             | Notifications sent when something you care about happens                    | [Real-time alerts](/docs/observability/alerts)           |
| **Call simulation**    | Test calls Tuner places against your agent, scored by your production Evals | [Call simulation](/docs/simulation/overview)             |
| **PII redaction**      | Sensitive caller data removed from transcripts before storage               | [PII redaction](/docs/observability/pii-redaction)       |

Every other term used across Tuner is in the [Glossary](/docs/resources/glossary).

## Ready to start?

<Card title="Quickstart" icon="rocket" href="/docs/getting-started/quickstart" horizontal>
  Connect an agent and get your first call analyzed — about 5 minutes.
</Card>