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

# Quickstart

> Connect your agent, describe what it should do, and run your first test in about 5 minutes.

## Overview

Skrut runs grounded, multi-turn conversations against your live agent and grades every turn — so you get a readiness score you can defend, not a demo you hope holds up.

## Steps

<Steps>
  <Step title="Add your agent">
    Connect a voice agent via LiveKit, or a chat agent via your HTTP endpoint.
    Skrut needs a URL it can send messages to and receive replies from.
  </Step>

  <Step title="Describe the expected outcome">
    Tell Skrut what your agent is supposed to do — in plain language.
    It generates grounded test scenarios from your agent's own knowledge base.
  </Step>

  <Step title="Run and get your readiness report">
    Hit **Run**. Skrut executes every scenario, grades each turn, and produces
    a readiness report you can share with your team or re-run every release.
  </Step>
</Steps>

## What's next

* [Agents](/concepts/agents) — how to connect voice and chat agents
* [Tests](/concepts/tests) — how scenarios are generated and run
* [Reports](/concepts/reports) — reading your readiness score