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

# Get started with Pome

> Test your AI agent against digital twins of GitHub, Slack, Stripe, Gmail, and Linear, and get a scored report for every run.

Pome is simulation testing infrastructure for AI agents. Stateful **digital twins**
answer the same REST and MCP calls as production systems, so you can evaluate
agent behavior end to end without touching real users, data, or APIs.

A scored run needs three inputs: a seeded world state, a task prompt, and the
twins the agent can call. Vary those, and Pome surfaces the edge cases unit
tests miss. Live runs and scores land on [app.pome.sh](https://app.pome.sh).

## Quickstarts

<CardGroup cols={3}>
  <Card title="Log your first scored run" icon="rocket" href="/quickstart/claude-code">
    Paste one prompt into Claude Code and get a failing score you can fix.
  </Card>

  <Card title="Connect your agent" icon="package-plus" href="/existing-agent">
    Point Pome at your repo — one paste-prompt writes `pome.json` and registers it.
  </Card>

  <Card title="Drive it from MCP" icon="plug" href="/docs/mcp/index">
    Author tasks, launch runs, and read reports by tool call from your coach.
  </Card>
</CardGroup>

## Workflow

<CardGroup cols={3}>
  <Card title="How Pome works" icon="workflow" href="/docs/how-pome-works">
    What happens in a run, from seed state to scored report.
  </Card>

  <Card title="Which surface?" icon="layout-grid" href="/docs/which-surface">
    CLI, skill, MCP, dashboard — same loop, pick where you drive it.
  </Card>

  <Card title="Dashboard" icon="gauge" href="/docs/dashboard">
    Agents, twin sessions, traces, and judge handoffs at app.pome.sh.
  </Card>
</CardGroup>