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

# What is the Playground

> The Playground is the no-code home for a playbook: describe an agent, get a working playbook, test it by voice, harden it, and ship it - all on one screen. What you hear here is what a caller hears.

## The no-code home for your playbook

The **Playground** collapses a three-day authoring job into about thirty minutes.
Describe an agent, get a working [playbook](/playbook/what-is-a-playbook), test it
by voice, harden it, and take it live - **without leaving one screen.**

It runs the same stack production does. The playbook is authored with
**SuperDialog**; the browser voice call is served by the same `AgentRunner` that
serves a real phone call. **What you hear in the Playground is what a caller
hears.**

<a className="pg-cta" href="https://superdialog.unpod.ai/playground" target="_blank" rel="noreferrer">
  <span className="pg-cta__icon">▶</span>

  <span className="pg-cta__body">
    <span className="pg-cta__title">Open the Playground</span>
    <span className="pg-cta__desc">Launch it at <code>superdialog.unpod.ai/playground</code>, describe an agent, and start talking to it in your browser. A guest trial lets you build before you sign up.</span>
  </span>

  <span className="pg-cta__arrow">→</span>
</a>

## One screen, three surfaces

<Steps>
  <Step title="Agent chat (left, always present)">
    You describe the agent in plain English ("confirm appointments, fall back to
    5pm"). The builder agent authors and edits the playbook for you. Attach a
    PDF or paste a URL and it reads from those too.
  </Step>

  <Step title="Editor tab (right)">
    The live playbook YAML. Every change the chat makes lands here; you can also
    edit it by hand. Validation runs as you type.
  </Step>

  <Step title="Preview tab (right)">
    The voice test. Press to talk, speak like a caller, and watch the transcript,
    the current checkpoint, and the metrics update live.
  </Step>
</Steps>

<Frame caption="One screen - the builder chat on the right, Editor/Preview tabs up top, the voice profile and model pickers, and the Press-to-talk orb in the center">
  <img src="https://mintcdn.com/unpodai/djZvOeKNVOnMwvUj/images/playbook/playground-pipeline.png?fit=max&auto=format&n=djZvOeKNVOnMwvUj&q=85&s=def42a31a52632d2e84b8e8b8f85facc" alt="Preview tab showing the voice pipeline: User speaks into STT, a USER_TURN arrow into DialogMachine.turn() under 'SuperDialog - your flow', an AGENT_TURN arrow into TTS, and 'Caller hears' - with a 'Connected - speak to run a turn through the pipeline' status." width="1919" height="960" data-path="images/playbook/playground-pipeline.png" />
</Frame>

## The end-to-end journey

<CardGroup cols={2}>
  <Card title="1. Build an agent playbook" icon="wand-sparkles" href="/playbook/build-an-agent">
    Describe it in chat or start from a document; the agent writes the playbook.
  </Card>

  <Card title="2. Test by voice" icon="mic" href="/playbook/test-by-voice">
    Press to talk in the browser and confirm it behaves like a real call.
  </Card>

  <Card title="3. Optimize" icon="gauge" href="/playbook/optimize">
    Run simulated personas, score goal completion, and harden the weak spots.
  </Card>

  <Card title="4. Publish & share" icon="share" href="/playbook/publish-and-share">
    Set visibility, share by link, clone, then deploy - as a voice agent on a
    number, or as an API endpoint.
  </Card>
</CardGroup>

## Reuse an existing agent

You do not have to start from a blank page.

<Card title="Browse the playbook gallery" icon="library-big" href="/playbook/library">
  The **Public** tab lets you open and clone any agent others published; the
  **My Playbook** tab holds your own drafts.
</Card>

## Who this section is for

| You are...                                                         | Start here                                                                      |
| ------------------------------------------------------------------ | ------------------------------------------------------------------------------- |
| **A builder** (non-technical) who wants a working voice agent fast | [Build an agent playbook](/playbook/build-an-agent) - operate the Playground UI |
| **A developer** who wants to call the agent from code              | [Endpoint API](/playbook/api) - the OpenAI-compatible endpoint                  |
| **Curious how the brain works** underneath                         | [SuperDialog](/superdialog/introduction) - the engine behind every playbook     |

<Note>
  The Playground is where you *build and prove* an agent. To put it in front of
  real callers, deploy the published agent as a **Voice Agent** on a
  [number](/speech-stack/numbers) (it wires a [Speech Pipe](/speech-stack/pipes)
  for you) - covered in [Publish & share](/playbook/publish-and-share).
</Note>