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

# Testing in the Playground

> Run your deployed workflow interactively and iterate.

The Playground is where you test a workflow with real inputs and see exactly how it behaves. It's the fastest way to iterate.

<Frame caption="The Playground — the thread list on the left, the conversation in the center, and the input box at the bottom.">
  <img src="https://mintcdn.com/aiplanet/Jy4Vl1U9sSF_9LZH/images/playground.png?fit=max&auto=format&n=Jy4Vl1U9sSF_9LZH&q=85&s=cb952e2db731f895f06ef70c7c0c3749" alt="The Playground" width="1920" height="1080" data-path="images/playground.png" />
</Frame>

## Opening the Playground

The Playground runs your workflow's **active deployment** — so you need to [deploy the workflow](/building-workflows/deploying) before you can test it. Once it's deployed, open the Playground from the builder. You'll see the workflow's name and status in the header.

## Threads

The left sidebar lists your **threads** — each thread is a separate conversation session. Use threads to keep different test scenarios apart.

* **New conversation** — start a fresh session with no prior context.
* **Rename** — give a thread a meaningful name.
* **Pin** — keep an important thread at the top.

## Running your workflow

How you provide input depends on your workflow:

* **Chat-style workflows** — type a message in the input field at the bottom and send it. Use Enter to send, Shift+Enter for a new line.
* **Form-style workflows** — fill in the input parameters in the main area and submit.

The agent's response streams back in real time, so you see output as it's generated. A typing indicator shows while the agent is working.

## Iterating

The Playground is built for fast iteration:

<Steps>
  <Step title="Run">
    Send an input and review the response.
  </Step>

  <Step title="Adjust">
    Go back to the builder, tweak the agent's configuration, save, and deploy again.
  </Step>

  <Step title="Run again">
    Return to the Playground and try the same input. Compare the results.
  </Step>
</Steps>

<Tip>
  Start a new thread when you change the workflow significantly — it gives you a clean comparison without leftover context from earlier runs.
</Tip>

## Reviewing what happened

Every run in the Playground is also recorded in [Tracing](/running-monitoring/tracing), where you can inspect each node's input and output step by step. This is invaluable when a workflow doesn't behave the way you expect.

## Next steps

<Card title="Deploy your workflow" icon="rocket" href="/building-workflows/deploying">
  Once it works the way you want, publish it.
</Card>