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

# Playground

> Try actions in natural language before wiring code.

The [AI Playground](https://app.stackone.com/playground) runs any action from your [linked accounts](/gateway/concepts/linked-accounts) using natural language — no code, no setup. Use it to confirm an account works and see which actions are available before building.

<Steps>
  <Step title="Select accounts">
    Pick one or more linked accounts from the dropdown.
  </Step>

  <Step title="Configure actions (optional)">
    Expand **Actions** to enable or disable specific actions. Selection locks once the conversation starts.
  </Step>

  <Step title="Chat">
    Try a prompt like the ones below — each tool call and its response appear in the chat log.

    ```text theme={null}
    What tools can I use?
    ```

    ```text theme={null}
    List the first 10 employees
    ```
  </Step>
</Steps>

<Tip>
  Start with "What tools can I use?" to see the available actions for your selected accounts.
</Tip>

## Model selection

Click the model selector at the bottom right to switch models:

| Model                 | Recommendation                                                                         |
| --------------------- | -------------------------------------------------------------------------------------- |
| **Claude Haiku 4.5**  | **Recommended.** Best balance of speed and tool calling accuracy. Selected by default. |
| **Claude Sonnet 4.6** | Use for complex multi-step reasoning tasks.                                            |
| **GPT-5.5**           | OpenAI alternative for comparison testing.                                             |
| **GPT-5.4 Mini**      | Lighter, faster OpenAI model.                                                          |
| **GPT-5.4 Nano**      | Smallest OpenAI model for low-cost runs.                                               |

<Info>
  **StackOne Tool Calling Model (Beta)**

  StackOne is fine-tuning a specialized model optimized for SaaS tool calling, at lower cost than leading models. Contact [ai@stackone.com](mailto:ai@stackone.com) to join the beta.
</Info>

## Defender

The configuration sidebar has a **StackOne Defender** toggle that scans tool call responses for prompt injection before the model sees them. It's a per-request override: it applies to the Playground session only, whatever your project-level setting is, and defaults to **on**. Use it to see how your agent behaves with Defender on or off without changing your project configuration.

With Defender enabled, every tool call in the chat log carries a risk icon next to its status badge:

| Icon                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | Meaning                                                                                                                        |
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ |
| <img src="https://mintcdn.com/stackone-60/D_ktR54Q8ZzCnqcJ/images/defender/defender_green.svg?fit=max&auto=format&n=D_ktR54Q8ZzCnqcJ&q=85&s=fd358164c4ca655ee031224bef467f8c" alt="Green low-risk Defender icon" width="20" height="20" style={{ display: "inline-block", verticalAlign: "middle", margin: 0 }} data-path="images/defender/defender_green.svg" />    | Low risk — response passed Defender's checks                                                                                   |
| <img src="https://mintcdn.com/stackone-60/D_ktR54Q8ZzCnqcJ/images/defender/defender_amber.svg?fit=max&auto=format&n=D_ktR54Q8ZzCnqcJ&q=85&s=3a87b795cc595ab0c25fcf9bb8090f07" alt="Amber medium-risk Defender icon" width="20" height="20" style={{ display: "inline-block", verticalAlign: "middle", margin: 0 }} data-path="images/defender/defender_amber.svg" /> | Medium risk — flagged but not blocked                                                                                          |
| <img src="https://mintcdn.com/stackone-60/D_ktR54Q8ZzCnqcJ/images/defender/defender_red.svg?fit=max&auto=format&n=D_ktR54Q8ZzCnqcJ&q=85&s=de5d7978a11dfe5bf2ab104591f33713" alt="Red high-risk Defender icon" width="20" height="20" style={{ display: "inline-block", verticalAlign: "middle", margin: 0 }} data-path="images/defender/defender_red.svg" />                     | High or critical risk — blocked from reaching the model when **Block High Risk Content** is on in [Defender](/secure/defender) |
| *no icon*                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             | Defender did not scan this response (toggle off, size limit exceeded, or no Defender metadata)                                 |

Hover any icon for the precise risk level. When a call is blocked, it shows a `Blocked` status in the chat log and the model receives an error in place of the tool response, which the agent can retry, skip, or surface like any other tool error.

<Card title="Defender" icon="shield-halved" href="/secure/defender">
  Detection modes, thresholds, large-response behavior, and SDK overrides.
</Card>

## Common errors

<AccordionGroup>
  <Accordion title="No accounts visible">
    Check the account is linked on the [Accounts page](https://app.stackone.com/accounts), and that actions are enabled on its [connector profile](/secure/scoping-connectors).
  </Accordion>

  <Accordion title="Slow responses">
    Switch to Claude Haiku (the fastest option) or reduce the number of selected accounts.
  </Accordion>

  <Accordion title="Tool not found">
    Verify the action is enabled on the [connector profile](/secure/scoping-connectors), then check [Request Logs](/connect/troubleshooting) for the failing call.
  </Accordion>
</AccordionGroup>

## Connect your own client

The **Use Setup** button shows the MCP config for your accounts (endpoint, authentication header, `x-account-id`) so you can move from testing to your own agent. See [MCP](/embed/call-actions/mcp).

<Note>
  The Playground is a testing tool, not a production agent. Build your agent with [MCP](/embed/call-actions/mcp) or the [Agent SDK](/embed/call-actions/agent-sdk).
</Note>