> For the complete documentation index, see [llms.txt](https://distance.gitbook.io/distance/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://distance.gitbook.io/distance/getting-started/playground.md).

# Playground

### **Introduction**

The **Playground** lets your team interact with your **AI Chat** agent in real time, simulate customer conversations, and review responses to ensure tone, knowledge, and behavior match your business standards. It is intended for testing and validation only and is not connected to live customer channels.

<div data-with-frame="true"><figure><img src="/files/OPrC4prnX0CQ87NoXaos" alt=""><figcaption></figcaption></figure></div>

This can be accessed by clicking it on the left sidebar to open the chat interface and start testing your AI Chat agents.

***

### **Why use the Playground**

**Preview agent behavior**. Test how the AI responds across different customer scenarios.

**Ensure consistency**. Verify that tone, script, and response style match your business standards.

**Test before going live**. Validate workflows, greetings, and conversation flows without affecting real customers.

**Troubleshoot and refine**. Identify knowledge gaps, improve responses, and update scripts before deployment.

***

### **Selecting an agent to test**

At the top-left of the **Playground**, click the dropdown to choose which **AI Chat** agent you want to test.

<div data-with-frame="true"><figure><img src="/files/6FjKoNsDO4sTbC4KG93B" alt=""><figcaption></figcaption></figure></div>

This allows you to switch between different agents without leaving the **Playground**.

***

### **Testing conversations**

Send test messages in the **Chat with your agent** section to evaluate how the agent responds in real time and validate its behavior across different scenarios.

<div data-with-frame="true"><figure><img src="/files/uXJ1KKhefBW6QoWxresN" alt=""><figcaption></figcaption></figure></div>

You can use general questions, edge cases, or service-specific inquiries to review responses and identify areas that may need adjustment.

***

### **Restarting a chat**

To start fresh, click **Restart chat** in the upper-right corner of the **Playground**.

<div data-with-frame="true"><figure><img src="/files/VlsRn9zyGuUZLTqsZ4Hq" alt=""><figcaption></figcaption></figure></div>

This clears the current conversation and resets the context, allowing you to test a new scenario from the beginning.

***

### **Playground side panel**

On the right side of the Playground, there is an information panel with four tabs: [**Editor**](#editor-tab), [**Agent overview**](#agent-overview-tab), **Ticket info**, and **Questions**.

#### **Editor tab**

The **Editor** tab uses Copilot AI to help improve your agent’s [**Knowledge base**](/distance/getting-started/knowledge-base.md) while testing conversations.

<div data-with-frame="true"><figure><img src="/files/GST86k5A3q4yeGdxxTHq" alt=""><figcaption></figcaption></figure></div>

If the agent responds with incorrect information or does not know how to answer a question, you can use the **Editor** to suggest updates directly from the **Playground**. This can include:

* Updating information in the [**Business overview**](/distance/getting-started/knowledge-base/business-information.md#business-overview)
* Modifying existing [**Custom questions**](/distance/getting-started/knowledge-base/custom-questions.md)
* Adding new [**Custom questions**](/distance/getting-started/knowledge-base/custom-questions.md)

Suggested changes are generated for review before they are applied. The **Editor** can only update content within the **Business overview** and **Custom questions** sections of the **Knowledge Base**.

A **Restart chat** button is available below the **Editor** text box to clear the current Copilot AI conversation and start a new editing session.

<div data-with-frame="true"><figure><img src="/files/anVBHjACvNyE0hUtjuIA" alt=""><figcaption></figcaption></figure></div>

#### **Agent overview tab**

The Agent overview tab displays configuration details for the active test agent, including name, last updated time, tone, response length, and specialization.

<div data-with-frame="true"><figure><img src="/files/DnWfnHwBrZb2BisWi9Ke" alt=""><figcaption></figcaption></figure></div>

You can click View agent settings to open the Agents page and make adjustments.

#### **Ticket info tab**

The **Ticket info** tab shows simulated contact and ticket data based on the current test conversation.

This section is for preview purposes only. The Playground is not connected to **Contacts**, **Tickets**, or **Inbox**, and it does not create or update real records. Even if you use existing contact details, no data will appear in the Inbox and no ticket will be generated.

<div data-with-frame="true"><figure><img src="/files/HU39El7StuH28KiUUxi2" alt=""><figcaption></figcaption></figure></div>

If a ticket would normally be created based on the conversation, this tab shows a preview of how it would appear, including contact details and a simulated ticket view with title, type, status, summary, and related conversation data.

#### **Questions tab**

The **Questions** tab provides pre-written prompts that you can click to send into the chat.

<div data-with-frame="true"><figure><img src="/files/CzjbxabbY9YPsmEtMaYC" alt=""><figcaption></figcaption></figure></div>

These help you quickly test scenarios such as general inquiries, pricing questions, scheduling requests, or custom business-specific cases.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://distance.gitbook.io/distance/getting-started/playground.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.