# Playground: Testing your Text AI Agents

#### What the Playground is

The Playground is a built-in testing environment inside each text agent.

It allows you to **chat with your most recently saved version of the agent** so you can test how it responds before using it live.

<figure><img src="/files/fQt4EsLpwoT1zGId6k8z" alt=""><figcaption></figcaption></figure>

***

#### What you can do in the Playground

Inside the Playground, you can:

* Send messages to your agent
* Test responses based on the current prompt and settings
* Validate changes after editing the prompt
* Experiment safely without affecting live users

***

#### How to send a message

To send a message to your agent:

1. Type your message into the text input box
2. Press the send button, or
3. Press **Enter** on your keyboard

Each message is sent to the agent exactly as a real user would send it.

***

#### Important behavior to understand

The Playground:

* Uses the **latest saved version** of your agent
* Does **not** update in real time while you are editing the prompt
* Requires you to save changes before testing them

If you don’t see a behavior change, make sure the agent has been saved.

***

#### Resetting the conversation

The Playground keeps conversation history so the agent can respond with context.

To start a fresh test:

* Click the **Reset** button in the top-right corner of the Playground

This clears the conversation history and lets you test the agent from scratch.

***

#### Common use cases

The Playground is commonly used to:

* Verify prompt changes
* Test language behavior
* Validate tone and response structure
* Debug unexpected answers before publishing

***

#### Common mistake

Forgetting to reset the conversation when testing new behavior.

If prior messages remain in the conversation, they can influence the agent’s responses.


---

# Agent Instructions: 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:

```
GET https://docs.dapta.ai/ai-text-agents/setting-up-your-text-agent/playground-testing-your-text-ai-agents.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.