πPlayground: Testing your Text AI Agents
Last updated
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.

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
To send a message to your agent:
Type your message into the text input box
Press the send button, or
Press Enter on your keyboard
Each message is sent to the agent exactly as a real user would send it.
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 donβt see a behavior change, make sure the agent has been saved.
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.
The Playground is commonly used to:
Verify prompt changes
Test language behavior
Validate tone and response structure
Debug unexpected answers before publishing
Forgetting to reset the conversation when testing new behavior.
If prior messages remain in the conversation, they can influence the agentβs responses.
Last updated