Playground

After you define your app and configure one or more tasks, test your settings before publishing. App owners and developers can chat with the app in real-time to test recognition, performance, and flow as if it were a live session.

​

Access

Go to Automation AI > Evaluation > Playground. Alternatively, select the Test icon in the top right corner of the Platform.

​

Testing an App

When you first open the Playground, select whether to proceed with Voice or Chat. This page describes the chat experience. The Debug Logs and Chat windows open side-by-side in the Playground display area. In the Message section, enter text to begin interacting and testing your app. Dialog GPT processes the task, verifies authentication, prompts for required task fields, and executes the task after all required information is collected. Try different variations of user prompts. If the app returns unexpected results, consider adding or modifying synonyms for your tasks and task field names.

​

Conversation Status

When a conversation is active and the developer is working in the Playground, conversation status can only be changed from within the Playground module. The system always matches the Test status with the Playground status, but allows updates only when the developer is outside the Playground.

​

Debug Window

The Debug window has two tabs:

​

Debug Log

Debug Log provides the sequential progression of a dialog task along with captured context and session variables. It’s a chat-like interface, grouped by user inputs and app responses for easier conversation flow tracing. It offers improved navigation and contextual information at a glance, enhancing log readability and streamlining the debugging process.

​

Session Context and Variables

The Session Context & Variables tab dynamically displays the populated Context object and session variables updated at each processed component in Dialog Builder. For more information about the parameters, see Using Session and Context Variables in Tasks and Context Object.