This is a beta feature. Please do let us know if you encounter any issues. We’ll continuously improve it.
A spreadsheet-style editor for running prompts and models across multiple test cases. Import testsets to easily test, evaluate, and optimize your LLM outputs.

​
Guide

1

Create a prompt

You should first create a new prompt on the Prompts page to use in the lab.

2

Create a testset (optional)

If you want to run prompts with various dynamic test cases, you can create a new testset on the Testsets page.

3

Import prompt and testset

Now, choose the prompt and the versions you want to test. You can also import a testset if you have one.

4

Evaluate prompts

Variables in prompts will be detected and displayed in the lab. You can edit the values and run the prompts to evaluate the outputs.

​
What’s next?

After you have evaluated the prompts, you can save the results to the Logs page for further analysis. If you’re satisfied with the results, you can deploy the prompt to your application. Check out the Prompts page for more information.

LLM playgroundTestsets