Using the AI agents in the evaluation playground

Once the agents are set up, you can test them in the playground (on the same page where you set up the agents). You can provide a query, expected response, and a response to evaluate to the agents for evaluations. You will see the label and reasons from the agents per round as well as the final label and reason from the meta agent.

There is also an option to provide feedback to the agents, which is useful to make them better over time.