# Testing the agent

> Now it's time to test your agent and see how you can improve it.

Now it's time to test your agent and see how you can improve it.

1. Navigate to the toolbar above the Studio Web designer.
2. Select the arrow next to the debugging environment, then select **Debug configuration**.
3. In the **Debug configuration** window, confirm the resources used in the solution and the sample input.
4. Select **Save and Run**.
5. Use the test output to refine the agent design.

After the first debug run, an evaluation automatically runs using the debug data and is added to the default evaluation set.

## Evaluating the agent

Next, go to the **Evaluation sets** and **Evaluators** panels to review and measure your agent.

1. In the **Evaluation sets** panel, rename the default evaluation set and add test cases with expected outcomes.
2. In the **Evaluators** panel, add evaluators to validate the agent output.

Each evaluation links a known input with an assertion about the output.

For details, refer to [Evaluations](https://docs.uipath.com/agents/automation-suite/2.2510/user-guide/agent-evaluations).

## Using Autopilot to improve your agent 

Select **Open Autopilot** from the right-side panel to receive suggestions on improving prompts, tools, and other components. For details, refer to [Autopilot for agents](about-autopilot-for-agents.md).