I have a very basic eval to test this feature out, but when started it is stuck for more than an hour as

queued

Anyone solved this issue please?

Hi Spoody, To get started with evaluating your AI assistant using the Vapi platform, you can follow these concise steps: 1. **Create an Evaluation**: - Define a mock conversation with user and assistant messages. - Specify expected behavior using exact match, regex patterns, or AI-powered judging. Here is a quick [guide](https://docs.vapi.ai/observability/evals-quickstart) for setting up evaluations. 2. **Run your Evaluation**: - Execute the evaluation against your assistant to validate its responses. - Use the results to debug and improve your assistant's performance. 3. **Manage Evaluations**: - List, update, or delete evaluations to keep your testing organized. - View run history to analyze past evaluation results. For more detailed instructions on each step, refer to the [Create Eval documentation](https://docs.vapi.ai/api-reference/eval/eval-controller-create). This will give you detailed API specifications and sample code to help implement your evaluations effectively.

I did all that, the eval run's status is stuck at

queued

Hi Spoody, Thanks for the update! Could you please share a screenshot of how your eval is currently configured? This will help us identify what might be causing it to stay in the queued state. Once we have that, we’ll take a closer look and get this resolved for you. Best, The Vapi Team

Hello, Here is the id of the Eval:

39a67fc0-187f-4247-9d8b-cab456482476

Thanks for getting back to us and updating us We’ll share an update as soon as more information becomes available. We appreciate your understanding and patience as we continue our investigation.

REOPEN

Thanks for reopening this! We recently released an updated and improved Test Suites system. Could you please try running your evaluation again using the new Test Suites flow and let us know if you still run into the run getting stuck in “queued”?