### Answer The available documentation doesn't explicitly state whether simulation testing runs against the published version or the current draft of an agent. However, based on the version comparison documentation, you can "make changes and test your agent safely—without affecting your live production calls" and then use the "Deployment" button to save a version. [(1) ]() This suggests that testing (including simulation) operates on the draft/current working version rather than the published version, since the purpose is to validate changes before publishing. For definitive confirmation, I'd recommend: 1. Checking the [simulation testing docs]() [(2) ]() 2. Reaching out to Retell AI support through [Contact Sales]() or [GitHub]() Would you like me to provide a general answer based on typical testing workflows, or do you have any other questions?

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

​ To learn more, see the sources I considered: [[1] Platform Changelogs | Retell AI](https://www.retellai.com/changelog) [[2] Automatically test your agent](https://docs.retellai.com/test/llm-simulation-testing) ​