Hi -- strange that didn't work. Overall, the semantic layer is designed to provide very tight guardrails and not hallucinate. You can see the agent suggest changes to the semantic layer if you give the produced answer a thumbs down.

The idea is for the system to provide answers that have close to 100% accuracy, but make it a single click for developers to to improve the semantic layer.

Was able to reproduce and pushed an update. Thanks for calling this out.

Just updated the README, thanks for the suggestion!