Hello Luca,
I trust this message finds you well. I would like to express my appreciation for your valuable feedback and for downloading our product. Allow me to introduce myself as Mushon, a member of the development team.
We have encountered a situation where users may experience delays when running the same query multiple times. This could be attributed to increased traffic resulting in OpenAI's slower response times, we have downgraded from GPT4 to GPT3.5 as a results (we will upgraded back when things would stable). Additionally, Atlassian imposes a timeout of 25 seconds. Further details can be found at: https://community.developer.atlassian.com/t/how-to-handle-slow-rest-calls-in-forge-10-seconds-limit/47880
Rest assured, we are working to resolve this issue. One potential solution could be to demonstrate the situation to the customer and inform them of the high traffic.