Dear Team, the question is how to make the automatic evaluation of a copilot agent work, because I've tried it today and results are always errors or fails, the same goes with artificially generated questions and with manually added questions. Is it the system itself that is not working or there is a way to make it work properly?
Yeah that is still something I do not use much at the moment (I have my own custom stuff) so its hard to say since its new and not something we control.
For the ones that failed, can you explain if it fails in the same way each time?
Since I do not use this, I can only suggest to take a look at this and just verify against the users suggestions for configuration etc
If these suggestions help resolve your issue, Please consider Marking the answer as such and also maybe a like.
Thank you!
Sincerely, Michael Gernaey
Was this reply helpful?YesNo
Under review
Thank you for your reply! To ensure a great experience for everyone, your content is awaiting approval by our Community Managers. Please check back later.