It would be great to be able to test impersonating other users as a Moveworks Admin across the AI Assistant. As the assistant steers questions based on attributes from each users, it’s tough to see how pages are returned to employees.
It gets even harder when we (IT) have restricted internal runbook documentation vs employee facing documentation, and seeing the differences between what we would get back vs employeees.
I was just about to make my own thread on this - would love this functionality! If we could impersonate users, it would allow for rapid testing of plugins and permissions while making changes or building out new agents. It would also remove the need to involve other departments or users in QA testing, as it can be completed ourselves. This feature exists in ServiceNow and is vital to properly testing out new forms and flows before publishing them.
I was hoping that the (beta) Conversations API would allow this, but looks like it’s not supported atm based on the API spec published on MW docs.
For admins though, I agree that a UI based impersonation tool will be great.
In MW setup, the indexed content menus let you check the permissions of a user to individual files/knowledge, but that can be tedious and would not give the full picture like impersonating another user and chatting with the bot.
Already have an account? Login
Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.
