How about a bug fixing use case? Let agents pick bugs from Jira and let it do some research and thinking, setting up data and environment for reproduction. Let it write a unit test manifesting the bug (making it failing test). Let it take a shot at implementing the fix. If it succeeds, let it make a PR.
This can all be done autonomously without user interaction. Now many bugs can be few lines of code and might be relatively easy to review. Some of these bug fixes may fail, may be wrong etc. but even if half of them were good, this is absolutely worth it. In my specific experience the success rate was around 70%, and the rest of the fixes were not all worthless but provided some more insight into the bug.
This can all be done autonomously without user interaction. Now many bugs can be few lines of code and might be relatively easy to review. Some of these bug fixes may fail, may be wrong etc. but even if half of them were good, this is absolutely worth it. In my specific experience the success rate was around 70%, and the rest of the fixes were not all worthless but provided some more insight into the bug.