I don't understand the category. Is getting things right not the goal?

These tools are marketed as if you just drop the jira text in and it spits out a finished PR. So it's notable that they don't work the way they are advertised.

Which is not what the OP did.

there exists tools that can zero shot complex tasks (claude/codex). bar has been raised and jules doesn’t stack up. knowing google it will probably improve in due time