The major difference is that people routinely ship shoddy, broken products in the world of software with few consequences, beyond needing to patch it later. Try the same thing with a court filing and you’re out on your ass.
Well hang on, "just work" implies an objective standard of correct vs incorrect. No such standard exists. I'm sure that there will be legal AIs that reliably do... something... but the whole point of the legal system is to allow space for humans to argue their case. If an AI "does legal" deterministically, without human intervention, how can it be said to be "working" if its very use defeats the purpose of the system it has learned to navigate so expertly?