text classification is equivalente to decision. This is exactly the same thing Jev does.
It is not. In a benchmark with actual decisions - navigation, traffic, waypoints - laya does only slightly better than a small classifier.
Jev does it more efficiently because it doesn't use an LLM https://typesafe.ai/blog/introducing-system-one-models-and-j...
If it has four legs, a tail and barks why not call it a dog?