The advantage of a turn-by-turn flow (honestly the chat interface was genius) is that with a little human intervention you can get much better results out of even silly models. The model of choice is strange, though. Not a particularly good one.

People apparently like Granite for RAG specifically. I'm not aware of any evaluations with numbers though, so I'm not sure if it's a real difference or just vibes.

Either it depends a lot on the model, or I’m bad at chat, or both, because in my experience once a chat starts going off the rails it’s pretty hard to correct the initial misconception. I find it works better to backtrack to just before the misconception and edit my previous response to head it off at the pass.