I love the idea of Phoenix and server side rendering (I happen to work on SkyMass, a related project).

This is a tangential comment and should not detract from what Chris and team have created. I think closing the loop between agent and the running output is a great/critical step forward.

However, I find using AI to build transitional Apps with a UI is a bit like improving the way automobile steering wheels are made. In a world that soon won't need steering wheels at all.

If the AI is so good to write the code for an App, how much longer before you won't need those Apps in the first place? And then the question is, what will fill the role that Apps play today.

I think it boils down to: if the AI screws up what I asked it to do, who do I have to hold accountable? If the answer is that there is no one I can hold accountable, because the AI agent I used removes any and all onus of responsibility in its terms of service, then I'm not going to use it for anything non-trivial.

I don't think we want to move to a world where everything we use is AI driven all the time.

A coded app is significantly more efficient to execute, and more predictable, than dealing with AI in most situations.