In AI products, much can often be done with the model directly in the conversation rather than through new bespoke UI, though there is a balance.

What can we do this without pixels? Can we do this with tokens? Can we do this with the model itself?" And always trying to push to to do more of that. What can happen directly in the conversation and and in the flow of of how you're using the experience versus trying to think about what new kind of bespoke UI to do we need for this