I don't find that the models are so capable that the workflow can be "much less about prompts". you still need to be in the loop, prompting and validating, to get good output. people will say otherwise -- I say those people are full of shit, have an adverse incentive, or don't have high standards.

Thanks. I could have phrased that better. What I meant was that so much of my work has been about the prompt that I feel like I'm neglecting where the rest of the process is.