At work, I have the same difficulty using AI as you. When working on deep Jiras that require a lot of domain knowledge, bespoke testing tools, but maybe just a few lines of actual code changes across a vast codebase, I have not been able to use it effectively.

For personal projects on the other hand, it has expedited me what? 10x, 30x? It's not measurable. My output has been so much more than what would have been possible earlier, that there is no benchmark because these level of projects would not have been getting completed in the first place.

Back to using at work: I think it's a skill issue. Both on my end and yours. We haven't found a way to encode our domain knowledge into AI and transcend into orchestrators of that AI.