As long as agents are fuzzy (which they will continue to be with the Transformers architecture), the need to validate will continue to exist. I cannot imagine merging code without at least 1 human review.

I've used agents quite a bit and I agree.

The current baseline workflow is something like agent output -> human review -> agent refinement -> human review -> agent refinement -> ...

But agents are capable of making meaningful improvements to their own output. I'm hoping dynamic workflows move towards something like:

agent output -> agent review -> agent refinement -> (cycle to fixed point) -> final human review