When I reject AI code even if it works
Key takeaways
- With implementation getting faster and faster, the real bottleneck moves to reviewing the volume of code generated by AI.
- Before coding agents, when given a task, I would explore the codebase, think of different solutions, experiment, and only then implement.
- I have to admit that with AI, completing big tasks still takes me days.
With implementation getting faster and faster, the real bottleneck moves to reviewing the volume of code generated by AI. I’m not even talking about your coworkers’ (and their agents’) PRs, but your own git diff after your coding agent has finished its job.
Even when I follow good practices – like starting with the plan mode, dividing big tasks into phases, and shipping small changes – I still feel cognitive overload when reviewing something I haven’t actually thought through myself.
Before coding agents, when given a task, I would explore the codebase, think of different solutions, experiment, and only then implement. That could take days of consolidating all that context. When I finally submitted that PR, confidence was higher, and explaining each of my changes to my coworkers was easier.