A production release failed. Twelve hours of debugging with Claude pointing confidently in the wrong direction, with me following. When I finally found the real cause buried in the error logs, I did what most developers do. I blamed the tool.
That was the wrong diagnosis, and I knew it the moment I said it out loud.
The AI didn't fail. The workflow did. Those gaps, no HTTPS testing, no failure model for what happens when the UX breaks, would have bitten me with any developer, human or AI. The AI didn't create them. It amplified the damage because fast code generation let me ship faster than my verification loop could catch up.
That's the loop companies need to understand before they start cutting headcount.
Agents deliver value on tasks with clear, mechanical outcomes. The build passes or it fails, the tests run or they don't. The human's job there shifts from writing the code to reviewing it. That's a real productivity gain.
Agents break down when trusted for diagnosis, when they're asked to explain why something is broken. AI produces statistically plausible explanations, not verified ones. It reads like confidence. The error logs had the real answer the whole time, but finding it myself would have required breaking the loop. "Claude says X, I merge X."
The shift agents actually require is this: the developer's job doesn't go away, it changes. Your job becomes proving the AI wrong before it ships. That's a harder job. It requires maintaining enough understanding to independently verify code you didn't write.
"AI slop" is what happens when that role goes unfilled. It's not a property of the tool. It's a property of the workflow.
Agents won't replace developers. They'll expose which organizations understand that distinction and which ones are about to learn it the hard way. You can't remove the human from the loop and expect the loop to hold. The assumption that you can is the actual death knell, not for agents, but for the teams that bet on it.
--
Michael Stelly is a Senior React Native Technical Lead and founder of ReFactory, a consultancy specializing in React Native architecture and modernization. Building production RN apps across healthcare, logistics, and retail since 2018.