Two years ago, without AI or with primitive autocomplete tools, there was a natural limit to how much code a developer could produce. The…Continue reading on Medium »
A pull request used to be the output of one engineer. Increasingly it is the output of a workflow. That changes what review actually is.Continue reading on Medium »
A repo-aware agent produces changes that look team-native. The problem is that “looks team-native” is not the same thing as “is correct.Continue reading on Medium »
AI made output cheaper to produce. It did not make engineering judgment easier to skip.Continue reading on Medium »
The Opacity Tax on AI-generated code is invisible until it isn’t.Continue reading on Medium »
I’m a solo developer. I work on multiple projects, ship code daily, and nobody reviews any of it.Continue reading on Medium »
Why your high-speed AI engine is destroying your cycle time, and why human connection is the only fix.Continue reading on Medium »
The productivity bottleneck has shifted from generation to review — and most teams haven’t updated their process to match.Continue reading on Medium »
Meta researchers developed a structured prompting technique enabling large language models to verify code patches.Continue reading on Towards AI »
Why generic bots fail and how to build an AI reviewer that actually understands your team’s unwritten rules.Continue reading on Towards AI »