AI Agents Increased One Engineer’s Workload
A full-stack engineer and technology executive describes using multiple AI agents across implementation, investigation, code review, and research. GitHub activity through October 27 shows sharply more contributions in 2026, while the author says the added review and context-switching workload led to fatigue. The figures are presented as a rough activity signal rather than a measure of productivity or value.
The first-person account offers practitioners a concrete example of how AI agents can expand an engineer’s workload through more parallel projects, reviews, and context switching.
The pitch was that AI would give us our time back. Write less boilerplate, delegate the boring parts, go home earlier.
I am not complaining about the tools. I use agents for all of my engineering work now, and I wrote about how that setup evolved and why I still read the code. I can investigate and ship things that would not have been worth starting two years ago.
But somewhere this year I noticed that I am working more than I ever have, and that it feels heavier than it used to. Not because any single task is harder. Because there are so many more of them, all at once.
This post is me trying to understand that, with some data from my own GitHub history.
The old load and the new load
As a full-stack engineer, a normal week for me meant two or three serious tasks. A feature, a tricky bug, maybe a migration. Each one needed real focus, but I could hold one of them in my head at a time, finish it, and move to the next.