Blog
From AI-Assisted Development to Evals: What I Learned from Three Real Cases
How I started turning development tasks with AI agents into evaluable experiments, with explicit criteria, evidence, and human decisions, based on three real cases in Developer OS.
October 11, 2026
Two silent bugs. One before the code existed, another after everything was green.
Two silent bugs in Developer OS were caught at opposite stages: one during planning, before any code existed; another after tests, build, and deployment were already green. What these cases taught me about independent review and AI agent orchestration.
September 27, 2026
Why I'm Building Developer OS
What Developer OS is for, why AI agents write most of the code here under my review, and why the process is documented as openly as the output.
September 1, 2026