AI agents · software engineering · platform · infrastructure
I build agent systems and the platform they run on.
Long-form notes from the inside of the work: agent architectures that survive contact with real repositories, the Kubernetes underneath them, and the unglamorous operational detail nobody writes down.
Writing
- Nothing here is specialEvery step is a Job, every brain is a ConfigMap, every score is an MLflow run, and one gateway holds every key. The platform under the agent flywheel, the libraries it is built from — the evaluation harness, Harbor, EvalHub, GEPA — what each one needed wrapped around it, and the sandbox that is built against the one that is only designed.
- The best brain, not the last oneTraining is evaluation in a loop: score a brain, let a second agent adjust it from the judges' reasons, score it again, keep or revert. Nobody touches a weight. What the adjuster may read, what it never sees, what it wrote in five steps, and three different engines for the adjust step.
- Closer than the spread is a tieA benchmark is an evaluation with three promises: frozen, shared, comparable. Sixty evaluations of three agents on four models ran in 21 minutes for 5.39 USD, and the top five variants were a tie. What has to be frozen, how many runs one variant needs, and why a benchmark must never pay twice for the same measurement.
- +42more posts