Topics

Why AI agents forget corrections, and the enforcement layer that makes them hold. The core research line — from the diagnosis to functional scars to instrumenting a live system.

AI agents doing real civil-engineering work: finding the file that holds the true source of truth, placing drainage culverts from a one-column list, and turning a one-off fix into a reusable skill.

Field notes from running a production system on LLMs every day — what actually cut a four-minute boot, why the optimization you wrote isn't the one that runs, and where today's tooling debates have played out before.

Installable primitives that came out of the work: fscars for correction persistence, callus for voice calibration.