Writing

One optimization loop. Three systems. Every one improved. The method is stupid simple and works on anything you can measure.

A devlog about building Engram — and the two AI agents who helped build it. Three wipes, 70 tickets, and the line between tool and teammate.

I asked my AI what we did today. It had no idea. So we taught it about time — and in the process, discovered why memory is harder than anyone thinks.

Four hours. Two humans. One AI. A simple form that wouldn't work. Sometimes the answer isn't in the logic — it's in the gap between what should happen and what actually does.

ADHD doesn't do incremental improvement. It does incremental chaos. Here's how conversational AI became my counter-balance.

What happens when an ADHD brain gets two uninterrupted days. Spoiler: a month's worth of work.

How five days of collaboration with an AI agent helped me ditch fake consultant branding and ship an authentic personal site.

First post. Why I'm writing, what to expect, and a bit about how this site came together.