The build log

Notes from running agents in production.

Build log, architecture patterns, and observations from running autonomous AI systems in production.

All ● The Timeline ● The Repo ● Signals

Filter by tag

Jun 29, 2026 · 4 min read

I stopped babysitting the browser, then had to build the part that was missing

I never launch the browser. My agents drive it. The problem was how unreliable that was: windows off-screen, sessions clobbering each other, an agent grabbing my personal Chrome. Making it consistent across many agents was infrastructure I had to build.
Jun 29, 2026 · 2 min read

The 200-Line Lie: Why My Agent Kept Forgetting My Goals

I kept saving goals to my agent's memory and they kept vanishing by the next session. The cause wasn't a flaky model. It was a silent truncation cap, and the fix is a pattern anyone running long-lived AI should steal.
May 23, 2026 · 3 min read

My agents quietly hoarded 48 GB of Chrome profiles until the machine froze

Per-session browser isolation was the right call. Per-session isolation with no reaper filled my system drive, froze the machine, and forced a reboot. The fix was a fixed pool.