I build real-time distributed systems using AI pipelines. I write about what worked, what didn't, and the numbers behind both.
Throughput doubled. Change-failure rate doubled with it. Both are in the posts below, with the caveats and the counts behind them.
At the end of a 20-month platform project, I listed what I wished we had measured. Five things were missing. Two were gone forever to retention windows, and the widest of them was one checkbox nobody had ticked.
My agent published a post nobody had reviewed, following a note I wrote and contradicted twice afterwards. Everything else in this repo is enforced by code. Memory was the one layer that only advises.
An agent optimises the ticket in front of it and cannot see the fix fighting the wider architecture. Design intent is the only thing that rejects a narrow local fix, and where you put it decides whether it works.
2026 · TypeScript · React · Claude Code
A local job-search CRM with agents at every step. It checks about 1,630 postings a morning and hands me one page of decisions.
What changes when an agent becomes the daily driver. Throughput, cycle time and change-failure rate, with their caveats.
Real-time quality analysis of video streams. Event-time semantics, the consistency boundary, the bugs that only show up in production.
Build versus buy, instrument before you roll out, when to defer. The decisions that never make it into a postmortem but should.
Terraform at a startup, schema evolution, and the database choice you regret six months later.
Most teams have adoption numbers, seats bought and suggestions accepted, and nothing on whether anything shipped sooner or broke less. I answer that from your own Git and CI data. Read-only, five days, fixed price.