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.
An outage left days of video sitting in storage, processed by nothing. None of it was lost. Getting it processed took two weeks, because every stage in the pipeline stamped its own arrival time and called that the truth.
Six months of daily agent use took our backend from 311 test methods to 2,198, and nothing in the pipeline could say whether that helped. The missing piece was not a test. It was a quality gate.
Our OpenAI bill was doubling about every week, and nobody could say which call was expensive. One table of call logs later, three fixes cut the input tokens per matched fixture by 88.8%.
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.