Nine systems, taken apart.
One long-form piece per project — what the problem actually was, the decision that mattered, and the part that fought back. Every number in them was verified against the repository before publishing, and each links to the code it describes.
Why My Data Pipeline Rejects 84% On Purpose
A pipeline that throws away 838 of every 1,000 rows sounds broken. Mine isn't — it's doing exactly what I designed it to do, and it can name the specific…
02AI Writes The Verdict. Code Decides If It Ships.
Card-fraud systems fail on two fronts at once.
03Same Query. Same Table. Two Different Answers.
A safety officer runs a query against the driver table and sees a heart rate of 134 bpm and a GPS position to six decimal places.
04My Pipeline Broke. It Fixed Itself In 22 Seconds.
A generated pipeline script failed validation — mid-run, inside CI, with nobody watching. The agent read the verbatim error, worked out which line was…
05The Pull Request That Leaked PII Never Merged
Most data governance is a report. Somebody runs a scan, a dashboard turns amber, a ticket gets filed — and the grant that exposed a schema of customer…
06Every Reading Was Valid. The Sensor Was Lying.
A temperature sensor starts reading five degrees high. Not wildly — five degrees.
07The Model Wrote The Report. Not One Of The Numbers.
A language model wrote a full CSRD sustainability statement — the disclosures, the methodology notes, the prose that explains what each figure means and…
0831 Of 36 Fields Go To A Human. That Is The Feature.
A customs broker receives the paperwork for one shipment: a bill of lading, a commercial invoice, a packing list, a certificate of origin, a customs…
09Eight Chargers Throttled. No Model Decided One.
On the live run, a substation went past its thermal limit — 485,442 W against a declared 450,000 W — and eight EV charging sessions were throttled to…
10The code your team started from
Nobody writes a retrieval-augmented AI application from an empty file. They clone a sample.