Work
Each case study carries the problem, the decisions — including what we rejected — the measured numbers, and the limitations. A study without a limitations section does not get published.
Building a 1.8 GB Persian legal corpus
A legal corpus and platform built to the point where retrieval becomes an engineering problem instead of a guess.
Building a clean Landsat corpus for mineral exploration
Caught an 80% duplicate rate in a supplied dataset before a single annotator hour was spent on it.
Migrating 29 repositories onto self-hosted CI/CD
Twenty-nine repositories and their pipelines onto infrastructure the client controls, with the two failure modes that cost the most time written down.
A public fraud registry, built in 26 hours
From empty repository to a deployed public registry with an approval workflow, an append-only audit trail and 1,360 test declarations, in about 26 hours.
An assessment platform in 14 days
A multi-tenant assessment platform, wallet, scoring engine and reporting pipeline delivered in fourteen days, with every number in a report traceable to the key that produced it.