Case Studies
Real projects. Real results. Evidence, not marketing.
Detecting $500M in Medicare Fraud with Public Data
A single Go binary ingests 548 million rows from 22 CMS datasets, scores 1.47 million Medicare providers, and serves an interactive investigation dashboard. 42% Precision@100 — an 890x improvement over random. Built in 13 days by 4 people. Infrastructure: under $800/month.
Read the full case study →Replacing a 100GB Graph Database with a Function Call
40+ graph algorithms for Go. Built to replace Memgraph — eliminated 100GB RAM, Docker dependency, and dual-license risk. Pure Go, 97.3% test coverage, MIT licensed.
Labs Case StudyNative Speech Infrastructure for Blind Developers
SwiftMac is a usable macOS-native Emacspeak speech server built in Swift. It supports voice control, tones, audio icons, and multi-device routing for real daily development workflow.
Labs Case StudyCross-Platform Speech Infrastructure
Omnivox is a usable Rust speech server for Emacspeak, evolving SwiftMac's macOS-native lessons into a broader architecture with platform backends, a shared audio pipeline, and concurrent streams.
R&D Case StudyNative Interface Over a Server-Run System
DelveGlass is a Godot client for WebTiles-compatible servers. It keeps gameplay, saves, rules, and process execution on the server while replacing the user experience with a mobile-first native interface.
R&D Demonstration12 Million Words, 2 Days, 1 Engineer
AI-powered extraction pipeline processed one of the longest works of fiction ever written — 12 million words across 807 chapters — into a searchable interactive map. 100% AI-generated code.