// VERIFIED SHIPPED ARCHITECTURE
Systems I Have Built & Shipped
Every system below is real code: production software running in a commercial contractor's Azure cloud, live products on Google Cloud Run, and reproducible evaluation and neuro-symbolic verification shells.
Northeast Florida Commercial Contractor
$150K/yr retired per-seat licenses
An engagement that began as one embedded engineer in the contractor's own cloud and now runs as the client's own small engineering team, shipping owned apps with guardrails-first delivery: forecasting, change-order routing, approvals.
Inspect Full Architecture & Metrics →
Real-Estate Lead Company
~517 ms to first audio on a real call
An inbound phone agent for a real-estate lead company: ~517 ms to first audio on a real call, a 16-scenario eval gating every prompt change, and every call persisted as a redacted record.
Inspect Full Architecture & Metrics →
TextTimeline
100% citation coverage
A search engine for SMS evidence. An attorney asks a question in plain English; every finding traces back to a specific timestamped message.
Inspect Full Architecture & Metrics →
GammaRips
14 Cloud Run services + ~20 schedulers
Fourteen Cloud Run services, ~20 schedulers, and a multi-agent publishing layer that filters market noise into one tracked, public, mechanically-held trade idea per day.
Inspect Full Architecture & Metrics →
Commercial Real-Estate Developer
One owned portal replacing fragmented SaaS
A custom investor and stakeholder portal for a commercial real-estate developer raising capital, built to replace fragmented SaaS with one system they own, running on their own Google Cloud.
Inspect Full Architecture & Metrics →
Detection Evaluation Shell
Open-source eval shell, public on GitHub
An open-source evaluation shell I built around a public X-ray contraband detector: the part that tells you whether a detection model is actually trustworthy, not just what its headline score is.
Inspect Full Architecture & Metrics →
Compositional Verification Engine
10/10 integration tests passing
A Rust prototype I built for a federal research solicitation: it translates typed ML outputs into logical facts, runs bounded reasoning through a real symbolic backend, and abstains when a case falls outside what it can support.
Inspect Full Architecture & Metrics →