Work
Systems in production.
What each one does, what made it hard to build, and the analysis it was built from. Two are our own products and one was client delivery — every case study says which, because evidence that blurs the two isn't evidence.
KriftAI
Own productGoverned AI for regulated workWhat we built
A governed AI platform: every model call passes through input and output validation, a deterministic compliance gate, and per-call audit logging — and nothing an AI writes reaches a customer without a human approving it.
The hard part: Making a language model safe to put in front of a compliance obligation
Specified first
Functional design document · Rules engine specification · Governance state machine · Data model · Acceptance criteria
See what shipped → for KriftAIImmiCase
Own productRegulated case managementWhat we built
A case management system for Canadian immigration practice, where programme rules live as data so a regulatory change is a configuration edit rather than a release.
The hard part: Rules as data — programme changes without a code deploy
CrewDispatchr
Client deliveryField operations and workforce dispatchWhat we built
A staffing and dispatch platform for field operations — scheduling, crew assignment and shift changes in one system instead of a phone tree.
The hard part: Real-world churn — the schedule changes all day