Complex systems and AI products

An offline-first learning platform reaching 13M+ learners and educators across 220+ countries and territories. Teachers moving content onto constrained devices could struggle to find import at all, or to understand what they were downloading — and a failed transfer can cost a class its lesson. I redesigned discovery and import across online, local-network and removable-media sources, and extended the design-system infrastructure with reusable component, status, accessibility and RTL patterns the rest of the platform reuses.

+85% discoverability · −60% failed imports in usability testing

Counter, marketplace, WhatsApp and direct orders all have to become the same truth for payment, kitchen, stock and dispatch. The design problem is shared state across live service: when an order becomes kitchen work, what the checkpoint is that moves stock from committed to consumed, and which single queue a fulfilment officer actually works from. I design that logic across the surfaces and stay in it through implementation.

31,324 paid, closed and confirmed tickets · ₦1.66bn processed · 14 venues · 23 Apr to 23 Sep 2026

ApplyOS is multi-user candidate software for market-aware discovery, eligibility-first job judgment and evidence-backed application preparation. The design work defines what the system may conclude, what stays deterministic, how career evidence is governed and where the candidate remains in control through final submission.

171 hand-labelled roles · feed-level precision 59% → 89% after market-aware gating

A live vehicle and driver document product where one upload creates or updates a vehicle, surfaces missing or expiring documents, and keeps renewal work visible until completion. The design centres on one question: when I open this, can I immediately tell what needs my attention?

I designed AI-assisted creation workflows for enterprise video across generation, asset libraries, brand controls, versioning, review, approval and export. The hard design work centred on source and version trust, configuration, clear next steps and recovery around generated output. This work was completed in the period leading into the company’s first announced $3M seed.