Changing how people work, through design and AI.
Ten years of B2B product design and 3+ years leading frontend. I've helped a paper-run welfare business onto digital workflows, cut a booking flow's peak-season inquiries from 200+ a week to about four, and built a first design system for a team that had none. Now I build LLM features into real operations, with a person at every decision that matters.
10 yrs B2B product · 3+ yrs frontend lead
Booking redesign: 200+ → ~4 inquiries/week
Paper-run welfare operator → ~100 staff on digital workflows
LLM systems built for 2 client businesses, with human review gates
Selected projects
LingoBun: Hardening an AI Language-Learning Product for Production
An LLM-powered vocabulary app taken past the demo stage: Redis-backed rate limiting and cost caps on every AI call, Zod-validated environment config, and a 180-test Vitest suite guarding the pipeline.
Understanding the Log Types in a Wazuh + Claude Security Pipeline
A field guide to the five log types flowing through my IFN737 research pipeline — from raw attack execution logs to Wazuh alerts to Claude's structured classifications — and how they connect.
Strobe Assistant—Extending Strobe with an AI Agent
How I extended Strobe, a photo-sharing app on AWS, with a conversational AI agent, an asynchronous pipeline that makes every photo searchable, and an agent that runs on its own every morning, plus what I'd do differently.
AuStride: Striding Towards an Active Future
Walking or riding rather than driving offers the two-fold benefit of increasing mental and physical health while reducing motorised transport’s impact on the environment. However, there are several challenges to consider: availability of safe and accessible walking and cycling options, lack of time and motivation, and gaps in transport infrastructure that make it impractical to walk, ride, or use public transport.
How I work
Understand the operation
Start from how the work is done today — on paper, in spreadsheets, in people's heads — and what the business actually needs to change.
Decide who decides
Design the system and its review points: what's deterministic code, what an LLM drafts, and what a person must sign off.
Design and build it
Interface and production frontend in one head, so trade-offs are made once instead of traded across a handoff.
Prove it and make it stick
Tests, evaluation and field feedback until the team uses it every day, plus a design system so it stays consistent after I leave.