Built a live dashboard tracker for client trials, kept up to date by an AI agent
Problem
Trial data sat in four systems and was brought together only once a trial had ended, too late to act on during it.
Solution
A daily picture of engagement and retention from 4 data sources. In its first week it showed who had not come back and flagged two data problems that would have reached the final report.
A decision-support dashboard for public-sector health teams: led the design from research to a clickable prototype, with input from an academic expert in biomedical informatics.
App delivery for 11 months: about 210 changes shipped with a team of three, from 248 tickets I wrote and prioritised.
A terminology system for a Japanese release, for a team that does not read Japanese: one glossary of 172 terms, one change log, English beside every string.
The analytics tracking plan and metric definitions, plus a monthly product data review run to one fixed structure.
An AI agent that drafts on-brand LinkedIn cards, with a cited source on every statistic and a person approving each one.
One colour and type system, carried across the website, the app and social templates.
The app's design system, with the design file moved onto shared colour and spacing tokens.
A rebuilt team workspace: 7 linked databases, so a weekly meeting updates the tasks and the tasks roll up to the quarter's goals.
Hiring for a product designer: the task, the scoring guide and the interview.