Start with three public projects. Then inspect the employer outcomes, where I name my role and keep the work unlinked because it is not mine to demo.
A plan can sound complete while its assumptions and missing evidence stay hidden.
An experimental tool for pressure-testing a plan and drafting a decision record. It treats the decision artifact as the output and keeps missing evidence visible.
Public Census data is useful but difficult to inspect without knowing its source structure, query language, and limits.
An open-source project for exploring public US Census data. It documents source vintage, constrains generated queries, and states the limits of the current data and interface.
Data-product decisions lose their evidence and ownership as work moves from a question into delivery.
Open-source skills and a file-based workspace for data-product decisions, evidence, quality checks, and human review.
No links here. These shipped inside employers, and the products aren’t mine to demo.
Real-world-evidence platform for mental health. Led product work across the $15M platform business, including $3M in standalone subscriptions. Scaled the clinical dataset from 0.5M to 46M+ patient lives and 59M+ clinical notes. Built the eval frameworks governing production GenAI across 25+ regulated clinical organizations.
Physician-referral graph product line. Grew the line to $1M ARR, up 225% over four quarters, across 12 health-system clients.
Enterprise patient-experience product. Deployed to 175 hospitals and 1,500 executive and nursing leaders. Cut report-development cost by $1.2M a year. Trained 200+ users.
No links by design. Employer work stays unlinked.
If the work maps to a product problem in front of you, the next useful step is a direct conversation.
What I’m building, what broke, and what I’d do differently. Healthcare data products, decision infrastructure, and the messy middle of building alone.
No spam. Unsubscribe anytime.