Product leader · hands-on builder · Chicago · US & Australian citizen, open to relocation
I build and deploy consequential AI systems where a working model is not enough to ship
Doximity Dialer, which I originated as founding product lead, carries more than 300,000 calls on an average workday across 250+ health systems — 9 years after I left.
14 years as a product leader and hands-on builder originating products across clinical care, oncology, and AI systems, on a foundation of biomedical engineering and molecular-biology research. See where I’d fit →
Organizations I’ve worked with
Current work
Primary builds on one problem: records that stop tracking reality while systems go on using them.
- Refract Change detection and provenance: a daily observation bot and 16,146 manifest-backed events beneath evidence sources.
- Fast Harm, Slow Repair Agent error evaluation: a benchmark protocol measuring how far AI mistakes propagate through tools and what remains wrong after correction.
What I’m brought in for
Three steps, in the same order, every time:
- Enter before the roadmap exists
- Build an unproven idea far enough to learn whether it holds
- Bring senior judgment to what happens next
I originated Doximity Dialer, led R&D at CancerCompass, and co-founded Andwise. Andwise settled the user question in year one; I did not settle who would pay until year two, by which point every fundable path put someone other than the physician in the customer seat. In 2024 I shut it down rather than build that company. Since then I have built the systems myself when that is the fastest way to learn.
Selected work
The patient sees the office, not the cell phone
A physician calling a patient had two bad options: the hospital desk phone, or a personal cell that showed “Unknown Caller” and gave the number away for good. As founding product lead, I originated the identity layer that let the call come from their own phone while the patient saw the office number — so it got answered, and the cell stayed private.
Read case study → Four specialty programs on one routing architecture
High-acuity cases across Surgery, Oncology, and Behavioral Health were stalling in exception queues, and the default was four separate products. I put all four on one routing architecture tied to clinical accountability, so a nurse and a navigator worked from the same facts and every case had an owner. Slower to build, faster to scale.
Read case study → Reading the contract before the physician signed it
Early-career physicians were signing employment contracts with no unbiased read of what was in them. Andwise’s software read the contract, flagged the clauses worth arguing about, and stopped there — it did not advise — with a named reviewer on a deadline behind every analysis before the physician acted.
Read case study →