From a working prototype in days to AI woven across the build. Off the shelf or tailored, evaluated and deployed, also in regulated settings.
A 30-minute call to get a first read on where AI earns its place in your product, and a proposal for a 2–4 week problem-framing engagement.
AI that earns its place in the product. Proven in a prototype before it ships, gated by a human, and built to hold up under regulation.
Most AI in product fails not in the model but in the deployment — the wrong pattern, no evals, no human gate, no path through compliance. I work inside your team and your code to put AI where it moves a real metric, and to change how the team builds so the speed lasts.
Off the shelf or tailored. The right model and pattern for the job — copilots, scribes, summarization, retrieval, agents — placed where they move a real metric, not where they demo well.
AI across the build, not just in the product. How your team specs, prototypes, ships, and reviews — prototyping working capabilities in days, not quarters — so the build itself gets faster and the org learns to work this way.
Vendor and model bake-offs, an evidence-based build vs. buy call, evals and guardrails, graduated autonomy — AI that proves state before it claims it, with a human in control. Deployed where work has to stay separated, HIPAA-aware, compliant, and auditable — clinical, payer, and other regulated workflows.
Not a deck. AI already deployed in a real clinical product, a system that runs my own practice every day, and a regulated product prototyped with AI in days.
The central proof: as SVP Product & Technology (CPTO) at Form Health (obesity and cardiometabolic care), I put AI directly into the clinical workflow — record review, scribe, summaries, and inbound-call handling — deployed and running in a live, regulated setting, not a pilot.
Every context in its own room, firewalled, while the learning compounds under your rules — agents, memory, guardrails, and audit as one system, built verify-not-promise so nothing ships on a promise. It runs my own portfolio daily, and is offered within engagements: deployed in your code, hosted, or managed.
Why this is the bet: the harness — the system around the model — is where reliability is won, and the field now measures it. On a fixed model, harness changes alone moved LangChain's agent +13.7 points. That layer is exactly what mnemur productizes.
Clinical programs were running on slow homegrown software. I chose a custom EMR on Medplum + Claude Code over extending the legacy stack, and used AI to prototype working capabilities in days, not quarters — a working prototype that proved a viable path off the old software, in a real clinical setting.
Most engagements start with a 2–4 week problem-framing sprint, priced by role and cadence, not hours. The phases overlap.
Where AI actually earns its place, build vs. buy, which model for which job — with evals and a compliance path defined up front, not after.
A real capability in your product, not a demo — prototyped fast with AI, tested against clinical and operational reality.
Guardrails, graduated autonomy, and a human gate for the regulated setting — and your team building this way after I’m gone.
See the one-page capabilities summary →