AI in the product & Product-development transformation

AI in the product and in how you build it.

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.

What

From "should we use AI here" to shipped, in your product and your build.

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.

AI in the product

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.

Product-development transformation

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.

Evaluation & deployment in regulated settings

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.

Proof, not promise

Real AI deployments

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.

Form Health
DEPLOYED · CLINICAL

AI in the product — shipped and running in clinical care.

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.

~50%
less clinical visit time
10×
faster patient access
30%
less clinician messaging
~50%
of inbound calls AI-handled
Read the Form Health case →
mnemur.ai
LIVE

A proprietary AI orchestration & context-management system.

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.
Visit mnemur.ai →
Maven Clinic
TAILORED · REGULATED

A custom EMR, prototyped with AI in days.

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.

Read the case →

How

Evaluate, prototype, deploy — and level up the team.

Most engagements start with a 2–4 week problem-framing sprint, priced by role and cadence, not hours. The phases overlap.

01 · Evaluate

The right pattern

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.

02 · Prototype

Working, in days

A real capability in your product, not a demo — prototyped fast with AI, tested against clinical and operational reality.

03 · Deploy & transform

Shipped, and it sticks

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 →

This is one of the ways I help.See how else I can help.
Back to the full offering →