arrow_back Back to Projects
Case Study AI Product · TPM · Health Diagnostics

Shipping AI Providers Trust: Two Features, One TPM Playbook

I put two AI features into the hands of 200+ clinical users, and I owned more than the timeline: I decided what the AI actually did. I set the thresholds, rules, and model selection for evaluation suites that flag and interpret lab results, and for a dashboard that reads a clinic's practice health, then drove the rollout across engineering, clinical, and product. This is where AI product judgment and program discipline meet.

RoleTechnical Program Manager
ScopeEngineering · Clinical · Product
SurfaceProviders & patients
OutcomeRolled out to 200+ users
How I Worked

Two jobs, held at once: shape the AI, ship the program

On both features I carried the product requirements and the delivery at the same time. I defined what the AI did, the thresholds it judged against, the rules it followed, and which model fit the job, and I ran the program that turned those decisions into something live: a charter, the dependencies between engineering, clinical, and product, a phased rollout, and the stakeholder alignment to keep everyone moving on one plan. The two halves below show that pairing in practice.

neurology

What the AI did

The product layer: requirements, thresholds, rule logic, and model selection. These were product decisions, and I owned them with engineering rather than handing off a spec.

conveyor_belt

How it shipped

The program layer: charter, cross-functional dependencies, phased rollout, validation gates, and the stakeholder cadence that kept engineering, clinical, and product aligned to launch.

01
Feature 01 · Diagnostic AI

AI-assisted evaluation suites

AI that analyzed raw lab data, flagged abnormal results, and surfaced diagnostic interpretations for providers and patients.

Situation

Raw results, expert interpretation, a manual bottleneck

Lab panels produced large volumes of raw values, but the value to a provider or patient is the interpretation: what is abnormal, what it means, and what to do next. That read depended on expert time, which made it slow and uneven. Two patients with similar results could get different depth of explanation depending on who reviewed them.

The opportunity was to put a consistent, fast first-pass interpretation in front of providers and patients, while keeping clinical judgment in the loop where it mattered.

Task

Own the timeline and the requirements

My mandate covered both sides. I had to define what the AI flagged and how it interpreted results, the thresholds, the rules, and the right model for the job, and I had to drive the program that built and shipped it across engineering, clinical, and product. Getting the AI logic right and getting the rollout right were the same job.

Action

Shaping the logic, then driving it to live

tune

What the AI did

  • ruleThresholds & rules: worked with engineering and clinical to define what counted as normal, abnormal, or escalate, so flagging was explainable, not a black box.
  • psychologyModel selection: weighed model options against accuracy, interpretability, and the cost of a wrong call, and picked the fit for a clinical context rather than the flashiest option.
  • diversity_3Two audiences: shaped the interpretation so a provider got clinical depth and a patient got plain-language meaning from the same underlying result.
groups

How I drove it

  • account_treeCross-functional execution: aligned engineering, clinical, and product on one charter and mapped the dependencies between them so handoffs did not stall.
  • verifiedValidation gates: clinical sign-off on flagging behavior was a gate, not a courtesy, before anything reached users.
  • rocket_launchPhased rollout: expanded access in stages, watching behavior at each step before widening, on the way to 200+ users.
schemaEvaluation-suite architecture
Illustrative
labs

Raw lab data

Panel values arrive from the lab system as the input to evaluation.

arrow_forward
neurology

Evaluation engine

rule

Threshold & rule layer: normal / abnormal / escalate

psychology

Model: interpretation selected for clinical fit

verified_user

Clinical review gate: human-in-the-loop on escalations

arrow_forward
groups

Surfaces

Provider view with clinical depth; patient view in plain language.

Raw values pass through an explainable threshold and rule layer plus a fit-for-purpose model, with a clinical-review gate on escalations, then render differently for providers and patients.
account_treeAbnormal-result decision flow
Illustrative

Step 1

Read result

Compare each value to its threshold band.

arrow_forward

In range

Normal

Interpretation surfaced, no flag raised.

arrow_forward

Out of range

Flag

Abnormal marker with plain-language meaning.

arrow_forward

Critical

Escalate

Routed to clinical review before it reaches users.

The flagging logic was designed to fail safe: the more serious the signal, the more it leaned on a human, so the AI accelerated the easy reads and routed the risky ones to a clinician.
Result

Faster, consistent reads, with a human on the risky ones

groups

200+

users on rollout

bolt

Faster

first-pass interpretation

balance

Consistent

reads across patients

verified

Verified outcome: the evaluation suites rolled out to 200+ users, giving providers and patients a faster, more consistent first read of lab results while a clinical-review gate kept judgment on the calls that needed it.

02
Feature 02 · Practice Intelligence

Clinic analytics dashboard

A provider-facing dashboard where AI analyzed how a clinic was performing, from financial signals to patient interaction, and explained what it meant.

Situation

Plenty of data, no intelligent read

Providers ran on signals scattered across systems: financial performance on one side, patient interaction on the other. Seeing the numbers was possible; understanding what they meant for the health of the practice was not. The story was buried in spreadsheets and disconnected reports.

The opportunity was a single view that did not just display the numbers but read them: surfaced what was working, flagged what was not, and pointed at why.

Task

Deliver a dashboard that explains, not just displays

I led delivery of a provider-facing dashboard where AI analyzed practice performance end to end, from financial signals like revenue, collections, and reimbursement trends down to patient interaction metrics like visit volume, follow-up rates, and engagement, and turned them into an intelligent read on business health. The bar was insight, not a prettier report.

Action

From scattered signals to an explained view

insights

What the AI did

  • mergeSynthesized signals: combined financial and patient-interaction data into one read of practice health instead of two disconnected views.
  • lightbulbSurfaced insight: explained what was working and what was not, in words, rather than leaving the provider to infer it from charts.
  • trending_upFlagged trends: called out movement worth attention so a slipping metric did not hide inside a busy dashboard.
hub

How I drove it

  • account_treeData dependencies: coordinated the financial and interaction data sources across teams so the dashboard had one trustworthy feed.
  • rocket_launchPhased delivery: shipped in stages, validating each data domain before layering on the AI read.
  • handshakeStakeholder alignment: kept product, engineering, and the provider-facing teams aligned on what "useful" meant.
monitoringClinic analytics dashboard
Illustrative

Financial signals

payments

Revenue

request_quote

Collections

receipt_long

Reimbursement

Patient interaction

groups

Visit volume

event_repeat

Follow-up rate

favorite

Engagement

auto_awesome

AI insight: revenue is steady, but follow-up rate is trending down and is the likeliest drag on repeat visits. Worth a look at scheduling.

trending_down

Trend flag: follow-up rate down vs. prior period.

Bars and sample values are placeholders for layout. The point is the pattern: category tiles across finance and patient interaction, then an AI read that names the story and flags the trend, rather than leaving the provider to find it.
Result

An at-a-glance read on practice health

insights

Outcome: providers got a single, explained view of business health across financial and patient-interaction signals, with the AI surfacing what was working, flagging what was not, and pointing them at the trends worth acting on, instead of leaving the story buried in disconnected reports.

Deep Dive & Highlights Both features

Where AI product thinking met TPM execution

Across both features, the through-line was the same: I made the AI product decisions and I ran the program that shipped them. Three moments capture that intersection.

psychology

I specified the model, not just the milestone

Thresholds, rule logic, and model selection were product decisions, and I owned them with engineering. The schedule mattered, but so did what the AI actually decided, and I shaped both.

verified_user

Human-in-the-loop by design

For diagnostic AI, safe failure is the feature. I built clinical-review gates into the flow so the system accelerated the routine reads and deferred the risky ones to a clinician.

auto_stories

From numbers to narrative

The dashboard's value was the AI explaining practice health, not displaying it. Delivering that meant coordinating the cross-team data dependencies that made one trustworthy read possible.

Reflection Both features

What I'd do differently

Across both features, what I would change next time.

arrow_backAll projects mailDiscuss this work