Christine Galligan  ·  Case Study 05
Case Study · Generative AI · Civic Infrastructure

Making healthcare policy legible — so participation is possible.

An NSF-backed generative AI platform that translates dense regulatory documents from CMS, FDA, and ONC into persona-specific explanations, gathers structured public comment, and submits it back into federal feedback systems. Built to close the gap between who healthcare policy affects and who actually shapes it.

Demo · CG Advocacy Platform · Beta
Role
Founder · Product Lead
Backing
NSF iCorps West · Microsoft AI Hackathon
Period
2023 — 2024
Stack
GPT-4 · RAG · NLP · CMS / ONC integration
Thesis

AI is not the product. It's the enabler. The product is a civic participation layer for people who have been shut out of policy conversations that shape their care.

Trust and transparency over accuracy. Co-creation over deployment. Emotional intelligence and systems design over model outputs.

The Problem

Three structural failures compounding into a participation gap.

Healthcare policy is written in language that excludes the people it governs. Feedback systems reward the actors who already have power. The public-comment infrastructure is a pipeline designed for institutions, not for patients.

Complexity

Policy documents from CMS, FDA, and ONC are dense and inaccessible.

Regulatory language is a barrier that deters community engagement before it starts. The people most affected by policy changes are the least equipped to respond to them in the window feedback is open.

Inequity

Current systems favor experts and institutional actors.

Rural voices, patients, and marginalized communities are systemically excluded from public comment periods — not because they have nothing to say, but because the system assumes legal fluency they were never asked to acquire.

Inefficiency

Manual review produces slow feedback loops and limited data utility.

Even when comments are submitted, the way they're analyzed doesn't turn them into actionable policy signal. Regulators receive noise; communities get no response.

The Solution

Three pillars. One stack. Built to translate in both directions.

An AI layer between federal policy documents and the public — designed to reduce cognitive load on the citizen side and improve signal quality on the regulator side.

01

Document Simplification

GPT-4 with a custom RAG architecture summarizes policies, translates jargon, and generates glossaries. Users can ask questions in natural language and receive persona-appropriate answers with source citations.

02

Persona-Based UX

Guided flows tailored to patients, advocates, hospital staff, and economists — each surfacing the parts of a policy document most relevant to their context, in the language that context uses.

03

Feedback Engine

Collects, clusters, and formats user submissions into structured packets for CMS and ONC public comment portals. Turns individual comment into thematic signal regulators can act on.

Process

How it came together.

01

Discovery

25+ NSF iCorps customer discovery interviews. Stakeholder interviews across hospital admins, rural health advocates, health economists, and policy researchers. Journey mapping and pain point identification.

02

Prototyping

Persona-based flow design, AI prompt engineering, data schema mapping. Early rapid prototypes built to test whether persona-specific explanation of a single policy actually changed comprehension.

03

AI Development

RAG architecture for document parsing, keyword extraction, and semantic clustering. Custom prompts for persona-specific Q&A and comment generation. Pipeline engineered for source-traceability and transparency.

04

Test & Deploy

Beta testing with hospital staff and policy researchers. CMS/ONC integration for real-time policy comment submission. Dashboard built to visualize feedback patterns and coverage gaps for regulators.

Results

Measurable change on every axis that mattered.

Before and after, across the four outcomes we set out to move: comprehension, accessibility, response time, and feedback quality.

Time to understand a policy document
2 — 3 hours of expert effort
Under 20 minutes, persona-guided
Policy comprehension across users
Low — accessible only to experts
High — accessible to patients, advocates, staff, and economists
Response time to comment periods
Manual delays; often missed windows
30% faster end-to-end
Feedback quality to regulators
Fragmented, vague, hard to cluster
Thematic, evidence-based, submission-ready
Stakeholder Impact

Different users. Different questions. One underlying architecture.

The platform was designed for three primary personas identified through NSF iCorps discovery. Each sees a different view of the same document.

Health Economist

Mapped policy changes to cost burden and regional economic strain.

Surfaces the fiscal implications of proposed policy — what it does to reimbursement, coverage, and regional health budgets over time.

Rural Policy Maker

Consolidated community feedback into actionable policy recommendations.

Aggregates rural-specific input and translates it into submission-ready language for comment portals — so rural voices arrive at CMS as signal, not noise.

Hospital Administrator

Identified funding gaps for rural rollouts.

Isolates implementation implications of policy changes — what it costs hospitals to comply, where the funding gaps sit, and what to ask regulators to adjust.

Technical Architecture

Four components. Built for transparency and control, not just capability.

01 · CUSTOM PROMPT ENGINEERING

Persona-specific Q&A and comment generation.

Prompt templates tuned per persona and per use case. Output formatted for downstream comment-portal submission, not for conversational output.

02 · NLP PIPELINES

Document parsing, keyword extraction, semantic clustering.

Pre-processing layer that structures dense regulatory text into retrievable chunks, surfaced to the LLM with source traceability preserved throughout.

03 · INTERACTIVE DASHBOARD

Visualizes feedback patterns and coverage gaps.

A regulator-facing view that turns individual submissions into thematic clusters, highlighting where comment volume is concentrated and where it's missing.

04 · SECURE SUBMISSION ENGINE

Comment submission with compliance-grade transparency log.

Every submission is auditable. Users see exactly what was generated, what was edited, and what was sent — preserving consent and public record integrity.

Strategic Insights

What I learned building generative AI for public infrastructure.

"Trust and transparency mattered more than accuracy alone."

In civic AI, a model that is 95% accurate but opaque performs worse than one that is 85% accurate and shows its reasoning. We over-invested in data stewardship and user control — which turned out to be the feature that actually drove adoption. Accuracy without provenance is just another black box.

"Co-creation with users was vital."

Diverse stakeholder input shaped everything from interface language to use case prioritization. Economists, advocates, hospital administrators, and patients used different vocabularies for the same concept — and getting that vocabulary right was the difference between a tool they used and a tool they abandoned.

"AI is not the product. It's the enabler."

Success hinged on emotional intelligence and systems design, not model outputs. The LLM was one component inside a larger choreography of trust, context, and control. Teams that reverse that ratio — model-first, experience-second — build demos, not products.

Reference
"Christine's standout quality is her constant curiosity, which she demonstrated in recent projects leveraging generative AI to drive innovation. Her contributions to projects involving CapsicoHealth's AI-driven analytics products helped demonstrate the value of these tools to stakeholders. Her ability to articulate the business and clinical implications of cutting-edge technologies makes her an invaluable collaborator in aligning AI capabilities with healthcare objectives."
Dr. J. Sairamesh CEO · CapsicoHealth

Applied AI that earns its place inside systems people already have to trust.

Open to senior strategy and applied AI roles at the intersection of healthcare, civic infrastructure, and public interest technology — particularly where research rigor, behavioral design, and engineering judgment all have to sit in the same person.

Start a conversation →
← All work · Christine Galligan