McKesson

AI-Assisted Design Pipeline: Governed design-to-code workflow for enterprise healthcare modernization

UX Research & Design Strategy Lead

Creating a faster path from design intent to implementation.

I built a VP-backed AI-assisted workflow connecting Figma MCP, GitHub Copilot, and Storybook — reducing design-to-handoff time from 12 weeks to 6–8 weeks.

The goal was not to use AI for its own sake. It was to shorten the path from validated design intent to implementation while keeping human judgment in the loop at every stage.

AI accelerates execution. Humans remain responsible for direction, validation, and approval.

Outcome

From scattered handoff to governed delivery.

Research and design intent was getting diluted between discovery, prototype, engineering, and implementation. The pipeline connected those stages into one continuous workflow with human review at every gate.

Time Saved
6–8 weeks

Per 12-week design lead cycle. Reduced buffer between research and engineering handoff.

Leadership Support
VP-backed

Senior Director and VP allocated dedicated engineering capacity outside regular roadmap commitments.

Adoption
Daily workflow

Adopted into the team's active delivery practice, not a one-time prototype.

Pilot Surface
Validated end-to-end

Proven in a sandbox pilot before applying to Treatment Readiness and Demand Forecasting.

The Problem

The opportunity was to connect research, design, and engineering into one continuous workflow.

The previous model required design to run a full release cycle ahead of engineering — a lead buffer of up to 12 weeks. At each stage, intent was reinterpreted: research findings moved into static mockups, mockups moved into handoff notes, and engineers built from those notes without a clear path back to the original decisions.

The opportunity

The gap between what research reveals and what engineering builds was not a people problem. It was a workflow problem. The pipeline was designed to close that gap — not by removing human judgment, but by reducing the number of times intent had to be re-explained.

Before Traditional Handoff Design Thinking ←→ SDLC: Disconnected
11 Steps 4 Feedback Loops ~6 wk Cycle Time
01
Research
02
Wireframes
03
Design Iterations
04
Stakeholder Reviews
Feedback Loop
05
Handoff Documentation
06
Developer Interprets Design
07
Build
08
QA / Design Review
Feedback Loop
09
Design Drift Corrections
Feedback Loop
10
Back-and-Forth Revisions
Feedback Loop
11
Release
After · In pilot today AI-Assisted Pipeline Design Thinking ←→ SDLC: Connected through AI
8 Steps 6–8 wk Saved Continuous Delivery
01
Research SynthesisHuman Validation
02
Figma MakeMultiple Concepts · Live AI Prototypes
03
AI-Assisted ReviewQuality gate before engineering
04
Figma Code Connect+ MCP
05
Implementation DirectionAI-assisted structure
06
GitHub Copilot RefactorDesign System Enforced
07
Storybook Validation
08
GitHub Release (Alpha Repo)6–8 weeks saved per 12-week cycle

The before model shows where intent weakened through sequential handoff. The AI-assisted model shows how research synthesis, live prototyping, design-system mapping, Storybook validation, and GitHub-aligned delivery carry decisions forward with less reinterpretation.

Governance

Human review stayed in the loop at every stage.

The workflow did not remove design judgment. It created a faster feedback loop while keeping human review, design-system validation, and enterprise constraints in place.

Human-led decisions

Problem definition, direction-setting, concept evaluation, and final approval stayed with the designer. AI accelerated execution at each stage — it did not make calls.

Enterprise constraints maintained

The pipeline used only approved enterprise tools — Figma, GitHub Copilot, Storybook — operating inside McKesson's security and compliance model, not around it.

Design-system validation

Every component passed through Storybook validation before product integration. Design system decisions were enforced at the code level through Code Connect and Copilot refactoring.

Validated before build

Live prototypes were reviewed by stakeholders and Customer Success before engineering commitment — moving feedback earlier in the cycle, not after build began.

What This Changed

Teams had a clearer path from insight to prototype to implementation-ready direction. The pipeline reduced the design lead buffer by 6–8 weeks per cycle — not by cutting corners, but by connecting the stages that were previously disconnected.

This work was built alongside the Treatment Readiness modernization effort. Finding the hidden work behind treatment readiness →