Stella

The healthcare industry faces a major data accessibility problem. Care managers often wait weeks or even months for critical patient information because data lives in siloed systems, requires manual extraction, and arrives too late to support timely interventions. This delay affects decision-making, quality of care and overall patient outcomes. These bottlenecks also allow healthcare costs to inflate, which gets expensive. (estimated at $25–45 billion annually in the U.S.).

During my internship at Blue Shield of California, senior leadership tasked a PM intern, an engineering intern and me with creating a solution to this challenge. We had three weeks from initial concept alignment to presentation to the C-suite of Stellarus, BSC’s technology arm. Our goal was to explore whether generative AI could help care managers access reliable patient data more quickly and independently.

My team and I built Stella, a proof-of-concept generative AI chatbot that retrieves and summarizes patient information through natural language queries. The prototype demonstrated how AI could streamline data retrieval, reduce bottlenecks, and empower care managers to make informed decisions faster. Stella ultimately served as validation for future investments in AI-driven data tools at BSC.

My Role

UX Designer & Researcher

Worked with: PMs, engineers, designers, directors, leadership

Timeline

June 2025 - August 2025

Roles/Responsibilities

Led UX design & research
Storytelling
Envisioned future-state
XFN collaboration
Prototyping & development

Tools Used

Figma
Adobe Photoshop
Roo Code
OpenRouter

The Main Problem

Care managers don’t receive necessary data on time, often waiting weeks or even months for key data reports.

My Deliverables

How Did I Solve This?

3 Screens

I designed 2 chatbot screens and one future-state mockup showing Stella integrated into an existing Blue Shield platform.

1 Style Guide

This project was created under the company Stellarus, the technology arm of Blue Shield. I created a new design system combining elements of Blue Shield’s UI system with Stellarus branding.

In addition to designing the product, since we had such a short amount of time to present it I worked directly with the engineering intern to aid in the development of Stella through Roo Code, OpenRouter and minor CSS.

Vibe Coding

Meet Stella

A generative AI data query tool that allows care managers to instantly access vital patient data to more effectively administer individualized care through natural human language queries.

*Screens partially blurred to protect NDA

*No real personal health information is shown here, the display text above is pulled from a JSON document containing artificial patient data.

Initial Thinking

  • How do care managers currently request, receive, and use patient data in their daily workflow?

  • What barriers currently exist that prevent care managers from accessing data? Who do they rely on for data?

  • How does delayed or inaccurate data affect care managers’ ability to support patients?

Key Research Findings

To understand the problem space, I worked with the UX team to synthesize extensive existing research from the development of Care Connect, Blue Shield’s primary care management platform. This included analyzing historical interview data, workflow studies, and pre- and post-launch personas to surface longstanding issues that continued to affect care managers today Knowing Stella would be an internal product, we tailored our synthesis to focus on internal workflows, data access barriers, and system usability challenges unique to Blue Shield’s care managers.

Target Users

  • Care managers at Blue Shield of California (internal company usage only).

Deployment

  • GenAI chatbot that pulls from all existing Blue Shield from a centralized database.

Research Methods

  • Analyzing previous care manager research.

  • Partnering with engineering to understand how data is structured, accessed and managed at BSC.

Guiding Questions

Navigating Challenges

A Few Bumps in the Road

The path to creating Stella was NOT straightforward. Early in the internship, our team faced significant ambiguity around what we were supposed to build. Requirements shifted weekly, sometimes even multiple times within the same week, as leadership aligned on priorities for our project. Our first concept not remotely similar to what Stella ended up becoming, it wasn’t even in the field of care management. This created numerous challenges, namely:

Unclear Scope and Direction

Compressed Timeline

Stakeholder Communication

To manage the unclear scope, I focused the team on features that supported the core concept and held frequent alignment sessions across our intern teams to quickly assess feasibility as priorities shifted, which prevented scope creep and saved significant time.

With only 3 weeks to work on Stella from conceptualization, we had to build fast. I designed while prioritizing essential functionality and fast iteration, additionally learning how to use OpenRouter and RooCode to aid our engineer with development.

To navigate the lack of clarity, I kept close communication with my UX team to avoid redundant work and escalated any ambiguity from our intern team to my manager, whose involvement helped align leadership on the project and clarify our direction.

So What Was Stella’s Impact?

Informing Blue Shield’s Future

Stella was developed as a proof of concept project, meant to validate if use of a GenAI chatbot to query a centralized data base would allow care managers to work more effectively and efficiently. The prototype demonstrated clear business value by showing care managers could retrieve accurate data both more quickly and independently.

Validating Business Viability

Stella was technical feasibility and proved to have user/business value by showing that it could create meaningful reductions in the time it takes to get data. This confirmation gave Blue Shields’s leadership confidence to commit to larger-scale investments in similar tools to solve the data problem, one of which is currently being developed.

Guiding Future Decisions

As the first tool of its kind at BSC, Stella became a reference point for shaping future internal data products. Its success helped answer key strategic questions, confirmed that care managers would adopt this approach and now informs the development of a new enterprise data tool built on the same foundational concept.

*Mockup of Stella integrated into a current Blue Shield of California product used to prove integration feasibility with existing systems.

Reflection and Learnings

Adapting to Change

My internship at Blue Shield of California can be summed by the word adaptability. I had to stay agile as project scope shifted multiple times, rethink work that had already been started, pivot frequently and apply tips and tricks from my incredible team taught me on the fly. This pace pushed me to learn new tools and adjust my usual workflow to keep the project moving forwards.

Manager Feedback

POV: Working With Danial

Thank you for reading :)