Epic's AI Design System

Epic's AI Design System

Designed and led Epic’s AI UX design system, standardizing AI patterns across 80+ apps used by 60,000+ clinicians.

Designed and led Epic’s AI UX design system, standardizing AI patterns across 80+ apps used by 60,000+ clinicians.

Role

Lead UX Designer

Role

Lead UX Designer

Disclaimer: Due to IP restrictions, this case study only includes conceptual visuals. Actual Epic designs and assets cannot be shared.

Disclaimer: Due to IP restrictions, this case study only includes conceptual visuals. Actual Epic designs and assets cannot be shared.

Designing an AI UX System for 80+ Clinical Apps

Designing an AI UX System for 80+ Clinical Apps

Designing an AI UX System for 80+ Clinical Apps

As the leader in electronic health records (EHR), Epic is rapidly integrating AI into clinical workflows. To prevent friction from inconsistent UX and trust issues, I helped build and maintain a structured AI UX design system for clarity, efficiency, and cross-enterprise integration.

As the leader in electronic health records (EHR), Epic is rapidly integrating AI into clinical workflows. To prevent friction from inconsistent UX and trust issues, I helped build and maintain a structured AI UX design system for clarity, efficiency, and cross-enterprise integration.

Epic’s AI Expansion in the News

Epic powers healthcare for over 300 million patients, with AI playing a growing role in clinical decision-making.

Epic’s AI Expansion in the News

Epic powers healthcare for over 300 million patients, with AI playing a growing role in clinical decision-making.

Epic’s AI adoption is making headlines, but scaling it across 80+ apps required a cohesive design system. Here’s how we solved it.

Epic’s AI adoption is making headlines, but scaling it across 80+ apps required a cohesive design system. Here’s how we solved it.

The Challenge

Bringing AI to 80+ Epic apps wasn’t just a technical challenge, it was also a design one. Adoption depended on a consistent experience so clinicians didn’t have to relearn AI in every feature, clear transparency and control to build trust, seamless integration into existing workflows, and ethical safeguards to ensure responsible AI. Without strong and consistent UX, AI adoption would struggle.

The Challenge

Bringing AI to 80+ Epic apps wasn’t just a technical challenge, it was also a design one. Adoption depended on a consistent experience so clinicians didn’t have to relearn AI in every feature, clear transparency and control to build trust, seamless integration into existing workflows, and ethical safeguards to ensure responsible AI. Without strong and consistent UX, AI adoption would struggle.

The Challenge

Bringing AI to 80+ Epic apps wasn’t just a technical challenge, it was also a design one. Adoption depended on a consistent experience so clinicians didn’t have to relearn AI in every feature, clear transparency and control to build trust, seamless integration into existing workflows, and ethical safeguards to ensure responsible AI.

Without strong and consistent UX, AI adoption would struggle.

The Solution

With the speed and scale of development, we had to quickly design and implement a thorough design system to keep AI consistent, usable, and trustworthy across 80+ apps. I helped lead this effort, later taking ownership of its evolution and maintenance. This included establishing design patterns to unify AI experiences, guiding teams on intuitive AI integration, equipping designers and developers with self-service UX resources, and educating leadership and customers on AI’s impact. These efforts created a scalable foundation for AI at Epic.

The Solution

With the speed and scale of development, we had to quickly design and implement a thorough design system to keep AI consistent, usable, and trustworthy across 80+ apps. I helped lead this effort, later taking ownership of its evolution and maintenance. This included establishing design patterns to unify AI experiences, guiding teams on intuitive AI integration, equipping designers and developers with self-service UX resources, and educating leadership and customers on AI’s impact. These efforts created a scalable foundation for AI at Epic.

The Solution

With the speed and scale of development, we had to quickly design and implement a thorough design system to keep AI consistent, usable, and trustworthy across 80+ apps. I helped lead this effort, later taking ownership of its evolution and maintenance.

This included establishing design patterns to unify AI experiences, guiding teams on intuitive AI integration, equipping designers and developers with self-service UX resources, and educating leadership and customers on AI’s impact. These efforts created a scalable foundation for AI at Epic.

The Outcomes

240

+

organizations using AI

0

K+

end users using AI features

0

M+

AI-generated messages & summaries

AI is reducing administrative burden, scaling adoption, and enabling smarter, human-centered experiences. More insights are available on Epic’s website.

Epic’s generative AI is making healthcare more efficient, helping clinicians work faster and communicate better.

The Outcomes

240

+

organizations using AI

0

K+

end users using AI features

0

M+

AI-generated messages & summaries

AI is reducing administrative burden, scaling adoption, and enabling smarter, human-centered experiences. More insights are available on Epic’s website.

Epic’s generative AI is making healthcare more efficient, helping clinicians work faster and communicate better.

The Outcomes

0

M+

AI-generated messages & summaries

0

K+

end users using AI features

240

+

organizations using AI

Epic’s generative AI is making healthcare more efficient, helping clinicians work faster and communicate better.

AI is streamlining workflows and reducing admin burden. See more outcomes on Epic’s website.

AI UX Beyond Epic

Building Epic’s AI design system taught me how to balance automation with human oversight, make complex AI feel intuitive, and build trust in high-stakes settings. But every AI product, healthcare or not, needs clarity, transparency, and a strong UX to succeed.

Great design can make or break an AI experience, and I’m bringing that knowledge to teams shaping the future of AI.

Have an AI experience to design?

AI UX Beyond Epic

Building Epic’s AI design system taught me how to balance automation with human oversight, make complex AI feel intuitive, and build trust in high-stakes settings. But every AI product, healthcare or not, needs clarity, transparency, and a strong UX to succeed.

Great design can make or break an AI experience, and I’m bringing that knowledge to teams shaping the future of AI.

Have an AI experience to design?

AI UX Beyond Epic

Building Epic’s AI design system taught me how to balance automation with human oversight, make complex AI feel intuitive, and build trust in high-stakes settings. But every AI product, healthcare or not, needs clarity, transparency, and a strong UX to succeed.

Great design can make or break an AI experience, and I’m bringing that knowledge to teams shaping the future of AI.

Have an AI experience to design?

Disclaimer: Due to IP restrictions, this case study only includes conceptual visuals. Actual Epic designs and assets cannot be shared.

📢 Full Case Study In Construction!

📢 Full Case Study In Construction!

A deeper dive into this case study is in the works, but if you want to hear about it now, let’s chat!

A deeper dive into this case study is in the works, but if you want to hear about it now, let’s chat!

Deep Dive: Designing Epic's AI Future

Deep Dive: Designing Epic's AI Future

Deep Dive: Designing Epic's AI Future

Epic's Scale Meet's AI's Speed

Epic is the largest EHR provider in the U.S., supporting 325 million patient records across 2,600+ hospitals and 80+ applications.

After the release of ChatGPT, in just a few months Epic launched AI tools across its platform - partnering with Microsoft and others to enable summaries, message drafting, and clinical support.

By 2025, 330+ orgs were live with these tools, 60,000+ clinicians used them, and 50M+ outputs had been generated.

A system this large moving this fast needed design standards that could keep up.

Epic “Health Grid” (80+ apps across)

The Challenge: 80+ Apps, 1 AI Experience

Each of Epic’s 80+ apps were building AI features on separate timelines, with different scopes and inconsistent UIs. Without shared standards, experiences were fragmented, confusing, and hard to scale.

Developers lacked reusable components. Designers had no guidance on interaction patterns. Teams were solving the same problems in silos, with no clear rules for building, validating, or improving AI.

In a system this large, speed without alignment risked trust and slowed delivery.

Epic needed a unified foundation: reusable tools, consistent UX patterns, and clear principles to scale AI responsibly across the ecosystem.

The Solution: Creating Epic's AI Design System

With teams moving fast, I worked with another designer to lead the creation of an end-to-end design system - defining patterns, crafting a distinct visual identity, and building scalable guidelines for implementation.

Defining Core AI Patterns

I began by auditing in-flight and upcoming AI features. Despite the variety, nearly all features mapped to four core interaction patterns:

Summarization

Summarization

Condensing clinical notes, conversations, or chart data into brief summaries to support faster decision-making.

Condensing clinical notes, conversations, or chart data into brief summaries to support faster decision-making.

Drafted Text

Drafted Text

Generating editable message replies, documentation, or orders for clinicians to review and finalize.

Generating editable message replies, documentation, or orders for clinicians to review and finalize.

Transformed Content

Transformed Content

Reformating technical or clinical information into patient-friendly language or role-specific context across Epic tools.

Reformating technical or clinical information into patient-friendly language or role-specific context across Epic tools.

Task Automation

Task Automation

Triggering actions like task creation, documentation, or order suggestions based on AI analysis.

Triggering actions like task creation, documentation, or order suggestions based on AI analysis.

This pattern-first framework helped teams speak a common language, make design decisions faster, and stay aligned as new features emerged. It also provided a clear foundation for reusable UX and development.

Establishing a Distinct Visual System

To maintain user trust, we needed a clear, consistent way to signal when content was AI-generated. I developed a new style system that felt modern and differentiated from the core clinical UI:

A fresh icon system

A fresh icon system

Modern & unique AI-specific icons for distinction.

Modern & unique AI-specific icons for distinction.

Distinct colors & gradients

Distinct colors & gradients

Custom styling to highlight AI-generated content.

Custom styling to highlight AI-generated content.

Imagery & signifiers

Imagery & signifiers

Visual metaphors that enhance AI understanding.

Visual metaphors that enhance AI understanding.

Naming & branding

Naming & branding

Consistent names and branding for AI features.

Consistent names and branding for AI features.

The goal: make AI outputs recognizable, usable, and appropriately cautious - without overwhelming the clinical experience.

Case study in progress