AI as LabMate

Redesigning research workflows by turning LLMs into reliable, intuitive research mates.
Agentic UX
Design System
LLM Interaction Design

Client

Michigan Medicine

Date

Nov 2023 - Present (1.5 yrs)

Role

Product Designer

Lab Website

https://jieliu6.github.io/

Background

The current lab ecosystem is like a maze—research functions are scattered across multiple platforms, requiring researchers to constantly switch between systems with complex and inconsistent workflows.

The lab also wants to embrace AI into their research workflows.

My Role

• End-to-end web platform design
• Redefine research workflow with AI capacities & limitations
• Created prompt-oriented UI design

01.
Understand the design context

Background Research

As genomic research is deeply technical and domain-specific, I collaborated closely with researchers and developers to understand their workflows, pain points, and goals.

What are researchers complaining about in the interview?

Pain points found in the user interview and the heuristic evaluation

🤨

Tedious processes

“It’s annoying to switch between platforms all the time. Can we just combine them?”

🧐

Hard to Read

“The results are all graphs and dense papers. I don’t know where to look.”

🤯

Not Smart enough

“I often struggle to tell the platform what I’m actually searching for.”

What are the highlights and AI opportunities of our lab?

By understanding what our custom-trained model can do—and where it excels—we identified actionable UX opportunities that go beyond prompt tuning to shape trustworthy, insight-driven AI experiences.
In the next section, I’ll walk through how these insights shaped a redesigned AI-assisted research workflow.

02.
Redefine
research workflows

Dancing with Complexity

To redefine our platforms into an all-in-one, AI-based platform, I had more workshops with our researchers and started by mapping the original workflow and identifying AI touchpoints.

What are the AI touchpoints in current workflows?

The yellow-highlighted steps mark where we decided to introduce AI.
Too complex, let's simplifie it.

Redefining the workflow with AI

From question to insight—faster, smarter, and more intuitive.

03.
Design
Human-AI Interaction

Design with AI, and its limits

Balancing the power of AI with human control, trust, and transparency.

AI's Pros and Cons & Our Design Solutions

✅ AI's strength

Understand natural language questions.

❌ AI's limits
May misinterpret ambiguous input.
🙌 Design solution:
Surface the AI-parsed query and let users refine it.
✅ AI's strength
Retrieve and summarize knowledge from graphs and literature
❌ AI's limits
Can generate hallucinated or outdated content
🙌 Design solution:
Support traceability with cited sources.
✅ AI's strength
Suggestive query design
❌ AI's limits
Lack of precision for expert use cases
🙌 Design solution:
Manual override: switch back to traditional search mode for advanced query crafting

Prompt-oriented Component Design

Context Steering
A UI module that lets users select graph nodes or summary segments to inject into the prompt, enabling fine-grained control of dialogue context.
Boosts relevance, reduces ambiguity, and reinforces user agency.

More High-fidelity prototypes

04.
Takeaways

Designing for AI-first Products

In this project, I approached the Large Language Model not just as a backend engine, but as a design material with unique properties: unpredictable, context-sensitive, and deeply conversational.
‍
‍
To support effective human-AI interaction, I designed a system where:
‍
💬 Context becomes the interface — Users shape what the AI knows through intuitive selection of graph nodes and summaries.
‍🤖 Prompting is embedded in interaction — Instead of typing prompts, users engage with structured components that generate meaningful inputs under the hood.
‍🩵 Trust is built through transparency and control — By letting users steer context and inspect what the AI sees, we restore agency in a probabilistic system.

‍
This is AI product design that goes beyond prompting — it’s about crafting semantic environments where AI and humans co-create meaning.
NomNow