01Complexity, made navigable
Gainful Employment
Help schools navigate evolving reporting requirements without losing flexibility or control.
Explore this projectDesigning trustworthy experiences for complex systems, human teams, and AI agents.
I’m Li Lu, a design leader and hands-on product builder. I create elegantly functional digital experiences, and I build the organizational capabilities that help design teams and businesses succeed.
My recent work sits at the intersection of UX and AI. I lead design for mission-critical AI/ML-enabled products, and I independently design and build agentic AI systems that explore persistent memory and context, multi-agent interaction, human oversight, transparency, and trust.
Before that I was Senior Manager of UX Design and Customer Experience Strategy at the National Student Clearinghouse, which serves 97% of U.S. higher education institutions, and I led work at MetroStar and Hubbell.
More about me- Experience
- 14 years in design research, 12 in product design
- Government and defense AI
- AI decision-support for the DoD’s Chief Digital and AI Office and the U.S. Department of State. Active Top Secret clearance.
- Design at scale
- Built the Excelsior design system from the ground up, adopted across eleven development teams, cutting redundancy and time to market by 60%
- Builds in code
- Sostenuto, an open-source memory layer for AI agents, and Lakehouse, a local-first multi-agent system
- Research
- Air Force–funded research on human-automation trust. M.A. in Human Factors and Applied Cognition, George Mason University.
A practice in evolution.
View all work
Selected work
-
Lakehouse: One Assistant, Many Harnesses
Designing continuity, coordination, and control in a personal multi-agent system.
-
Talking to the Assistant I Already Know
Designing voice and video for a personal AI assistant, with continuity, conversational control, and privacy at the center.
-
CONSORT: Turning a Clinical Registry into a Guided Experience
Redesigning a registry for hand and face transplant trials so its long forms read like a guided interview instead of a wall of fields.
-
AI-Enabled Policy Research Platform
Keep AI-assisted policy research traceable to its sources, including when evidence is insufficient.
-
Designing a Verifiable AI Health Experience
Give a person and an AI assistant a shared view of health data—and the limits of what it can support.
-
Conversation Trajectory Safety Framework
Make patterns across AI conversations visible while preserving human agency.
Recent writing
-
The Waterside Workshop: How My Homepage Was Made
I turned a room developed through conversations with ChatGPT into an explorable entrance to my portfolio, working with Claude to build it in Blender. A case study in creative direction, personal meaning, and designing with agents.
-
What Music Composition Reveals About Experience Design
Composition and experience design both involve giving an experience a structure that someone else will inhabit over time.
-
Beyond Personal Agents: Designing for More Than One Principal
As AI agents move into families, workplaces, and caregiving networks, the central design problem changes. The question is no longer only what an agent can do, but who it may do it for.