A semester-long studio bridging learning theory with real-world design practice. I worked with Harvard's Teaching and Learning Lab (TLL) on a university-wide Data Fluency initiative — a foundational program to help staff across all Harvard schools build practical data literacy skills.

The course began with deep exploration of learning theories — Cognitivism, Constructivism, and Connectivism — and their application to adult learners. Through extensive stakeholder engagement and discovery work, I learned that the problems Harvard staff actually faced were very different from what we initially assumed. This gap between assumed and surfaced problems became the defining lesson of the semester.

The portfolio records how I thought about the data fluency course and how my thinking moved as I learned new concepts. In the spirit of visible thinking, it serves as a place to showcase the artifacts I make and the reasoning behind them — legible to me and to anyone learning alongside me.

Capstone

T127 Course Capstone: Generative UI for Education

completed

A proof-of-concept generative interface that scaffolds personalized learning modules for Harvard's data fluency course. The system adapts to each user: rendering structured support (worked examples, guided steps, glossary panels) for novices and progressively stripping it away as the learner model indicates competence.

User answers to dynamic questions help build a Harvard-wide data dictionary through learnersourcing. This creates a richer content base that can be cross-referenced by learners in the future. Quality control is managed through a tight, inspectable, open-source ingestion pipeline.

Key details: ~$300/50k UI generations · Open-source · Portable to standard LXP iframe · Human-in-the-loop design philosophy

Semester Journey

Supporting Artifacts

Key Takeaways