An AI tutor for programming education that allows students to ask questions within their programming environment while receiving constructive feedback and guidance. The AI Tutor is designed to not give away answers, but rather to help students think through problems and learn effectively. This project is supported by the National Science Foundation (NSF).
Computational notebooks such as Jupyter are widely used by scientists given the ease to explore data and record findings in an integrated way. However, explorations can clutter up easily and lead to messes, while some notebook users hope to maintain notebook clarity throughout the authoring process. I built a prototype notebook system that supports the always-clear notebook authoring paradigm. A user evaluation shows that the system helps users maintain notebook clarity without compromising usability.
AI-generated code is helpful as building blocks towards a complete program, but validating the behavior of such code is not easy. What if we utilize live programming to facilitate the validation of AI-generated code? We built a prototype incorporating live programming and an AI-powered program synthesizer and probed its effects through a user study. Our results demonstrate the effectiveness of live programming in validating AI-generated in mitigating over- and under-reliance on the AI and lowering the cognitive load.
I developed the Z3 Guide, a 100% client-side web-based educational environment for logic modeling with the Z3 SMT solver. The development of Z3Guide adopted an iterative design with Z3 educators. Since deployment, it has been well perceived by educators and students of logic modeling and Z3. It is also a first step towards reviving rise4fun, a legacy web environment for research tools developed at RiSE @ Microsoft Research. This work was done during my internship in summer 2022 at Microsoft Research. See my fork of the version concluded at the end of my internship, or here for the most recent official Z3 Guide.
GUI applications often preserve complex behavior building upon at least three layers of information: GUI changes, code execution, and user-interactions. To help programmers reason about the behavior of GUI applications during debugging, I built a live programming environment that directly displays a time line of intermediate GUI states upon user interactions with the GUI. Without using logs or breakpoints, users can see a timeline of changes in the GUI and their connections to the code in the tool, and such information is always up-to-date to the code.
Built on top of SnipPy, SnipPy+ features a new interaction flow where the user can constantly interact with the synthesizer without leaving and restarting the specifications writing process: they can (1) see synthesis results as they are typing in specifications and (2) keep modifying the specifications / inspecting new synthesis results, until they intend to exit the process.
I explored the idea of PopPy in collaboration with Kasra Ferdowsi in a class project. Also built on top of SnipPy, PopPy allows the user to write partial instead of full specifications for program synthesis, which can be especially useful when the specs involve long, complicated data structures.
We used Projection Boxes, a Live Programming visualization, in an introductory programming class with 600+ students at UCSD over one academic quarter, and found that students preferred Projection Boxes to the baseline IDE and considered them helpful for their learning.
Venbrace is a textual representation for the block-based MIT App Inventor. Its design is principled and empirically evaluated through two user studies. Although no conclusive evidence was found from either study, this project is my first exploration in the space of human-centric programming language design.
TwitterTrails is a tool that allows members of the media to track the trustworthiness of stories shared on Twitter co-built by Panagiotis Metaxas at Wellesley College. My prototype visualizes the stories (circles) and their tags (linked lines connecting the circles to the dots on the outer bigger circle) alongside their magnitudes of spread (sizes of circles) and levels of trustworthiness (blue=undisputed, red=doubtful) as determined by TwitterTrails’ algorithm. With this interactive visualization, users are able to focus on stories/tags of their interest through the filtering mechanism and interpret metrics of a story more easily without examining its associated tweets.