Projects
These aren't polished products - they're explorations. Each one digs into how data, language models, and software engineering can work together to solve real problems I've encountered. If you're curious about me and my research, feel free to explore my insights page.
LegalReasoner: A Framework for Legal Document Analysis and Reasoning
Developing AI systems that model explicit relationships between legal concepts, cases, and statutory provisions.
GraphRAG for Education: Addressing Knowledge Representation Gaps
Inspired by Harvard's work with CS50.ai, this AI teaching assistant maps conceptual relationships within educational content
Automated Unit Test Generation: Making Reliable Code Less Painful
Built a systematic pipeline that generates Python unit tests from docstrings, then uses mutation testing to verify the tests actually catch bugs
The Hunt for Flaky Tests: When Code Analysis Meets Reality
Building tools that help ML teams ship more reliable software
Systematic Prompt Engineering for Code Generation
A methodical evaluation of prompt improvements on HumanEval using Gemini 1.5 Flash.