Side Projects
A small collection of side projects, built around things I’m curious about professionally.
Benefits Q&A Checker
Can an AI answer questions about your health plan without making anything up? A real RAG pipeline, chunked, embedded, and retrieved from six actual health plan documents, answers 88 real questions and gets graded on two separate things: did it find the right document, and did it get the answer right.
Full write-up on GitHub.
Access Policy Compliance Eval
Can a model keep three separate written policies straight at once, and get the right answer for the right reason? Three fictional companies, three full access policies, all sitting in the same prompt, graded on whether it picked the right policy, cited the exact right rule, and reached the correct decision.
Full write-up on GitHub.
Access Request Agent Evaluator
Can an AI be trusted to act on incomplete information, not just answer a question but decide what to do next? This one runs a full agentic loop: an LLM handles IT access requests with five real tools, look someone up, check policy, ask a question, escalate, or decide, tested against Claude Sonnet 5 and GPT-4.1 side by side.
Full write-up on GitHub.
Accessibility Fix Queue
Free accessibility scanners tell you what's broken, not what to fix first. This scans a live page with axe-core, then uses Claude to group violations by shared root cause, rank them by real-world impact, and draft a ready-to-file ticket for each one, the actual fix, not just the problem.
Full write-up on Github
Fluff & Pixel Studios
A solo indie game studio, mine end to end, with our 1st title available on the App Store (iOS - iPhone and iPad). Vibe-coded rather than hand-built line by line. Cozy, small, made with a lot of heart. Sign up at the page below for updates.