AR

All Demos and Side Projects

Complete list of prototypes, tools, and research engineering experiments.

Live Demo

HEARSAY

A voice agent's safety guardrail checks what the speech recognizer wrote down, not what the caller said. HEARSAY reads the guard code, finds the handful of sounds its promise depends on, and tests the hearing exactly there with generated phone audio whose truth is known. Play the clips: the caller says fifteen, the line says fifty, and the guard approves the wrong transfer. It ships the promise with an honest envelope, certified on these lines, broken on those, untested elsewhere.

Whisperfaster-whisperClaudePythonGitHub Pages

Live Demo

GLASSBOX

An AI agent is dropped into a game it has never seen and recovers the rules as runnable code, tested cell by cell against every recorded observation. Includes invented rule variants that exist in no training data. Every reconstruction is decompiled back to code and playable.

Claude Opus 4.8NodeInsForgeGitHub Pages

Live Demo

RAGScope

Static retrieval debugger that shows where RAG failed: chunk split, metadata filter, or reranker regression. Each case includes gold support spans, counterfactual fixes, and answer claim audits.

JavaScriptGitHub PagesAstroJSON