My portfolio
Production native AI products across vector RAG, evals, audit pipelines, agents, and developer tools. Each row picks one slice of the AI stack and ships it end-to-end.
Foundation
Personal RAG Knowledge Base
A production-ready personal RAG system over 42,000+ knowledge documents — multi-workspace semantic search (LL work, MindX consulting, personal, shared research, AI vendor canon) accessible from Claude Desktop, Claude.ai web, and iOS app via the Model Context Protocol.
AI-Canon-Crawler — Authoritative Vendor Doc RAG
A sister tool to Personal-RAG that crawls authoritative AI vendor docs into a dedicated _canon workspace, with routing rules that prefer vendor truth for spec/price/version questions.
Eval-Framework — LLM Bake-off & Production Judge
A personal eval harness that turns LLM model + prompt + scorer decisions from gut-feel guessing into evidence-based answers via stratified eval sets, multi-provider bake-offs, and LLM-as-judge scoring.
Knowledge-Audit — Cross-Source Contradiction Detector
A 3-layer audit + 4-tier cron that catches stale facts and cross-source contradictions in a personal RAG knowledge base — caught 25+ drifted facts in 79 files on day-one deploy.
Vertical app
Health Coach — ADHD-mode Garmin Insights
A personal health coach over Garmin data lake with ADHD-friendly nudges. Daily morning ping + Saturday digest + Calendar pre-meeting breath alerts via Telegram. Goal — weekly avg sleep score ≥80.
Voice-Assistant — Native macOS AI Voice Assistant
Voice-first agentic assistant running native on macOS — push-to-talk or continuous mode, controls 40+ Mac actions (open apps, type text, click, browser tabs), searches personal KB, multi-LLM (Cloud Haiku / Local Hermes / Apple Foundation Models). Pure Swift, ~50MB DMG, no Electron.
Mail-Assistant — ADHD-first AI Inbox Triage
A local-first AI inbox triage layer that classifies threads P0/P1/P2/NOISE with cross-channel verification — cutting daily triage from 90 minutes to 8 minutes.
Lumi
The first conversational SMS for SEA preschools — teachers narrate the child's day by voice, principals run the school through chat. AI drafts, humans approve, the system executes.