~/projects

Selected Work

Projects that represent how I think about AI systems, product design, and engineering leadership. Each one taught me something worth showing.

01 live flagship

Multi-Agent OpenClaw Orchestration

Built a role-based multi-agent system with explicit orchestration, specialist routing, durable memory, and handoff workflows. The goal was not impressive demos. It was reliable AI work across sessions.

Agent Architecture Orchestration Memory Design OpenClaw
View case study
02 live flagship

Jarvis: Hermes AI Operating System

A persistent, always-on AI operating system built on Hermes Agent. Layered memory, a 125-skill library, a 590-file Obsidian knowledge vault backed by GitHub, and cron-driven autonomous workflows. Accessible from anywhere via Telegram.

Hermes Agent Python Obsidian Telegram Cron Automation OpenAI
View case study
03 live

Employee Communication Simulator

Built a simulation platform for testing how leadership messages land across a 450-person org. Weighted personas, Monte Carlo scenario analysis, multi-provider LLM integration, and executive-ready reporting in PDF and PowerPoint.

Python React 19 Multi-LLM Monte Carlo Executive Reporting Decision Support
View case study
04 live

Browser Workflow QA Agent

An AI agent that performs structured QA on live websites. Navigate pages, audit console state, capture desktop and mobile screenshots, produce evidence-backed PASS/WARN/FAIL reports. Triggered by a single Telegram message.

Python Browser Automation Agentic Workflows Telegram QA Engineering TDD
View case study
05 live

Agent Trust Control Plane

Built a local governance layer for AI agents. Every proposed action is classified as allow, approval_required, clarification_required, or blocked. YAML policies, deterministic risk classification, human approval gates, and JSONL audit trails.

Python Policy Engine Risk Classification Audit Logging Agent Safety
View case study
06 live

OpsCore Dashboard

A real-time operational dashboard for monitoring containerized AI services on a VPS. Python metrics agent on the server, Next.js frontend on Vercel, remote visibility into CPU, memory, disk, and container health.

Next.js TypeScript Python Docker Traefik Vercel
View case study
07 live

Durable Memory for AI Agents

A reliability engineering case study on making long-running AI systems trustworthy. Explicit source-of-truth artifacts, retrieval rules, and handoff workflows. The kind of work that matters on Tuesday morning, not just when everything is going well.

Reliability Memory Design Agent Systems Durable State Operational Hygiene
View case study