Work
Published work is produced with AI assistance — research, argument testing, data analysis, drafting, and critique. Each piece is organized so it can be revisited, challenged, and updated.
Contexts
Topics
← All topicsSoftware
Life Calibration Engine
A mobile-first PWA and agent-accessible MCP for life assessment, goal prioritization,
Personal Runway Calculator
A local-first calculator for estimating how many months liquid savings cover
OpenCode Go Chat
A browser-based chat interface for OpenCode Go with a deployed proxy for chat, search, fetch, and browsing tools.
LLM Benchmark Platform
A deployed benchmark platform for running role-based coding-agent evaluations across OpenCode Go models and tracking results over time.
Life Equivalence Calculator
A relocation decision-support app that compares gross salary, take-home income, local costs, family plans, retirement, and end-of-life wealth across Cologne and Boston.
Data Analyst AI Agent
AI-powered data analytics dashboard with natural language chat and real-time visualizations
V1 Staging Is Live
First artifact published through the staging deployment on ai-sandbox: API to Supabase to a stable URL, no deployment involved.
First Supabase-Published Artifact
Proving the canonical path: publish request through the Publishing API into Postgres, rendered without any deployment.
Agent Native Applications
A first-principles definition of agent native applications: software products reorganized around delegated intent, governed AI agents, and supervisory interfaces, with email as the central example.