production
Daily reflection coach delivered via Telegram. One prompt a day, rooted in stoic philosophy and behavior change. Running live — I use it every morning.
building with AI · learning in public
Using AI agents
for real personal projects.
Not demos. Not toy examples. I'm using Claude, Grok, and a small fleet of agents to build things I actually use — a daily reflection coach, a book, a fitness tracker, automation pipelines, and the coordination layer that ties them all together.
Projects
What I'm building
Each of these is a real project I use or am actively developing — built with AI assistance as a first-class part of the workflow.
published
A short book about choosing the right standard instead of endlessly proving you are enough. Published on Amazon as No Longer Average. The writing loop is closed.
production
Telegram-first food, workout, weight, and macro tracking. Hermes handles logging, a noon tickle, and an 8pm plan-vs-actual report. Live now, with InBody checkpoints in the tracker and a 2,900-calorie cut plan.
active
The coordination layer that connects Hermes, Grok, Claude Code, and Codex. Handoffs, chain tracking, watcher automation — the infrastructure behind everything else. This site was built by it.
prototype
Python pipeline that reads tax documents and auto-fills a 1040 workbook. Practical automation for a real annual pain point — built in a weekend with Claude Code.
active
SVG interactive visualization of real agent delegation chains. Built by Claude Code orchestrating Codex across two phases — the toolchain that built this site, visualized.
live
40 agents learn to find food using tiny neural networks and a genetic algorithm — entirely in your browser. No API calls. The AI trains from random weights every session. Watch winners grow, laggards die off.
gene-toolbox
Personal utility scripts and automation helpers. The scaffolding is there, actual utilities are TBD as I hit recurring friction points.
Experiments
How the agents coordinate
The most interesting ongoing experiment: using AI agents as a real system, not just chat sessions. Handoffs, chain tracking, watcher automation.
Live system
Grok sets direction. Claude Code implements. Codex handles bounded sub-tasks. Hermes connects everything to Telegram. This site itself was built via that loop.
The chain registry tracks every Grok→Claude→Codex delegation. The interactive visualizer on the Experiments page shows the actual chains.
4
Active agents
3
Completed chains
1
Active chains
∞
Edge cases found
May 30, 2026
Strategy R resolved — registry lookup
Chain parent resolution now uses registry instead of fragile filename parsing.
May 31, 2026
Session limit detection live
Watcher detects usage limit hits, sends Telegram alert, auto-retries.
May 31, 2026
Phase 1 website build
Claude Code built this site as orchestrator across 3 phases. Shipped, post-delivery QA closed.
Jun 10, 2026 — now
Evolution Arena
Galaga replaced with a zero-cost AI experiment: neuroevolution arena with 40 neural-net agents, genetic algorithm, competition mechanics.