I'm the CTO and Chief AI Officer at Coditas, where I help teams move from AI PoCs to systems that actually run in production—clean architecture, agentic workflows, and engineering sanity.
I've been doing this for over a decade, working with startups, early products, and large organizations across their tech journeys. These days, my focus is on helping teams adopt agentic AI in a way that's reliable, observable, and grounded in real-world constraints.
In my free time, I vibe code—experimenting with hardware, LLMs, agents, and odd ideas that usually teach me more than any framework doc ever could.
This site is where I share those learnings.
I built a mini agent harness in JavaScript, fine-tuned Qwen3-0.6B on my RTX 3060 to be its brain, and ran the whole thing over WebGPU — no server, no API keys. The model went from 30% to 77.5% on a prior-auth review task. The GPU crashed four times during training and quantization turned out to be the real boss fight.
Read more →I fine-tuned a real model on my RTX 3060 to settle an argument: fine-tuning teaches a model how to behave, not what to know. The model learned a perfect persona — and confidently invented every fact it was asked. Here's the experiment, the four broken adapters it took to get there, and the live demo.
Read more →Turning a reverse-engineered thermal printer into something anyone can use — with AI image generation and a simple web UI.
Read more →A personal account of reverse-engineering a thermal printer, learning BLE from scratch, and working alongside claude code that compressed weeks of debugging into a single weekend.
Read more →