VP by day.
Builder the rest of the time.
I lead pre-sales architects across North America for a leading database, cloud, enterprise applications, and AI company. On weekends I fine-tune small models, build RAG eval harnesses, and ship local LLM systems on an RTX 5090. This is the lab notebook.
When Every Developer Has an Agent
What happens when multiple developers try to work together on a project, and they each bring their own agent? It used to be easy to coordinate development efforts, but agents operate at an accelerated pace, moving quickly through codebases and spawning subagents. This is what we learned with a real team - four humans, four AI agents, and one shared codebase
Glassbox: Watching a Tiny LLM Learn
I built an 11.5-million-parameter LLM from scratch and instrumented it so you can watch it learn to tell stories - every word, every probability, every training step.
I built a terminal that knows when your AI is waiting on you
vibeflow is an open-source Linux terminal that shows, per tab, whether the AI agent inside is working or waiting on you — so you stop alt-tabbing to find the one that needs a reply.
How vibeflow knows what your AI agent is doing
A deep dive into how vibeflow detects per-tab AI agent state: the open OSC 1338 protocol, the /proc heuristic fallback, the trust rules that keep the indicator honest, and the bugs daily use and a pre-launch audit surfaced.
Robot Car: Origin Story (How Our Little Hero Got His Wheels)
I have a working robot car in my office. I've never built one. I didn't read the manual. Here's what the build looked like when the AI had the knowledge and I had the hands.
AIOS ThinkTank
What does an operating system look like when the user is an LLM? I'm building a robot car driven entirely by AI to find out — hardware, firmware, and the prompt layer that ties them together.
SLM Research
Field notes from testing the Specialized Language Model thesis: that small, fine-tuned models on the right data beat large general-purpose ones on the work I actually do.
Building a Knowledge Management App with Oracle AI Database 26ai
Building a multimodal knowledge base on Oracle AI Database 26ai — CLIP-in-database, JSON Duality, Vector Search, and a vision-aware RAG pipeline that actually sees images instead of describing their captions.
Building an SLM Powerhouse
Designing, building, and stress-testing a local workstation for fine-tuning specialized language models. RTX 5090, 22-hour training runs, and the part list that actually ships.