⚡ Free 30-min consultation · Booking Q2 now
Home Edge AI Local LLMs Agentic Engineering Mentoring Workshop Advisory Services Work Pricing Build Stories Contact About Book a Call

Notes from the build.

Build notes on agentic engineering, edge inference, hackathons, and what I'm learning while taking AI systems from prototype to production.

What Agentic Workflows Change About Problem Solving

A practical look at what agentic workflows change: smaller briefs, clearer evals, parallel work streams, sharper review, and faster technical learning loops.

Eight AI Builds in a Quarter: What the Reps Taught Me

Eight AI builds in one quarter turned agentic engineering from a productivity idea into a problem-solving method: smaller briefs, stronger evals, faster prototypes, and sharper technical judgment.

Winning Raw to Curated at GTC: A Local AI Workspace for Photographers

Studio Copilot won the Raw to Curated track at NVIDIA GTC's Hack to Create. The product is simple: a local AI workspace for photographers that handles culling, contracts, and client review without ever uploading a file. Here's why edge AI for creative professionals is genuinely the right architecture.

Three Simulated Bodies, One Brain: Building Toward Physical AI

At the Nebius hackathon the day before NVIDIA GTC, I worked on Sideline: one Cosmos Reason 2 loop controlling three simulated bodies. Same brain, three environments. Here's what worked, what didn't, and what simulation teaches about physical AI.

When Cosmos Reason 2 Watches a Tennis Match

I put NVIDIA's Cosmos Reason 2 on a Jetson and pointed it at amateur tennis. The model does more than see frames. It reasons about ball trajectory, line calls, and the physics of a moment. Here's what that buys, and where it falls down.

How Not to Flash Your Jetson: 19 Attempts and One Kernel Parameter

Two MacBook Pros, two operating systems, three flash tools, an OTA upgrade that bricked the bootloader, raw PyUSB debugging, and one kernel parameter change to flash an NVIDIA Jetson AGX Orin 64GB. Over 20 attempts across two days. Everything that went wrong and the one-line fix that finally worked.

From Vibe-Coding to Launch: The Four Stages Where Products Die

Most AI side-projects don't make it past stage two. Here's the funnel I now run every product through: what each stage is for, what kills you between them, and the gate that lets you move forward.

Porting Undervolt from Cloud to a Jetson Under My Desk

What changes when the same product runs on a $2,000 box under your desk instead of a per-token API. Latency, cost curves, what breaks, and the LiteLLM-as-router pattern that lets you flip between local and cloud without rewriting agent code.

Winning the NVIDIA DGX AITX Hackathon

One weekend, one Jetson, 2.3 million Austin construction permits, and a Nemotron Nano 8B running locally. The technical problem-solving behind the DGX AITX win.