Web app
AI Deployment Calculator
Estimates VRAM and recommends GPUs for inference, embeddings, vision, image diffusion, and fine-tuning based on task, model size, quantization and batching.
Engineer in the Loop, San Francisco
Human in the loop. Build tech to survive first contact.
I did time at FAANGs as a SWE and then Forward Deploy Engineer / Partner Engineer, a recent stint in VC, some stealthy startup time. Now I build apps with my AI interns, with a lot of quality checks. I'm the engineer who groks the business. Ship the thing that moves the number.
Currently Working on
Python LoopGate Harness
Recent Projects
Developer tool
LoopGate Harness
A quality-driven loop harness for agents. It loops agents through verification gates, leaving engineers free to scheme.
Web app
Comfyday
For teens, for fun. A tiny weather-to-outfit app for what to wear today. Enter a ZIP code, check weather, get a weather-specific outfit.
AI eval case study
Inference Conference
Three AIs walk into a frontier lab. This is what happened.
Classic Full Stack Web App
Rent or Own
A quick attempt to answer the forever debate, rent or own?
What I Care About
Thoughtful adoption, not hype. Minimalism, not line count. Evidence, not guesses. And moves regardless of the crowd. Curious about: AHI (agent-human-interaction), the evolution of evaluations, and the practical mess of using AI to build.
Loops
Everything comes full circle. Fresh context, clear specs,
commiting, and quality. In life and in code.
Evaluation that bites
Measure the path, audit the source, and treat confident
wrongness as worse than refusing to guess.
Practicality
Elegance in less. Clear interfaces. And enough empathy that the
next human gets it.
Find Me
repos and writeups