Matthew Newton

Startup CTO who scaled ML from prototype to production, with hands-on expertise in federated learning (Google), AutoML (Meta), and generative AI (Comfy Org).

View my full resume →

Recent Articles

Why We Ditched RAG for a 'Dumb' Solution (And It Worked Better)

We built a life insurance classification bot that matches clients with carriers based on medical conditions. Our initial implementation used what we thought was a temporary hack—letting the LLM pick and read files directly. After attempting to 'properly' implement RAG, we discovered our hack wasn't just simpler—it performed better.

Read more →