Hello, I'm Matt!
I've spent 20+ years building software and data systems, with the last decade focused on ML and data infrastructure. Today I help teams understand what's actually possible with large language models and build solutions that deliver real results.
I help teams cut through the AI hype to build systems that actually solve their business problems.
These tools can solve problems in ways that weren't possible before - processing complex documents, understanding customer intent, generating insights from unstructured data. But the key is starting with your actual business problems, not the technology. I help you figure out what's worth building, then build it alongside your team, and make sure your people can maintain it.
My approach is hands-on: I architect and build alongside your team rather than just giving advice. The goal is reliable systems that create real value, not demos.
Recent Writing
Why Successful LLM Products Start with Spreadsheets
Systematic evaluation is what separates working products from demos.
AI Coding Tools Amplify What You Already Know
These tools are productivity multipliers for people who understand the domain.
What Actually Matters When You're Building AI Products
A few takeaways from Hamel Husain's guide to improving AI products.
Five Insights from Andrew Ng on Building Faster with AI
Practical advice on shipping AI features quickly and effectively.