Two years ago, automating a single ETL flow took me weeks. This week I built a full internal tool in five days. The real shift isn't better AI tools — it's the collapse of the cost of problem-solving, and what that does to the SaaS math.
Essays
Long-form. Strategy, systems, and the builds behind them.
Buying a generalist chatbot raises the floor of competence. It doesn't build your edge. True value comes from bespoke systems that understand your specific business logic and data.
A week in Google Meet taught me something about architecture constraints. You can't brute-force performance through a browser tab.
After nearly a thousand hours building with Claude Code, I've learned a few lessons the expensive way. These are my three non-negotiable rules for every AI coding agent.
AI has two modes: Cognitive and Operational. Work slop comes from treating everything like Cognitive Mode. The fix is knowing when to constrain AI to data-backed execution.
I manage countless scripts, four production apps, one in development, and another in planning. The hardest part isn't building them. It's making sure they're still understandable six months from now.
For weeks, the dream of bridging our underwriting models to the data warehouse felt like a fantasy. The breakthrough came when I stopped patching cracks and rebuilt the foundation.
The hardest part of building in the age of AI isn't figuring out what's possible. It's deciding what gets built first when the barriers to solutions have collapsed.
The first version of our document routing agent hit 37.5% accuracy. The problem wasn't the AI — it was building probabilistic inference into a step that needed to be deterministic.