Your AI Has a Three-Phase Problem
Most AI systems fail not because they lack intelligence, but because they lack diagnosis. Why context collapse happens in three distinct phases and how to prevent each one.
Essays, frameworks, and observations on context architecture, AI product strategy, and building what matters.
The AI industry has reduced context to what fits in the window. That's a category error. Context is a property of organizations, not model architecture — and only one of its two forms becomes a moat.
While on paternity leave I stood up fourteen agents on a single $50/mo VPS, watched three vendor moves break my plan in seven days, and learned that the infrastructure is not the moat.
Most AI systems fail not because they lack intelligence, but because they lack diagnosis. Why context collapse happens in three distinct phases and how to prevent each one.
The diagnostic process that cardiologists use — pattern recognition, differential diagnosis, synthesis — is exactly what we should be engineering into AI memory systems.
Product-led growth isn't just a tactic. It's a framework for understanding how products compound through quality, trust, and network effects. Here's what I learned.
Not all AI architecture decisions are created equal. A framework for evaluating tradeoffs between latency, cost, accuracy, and maintainability when designing AI features.
What happens when you try to build context architecture in the real world? This is what I learned in the first week of building my own implementation.
A story about attention, context, and what it means to actually listen. Why the best interviews are the ones where the interviewer fully shows up.
A newsletter on the architecture behind AI memory, context synthesis, and building products that think. Launching Q3 2026.
Want to discuss these ideas?
Get in touch →