Notes on architecture in the age of coding agents: how teams read what they have, decide what should change, and verify what actually shipped.
3 min read
Code preserves what was built. It does not preserve why. AI coding agents make this gap worse, not better - they read the artifact and not the input. The fix is not better diagrams or longer system prompts. It is keeping the reasoning alive next to the code it explains.
6 min read
Sequoia Capital identifies a $10 trillion services automation opportunity, but calls this the "steam engine moment"—the foundational AI technology exists, but we're still decades from systematic deployment. Early agent-first implementations show 40-85% efficiency gains, yet success requires architectural expertise concentrated among technical specialists. The companies that democratize this knowledge—making agent system design as accessible as ChatGPT—will become the Westinghouse of the cognitive revolution.
3 min read
An engineering retrospective from 2025. We prototyped a type-safe agent-workflow builder, then cut it — because the harder question turned out to be the simpler one: what is actually in my system, and what will this change break?
8 min read
How we built type safety, human-AI collaboration, and visual workflow authoring by putting an explicit input/output resolution layer on top of LangGraph's state annotations — and the patterns that made composable, type-safe workflows possible.