Series
Essays written to be read in order.
Agent Continuous Learning 3 parts
Building feedback loops that make your AI coding agent smarter from its own mistakes, one correction at a time.
Agent Sandboxing: From Execution Modes to Production Security 2 parts
A four-part series defining how agents run in production, what goes wrong without sandboxing, the three sandboxing patterns, and what breaks at scale.
Beyond LLMs: Building Whole AI Products 3 parts
From product frameworks to agentic systems to compound moats — what it takes to build whole AI products in 2026.
History, AI, and Non-Consumption 2 parts
A journey through AI history, innovation theory, and the nonconsumption lens.
The Verification Economy 3 parts
Exploring how AI scales execution while verification remains human-bounded.




