Articles, thoughts, images, ideas, and updates.
The real barrier to the software dark factory isn't agent capability. It's the organizational capability to manage them.
What we learned from making a research agent durable, routed, visible, and eval-driven.
Claude Code's deep-research workflow, pulled from its binary and dissected. Wide search, no second hop.
A reflection on Anthropic's dynamic workflows post, from someone building a browser agent on the same idea.
Everyone building agents asks which model to use first. Wrong first question. The harness is where the agent lives or dies.
A copy-paste recipe for content negotiation that gives AI agents clean markdown while browsers keep getting HTML.
How extensibility shifts from packaged plugins to agent-readable recipes, and why the connector is the new extension point.
I trained a Clojure LLM from my phone. It 'beat' GPT-5.4—kind of. Here's what actually happened.
Four unsolved problems blocking the agentic future: correctness, architecture drift, context scaling, and judgment.
A durable wrapper pattern for autonomous agents: Bash owns state, validation, recovery, and completion.
Analysis of AI agent architecture, dev tool reviews, and go-to-market strategies. Unsubscribe anytime.