May 21, 2026
Why Enterprises Should Own Their Agent Harness
The durable enterprise advantage in agentic AI will not come from owning the model or adopting the newest agent SDK first. It will come from owning the harness: the operating layer that turn...
Read on SubstackMay 14, 2026
Intent Is the Missing Layer for Agents
The hidden problem in agentic work is not instruction. It is intent. Something changes when agents stop answering questions and start doing work. A prompt is no longer just a request. It bec...
Read on SubstackApr 24, 2026
The problem with Agents writing your pull requests
Something odd shows up once you let agents loose in a repo for long enough. The code is usually fine—sometimes better than what people would write under pressure—but the pull requests get st...
Read on Substack