Five Modes of AI: Match the Machine to the Need AI maturity is not climbing from questions to agents. It is knowing whether you need an oracle, generator, collaborator, agent, or dialectical mirror, then judging when the answer is enough, when to dig deeper, and when to switch modes.
AI Engineering Featured Harness Observability: The Next Loop in AI Engineering Skills package capability. Harnesses determine how that capability performs in production. This article explores three nested control loops and shows how observability becomes governed adaptation, with evidence passing through evaluation and policy before it can safely steer execution.
The End of Software Engineering? No. The End of Software Implementation as a Profession. The scaling law is breaking: more software no longer requires more engineers. For most of the history of software engineering, scaling software meant scaling engineering teams. If you wanted more software, you hired more engineers. More products required more teams, and more features required more developers. More systems required more
AI Engineering Featured Skills Are a Start, Not the System Skills provide capability. Workflows direct the work. Harnesses control execution. Factories make the whole system repeatable. This article proposes the architectural boundaries between them and extends the factory model beyond software delivery into enterprise work.
Agency An LLM in Your App Is Not Agency The difference is between an LLM-powered feature, an orchestrated workflow, and a system that can act with bounded agency.
Loops Featured Loops Are Not Layers: Why Most Agent Loops Are Still Flat Everyone is talking about agent loops, but most are just retries, workflows, or DAGs with model calls. Real loops add another dimension: feedback, state, judgment, and abstraction gain. They do not just repeat work. They climb.
