AI Engineering From Scripts to Seats Agentic systems are moving from tool use to loops. The harder transition is turning those loops into accountable seats. That requires an operator to encode SDLC knowledge, verification, authority, and evidence so responsibility can be delegated safely.
AI Engineering Featured We’re Converging on a New Shape for Software Anthropic’s AI-Native SDLC and my Software Manufacturing white paper point to the same deeper shift: as code generation becomes cheap, software engineering reorganizes around intent, standards, evidence, control, and safe delegation.
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.
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.
AI Engineering When Code Becomes FLUID, Where Does the Engineer Go? HydraFlow as a live test of FLUID systems and the operating patterns that emerged from running one.
