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 Factory Software Factories Need Building Codes Harnesses govern how autonomous software gets built. The next problem is deciding what properly built software means.
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 Factory Featured What Matters After the Software Factory Works Six months and 1,700 pull requests into building an autonomous software factory, throughput turned out to be the least interesting part. What mattered was trust, calibrated actors, institutional memory, and intent. Those lessons eventually formed a governance model: PAAA.
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.
