Generation became cheap; acceptance did not. A working definition of AI-native engineering, four mental models for reasoning about it, and what it changes for teams and for individual engineers.
Code generation has a free, instant, perfect oracle. Prose has none. Here is two months of narration-quality fixes in PaperCast, why each one was locally right and globally insufficient, and what we are changing.
A practical look at tracing, operator-facing observability, and trace-aware evals in the live harness-engineering demo after adding persisted trace summaries and lightweight eval fixtures.
A comprehensive white paper on agentic harness engineering: the runtime, tooling, controls, evals, and governance patterns that make AI agents reliable in production.
