Essay · July 7, 2026

AI-Native Transformation Starts With Preserving Expert Judgment

Ford’s quality turnaround is a useful warning for every company trying to become AI-native: experts are not merely legacy cost. Until their judgment is captured, tested, and connected into feedback loops, they remain part of the production system AI depends on.

Field Note · Part 3 · June 5, 2026

What an Enterprise Capability Resolution Layer Should Return

A capability resolution layer should return more than a tool name. It should return a structured decision package that agents, platforms, and operators can trust.

Field Note · Part 2 · May 1, 2026

The Hidden Cost of Wrong Tool Use in Agent Systems

Wrong tool use is not just a correctness problem. In agent systems, it can create retry loops, wasted model calls, higher latency, and weaker AI economics.

Field Note · Part 1 · April 10, 2026

Capability Resolution: The Missing Layer Between Agents and Tools

As agent systems gain access to more tools, APIs, workflows, and sub-agents, the harder platform problem moves upstream: resolving the right capability before execution.