Areas of sustained work
A focused map of the questions I return to across engineering, organizations, and systems. Each topic is assembled from the published corpus; the framing is written by hand.
AI agent governance
Useful agent autonomy depends on explicit identity, bounded authority, human decisions, and evidence that survives the action.
48 published pieces →AI engineering
The engineering advantage comes from making probabilistic components legible, testable, and bounded inside deterministic systems.
47 published pieces →AI software delivery
Faster generation only becomes delivery when coordination, review, ownership, and correction loops absorb the increased output.
22 published pieces →Engineering hiring
A serious hiring process maximizes decision signal while respecting the candidate cost required to produce it.
3 published pieces →Engineering leadership
Engineering leadership is the design of decision, ownership, feedback, and learning systems—not the supervision of output.
60 published pieces →Regulated systems
In regulated systems, trust is produced by explicit controls, traceable decisions, and evidence—not by confidence in the happy path.
8 published pieces →