Writing
Notes on enterprise AI governance, portfolio architecture, and the practical work of delivering secure digital services in the public sector.
-
Fifty-five hours: a public registry built specification first
I took a public-facing registry from scratch to production in about 55 hours of development time. The specification carried most of the load, and a person approved every handoff.
-
From specification to evidence: how AEGIS keeps a person in charge
AEGIS is my open-source toolkit for delivery with AI agents. It writes the specification first, blocks code until the specification is complete, and records the person who approves the release.
-
Model Context Protocol as an architecture knowledge system
Architecture standards fail at the moment of the decision. MCP moves them to where the decision is made.
-
Six weeks, one mandate: architecture decisions when the date is not negotiable
A fixed launch date does not change what good architecture is. It changes which decisions you are allowed to defer.
-
What it takes to put AI inside a government delivery pipeline
Most AI pilots in the public sector fail at the governance seam. The work is in making governance something a delivery team can program against.