Work in progress
Living documents — experiments, university work, advisory projects, and ideas being tested. Each collects related writing and resources in one place.
Agentic Systems in Government
Exploring what it means when AI agents, not forms, not chatbots, deliver government services at scale. A consolidation of my personal thinking on agentic government.
Updated 30 May 2025Publish It Yourself
A beginner's path to putting your own work on the open web. It starts with no-code publishing and moves to building and shipping pages with Claude Code, one small step at a time.
Updated 22 July 2026Making This Site Agent-Readable
An exploration of designing a website to serve two readers at once: a human and an LLM/agent. Clean per-page markdown, an llms.txt index, structured data, and a deliberate crawler posture.
Updated 3 June 2026Slop-Meter: An Anonymous AI-Slop Rating Widget
A small, reusable, privacy-first widget that lets readers anonymously rate how much any piece of writing smells of AI slop. A slider from human craft to pure slop, with a live crowd verdict.
Updated 3 June 2026Canvas LMS via MCP for Claude
An open-source MCP server that lets Claude read my Canvas data, my subjects, grades, and due dates, and turn it into a live study dashboard inside Claude Desktop.
Updated 1 June 2026Government ICT Investment: Visualising and Evaluating the IT Portfolio
An exploratory data analysis of the US Federal IT Portfolio dataset — 6,716 investments across 26 agencies, covering FY2020–FY2025 and approximately USD$476 billion in ICT spend.
Updated 31 May 2026