Selected work
Work you can open and check. Each piece says what it is and when I made it.
Every project was accurate at the time of writing. My tools and methods have moved on since some of them, so treat the older pieces as a record of how I worked at the time.
Interactive capstone
October 2026.
The part of the Offerings Atlas you can try. Tell it what you run and what worries you about AI agents. It walks the knowledge base as a network, then shows what your stack covers, which gaps are real, the ways each one could be closed, and the engagement I would propose to close them.
Try itKnowledge base case study
Built 6 to 10 October 2026.
I built a knowledge base of AI agent security controls that agents research, verify and keep current. It covers 151 platforms and tools, and an enterprise questionnaire answers a client's concerns from it with every citation checked against the knowledge base itself.
Project detailsPersonal tooling
October 2026.
I built a personal gateway that gives every agent I write one OpenAI-compatible endpoint. Role aliases decide whether a call goes to headless Claude Code, headless Codex or an API model, and every call leaves a proof record.
Project detailsAgent build case study
First live cloud run 27 September 2026.
I designed and built a custom AI agent that runs in the cloud, draws everything it knows from an open knowledge base, and can only act inside policy written as code. I tested it on a live, high-stakes domain: my own job search.
Project detailsPractitioner reference
Version 1.4, evidence cut 23 September 2026.
A reference for administrators on what the Claude Cowork admin console, device policy (MDM) and third-party deployments on Bedrock, Vertex and Foundry actually control, where they fall short, and which defaults to change first.
Project detailsSOC advisory white paper
Version 5, evidence cut 23 September 2026.
A SOC advisory paper on telling AI-driven attack activity apart from human and automated activity, and what that means for detection and response.
Project detailsStudy game
First released July 2026, last updated September 2026.
A pixel-art side-scroller I built to study for the Claude Certified Architect, Foundations exam, with question terminals, boss fights and timed mock exams.
Portfolio proof of concept
May to July 2026.
A working demonstration of structured review for AI agent integrations and MCP-connected tools. Each integration is treated as a governed access request, not unmanaged developer tooling.
Project detailsOpen-source tool
First released June 2026, last updated July 2026.
A command-line pipeline that takes several AI deep-research reports on one topic and consolidates them into a single verified master document.
Project detailsFictional case study
April 2026.
A fictional case study for Rossco's Coffee, covering security architecture and migration planning on AWS.
Project detailsPlanning portfolio
April 2026.
A practical incident response planning portfolio structured around NIST SP 800-61.
Project details