2026-09-04 · 5 min
How to use AI for project status reports without losing control
A practical workflow for drafting, reconciling and approving project updates, with the failure cases a human still has to own.
Writing
Notes and practical guides on digital commerce delivery and AI agents.
2026-09-04 · 5 min
Before your first AI agent pilot: a practical checklist
How to choose a bounded workflow, set permissions and costs, define acceptance criteria, and make a real stop decision.
2026-09-04 · 5 min
What headless commerce changes for a retail delivery team
A product-neutral responsibility map for storefronts, commerce services, integrations, releases and incidents.
2026-07-10 · 4 min
A PM with an agent chief-of-staff
What actually happened when I ran an AI agent as my own chief of staff for a few months: architecture, failures, and the rules that came from them.
2026-07-10 · 7 min
Building AI agents on Claude and Microsoft Foundry: field notes from e-commerce delivery
A delivery lead's view of model choice, agent tooling and hosting across Anthropic and Microsoft Foundry, including the operating work both approaches require.
2026-06-28 · 6 min
Why my portfolio runs an MCP server
My portfolio serves HTML, markdown and a small MCP server. Compatible clients can connect to five tools and two resources through a declared protocol.
2026-06-15 · 6 min
What 15 years of e-commerce delivery taught me about shipping AI agents
The technology is new. The way agent projects fail is old: e-commerce replatforms already taught me most of the fixes.