I work across agentic commerce and marketing, multi-agent product systems, and AI-native strategy. This is my working desk: essays, research, tools, and the models I use to turn emerging capabilities into products people trust.
One series: Agent systems from first principles.
intelligence → action → outcomes
Three connected areas shape the work.
Agents across discovery, decisions, content, and transactions.
Clear roles, dependable handoffs, and policy-aware execution.
Turning new capabilities into measurable customer value.
Agentic commerce depends on context assembly: giving a shopping agent the right information at the right moment.
How tool calling connects your request to product searches, stock checks, and an authorized purchase.
How an AI suggestion becomes a real-world action—and how permission checks, approval gates, and recovery logic keep a helpful agent from making an expensive mistake.
Most confusion in agent architecture begins when one system is asked to decide when work starts, how it proceeds, and when it is safe to act.
It can look like forgetting. Usually, it is something more ordinary: the information was kept in the wrong place — or it was never kept at all.
Globegraphy — markets, platforms, source-audited reports.
Coming. It will sit next to e-commerce.
LinkedIn, X News, and five public wires, filtered to AI agent product news.
Leave your email and I’ll send new essays when they go up.