Writing

I write about product craft, designing AI features, and keeping agents safe.

Selected

All writing

Parameter-bound HITL for agent authorization

2026

Why boolean approval prompts fail when AI agents call destructive tools, and how parameter binding, bounded intent, consent atomicity, and cryptographic delegation solve the authorization problem in practice.

Inside ActionAuth: a code-anchored walkthrough

2026

A code-anchored walkthrough of how ActionAuth realizes three-layer delegation, durable replay state across distributed replicas, and the two carriers that move human approvals across single-agent and multi-agent systems.

The anatomy of a strategy pt. 1

2023

Most organizations operate with high-level board metrics and a disconnected backlog of projects. A practical framework for connecting mission, strategy, and execution.