Posts

Thoughts on technology, design, and building products.

2026

April

Most Agents Are Just Prompt Chains With Better Branding

A practical, opinionated breakdown of agentic AI development for builders who are done with demos and want to know what actually works in production — covering orchestration, failure modes, guardrails, and the patterns worth betting on.

February

OpenClaw Sent 500 Messages to My Wife

A real-world OpenClaw safety failure: my home automation agent sent 500 messages, got stuck in a loop, and ended up in Bloomberg.

Agentic Workflows That Actually Work

How to build production agentic workflows with retry logic, audit trails, and human-in-the-loop checkpoints that survive real-world failure modes.

January

The Gap Between AI Demos and Production

The gap between AI demos and production: what happens when you deploy AI agents into incomplete data, hostile inputs, and users who don't read instructions.

Recurring Value: Beyond Clever Automation

Why the best AI automation compounds over time — building structured workflows with human checkpoints instead of one-off scripts that break.

Previous Years

2025 →