Posts
Thoughts on technology, design, and building products.
2026
June
How I Code: Summer 2026 Edition
Six hours of driving, ten merged PRs, zero humans in the loop. A snapshot of how I actually build software in mid-2026: a monorepo from day one, letter-graded PRDs, hourly agent loops across three dusty Macs, a Design Review gate that keeps ten agents from shipping a ten-personality UI, Neon branches as the safety net, and why I split planning, building, and review across different AI providers.
The 24-Hour Sprint
TL;DR: Agentic coding is compressing the dev cycle into 24 hours. Here's how it looks from the inside.
May
There Are Three Kinds of "Similar" in Food. Most Recipes Only Know One.
Researchers built a map of ingredients that answers three different versions of "what's similar" - and the results are weirder and more useful than any recipe site has ever managed.
What a Papal Encyclical Just Added to Your AI Governance Checklist
Pope Leo XIV's first encyclical, Magnifica Humanitas, isn't just theology - it's a portable moral framework that will land in EU AI Act commentary, customer RFPs, and bank ethics committees within a quarter. Here's how its four questions map onto the AI governance work enterprise teams are already doing.
The Model Isn't the Moat
Notes from AI//FORWARD and a leadership-development talk: why the companies winning with agentic AI aren't winning on model selection, and what they're building around it instead.
How I Evaluate an AI Tool Before I Trust It in Production
Most AI tool evaluations stop at "does it work in the demo." Here's the framework I actually use before trusting something in a production system.
The Southeast Doesn't Need Permission to Build
The assumption that serious tech work only happens in San Francisco, New York, or Seattle is wrong — and increasingly expensive to believe. A practitioner's case for building in the Southeast by choice.
April
Your AI Agent Didn't Go Rogue. You Gave It the Keys.
Why the Cursor/Railway incident wasn't a vendor failure - it was an architecture gap. How to prevent AI agents from accessing permissions they shouldn't have, and why ownership matters.
What I'd Tell a Team About to Ship Their First AI Feature
The gap between a working AI demo and a production AI feature is wider than most teams expect. Here's the honest version of what to know before you cross it.
The Seven-Layer AI Agent Stack
Every production agentic system has seven layers. Miss one and you'll find out in prod. Here's what each layer does, why it matters, and where teams consistently get it wrong.
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.