AI
Young Infrastructure
Eleven incidents in four days. AI APIs aren't as reliable as the cloud services we're used to — and some of us rely on them anyway.
Claude Code
AI
Living Dangerously?
When you spend hours a day with AI, patience for permission prompts wears thin. Here's the Claude Code flag I reach for — and where I draw the line.
AI
Anthropic's Claude Certified Architect Exam
Anthropic launched its first technical certification on March 12. Here's what it covers, what it costs, and whether you're eligible at this time.
AI
One Million Tokens
Anthropic's Claude Opus 4.6 just went GA with a 1 million token context window. I watched it happen in my own terminal.
AI
Roll Your Own AI Note-Taker
A colleague mentioned he built his own digital transcriptionist in minutes. I followed suit — and now I have better meeting notes than ever.
AI
From Vibe Coding to Agentic Engineering
A year after coining 'vibe coding,' Andrej Karpathy says the real discipline is 'agentic engineering' — orchestrating AI agents under structured human oversight. Here's why the distinction matters.
AI
Giving Claude Code Eyes with Playwright MCP
Model Context Protocol lets AI coding agents use external tools. Playwright MCP gives Claude Code a browser it can control — and for a blog like this, that changes the frontend workflow entirely.
AI
The SaaSpocalypse Reached My Office Today
A colleague replaced a $2,900/year SaaS app. A CNBC reporter replicated a $5 billion company. Wall Street is in freefall. And the tools just got better.
AI
When Claude Isn't Working
AI APIs go down. If your product depends on one, you need a plan for when it doesn't respond.
AI
Getting Started with Agentic Coding: A Guide for Non-Engineers
You don't need to be a software engineer to build applications with AI. These are the things I'd want to know if I were just getting started.