Building AI agents that survive production. 30 years in software, now writing about what works and what breaks.
Jun 5, 2026
•
2 min read
Robin Sloan built an app for his family in 2020 — and why the AI era just handed that exact power to everyone who can write a sentence.
May 29, 2026
Anthropic's new model is the first that stops quietly shipping broken code and telling you it worked — the upgrade non-coders actually needed.
May 22, 2026
Two competing "Managed Agents" launches, one identical architecture — and the cage that quietly closes around your stack.
May 15, 2026
The silent subsidy that funded your AI flow is drying up — here's what shifts on your bill this week.
May 9, 2026
What 3 months of shipping with Claude Code taught me about defensibility. And the one moat AI literally cannot copy.
May 6, 2026
The hidden layer that lets AI agents close their own loop — and why your `scripts/` folder doesn’t count.
AI Agents
+2
Apr 10, 2026
3 min read
7 articles in 8 days. 4 were about security. That was not the plan.
