Polish is the final step of compound engineering: using the app myself and telling the agent what feels off until it doesn't
The AI-native engineering philosophy has expanded from four steps to eight
We’ve been working on a big release on the future of work for next week, shaped by what we learned from building Plus One
How one general manager runs a full product using AI for planning, monitoring, and research
I'm running 44 AI agents across multiple projects. Each one is just a model pointed at a folder.
Lessons learned when vibe code meets high load
Kieran Klaassen turned a prompt into a working app in an hour and shows you how
Our comprehensive guide to OpenClaw is here
Demos, workflows, and hard-won lessons from building agents that run 24/7
Start with three simple tools, and let the AI figure out the rest
A comprehensive handbook for the AI-native engineering philosophy
OpenAI nailed the interface. But it's built for hardcore engineering.
It's the first AI tool that feels like delegating to a colleague, not prompting a chatbot
How 13 AI agents reviewing in parallel caught a critical bug I would have otherwise missed
Cursor team members share their thoughts on building software with AI and why model selection beats prompting tricks
Compounding engineering turns every pull request, bug fix, and code review into permanent lessons your development tools apply automatically
Whoever wins vibe coding wins how you work on your computer—Claude Code is in pole position
A new software paradigm for the AI age
Lessons from the team that built Codex and launched a number-one app with it
A four-step engineering process for software teams that don’t write code
Kieran Klaassen
Brandon Gell
Marcus Moretti
Dan Shipper
Katie Parrott
Sign in
