How one general manager runs a full product using AI for planning, monitoring, and research
Plus, the CTO-to-IC pipeline and GPT-5.5 one week in
Plus: The end of the AI subsidy, do you actually want to talk to your agent, and how to turn customer feedback into a product queue
Plus: Agent-designed automations, why final review belongs in the destination app, and how to use our compound knowledge plugin
A step-by-step guide to using agentic capabilities for better product management
The real cost of AI agents is your time. A four-step framework for keeping your AI costs in check.
Plus: Our GPT-5.5 benchmark, Monologue Notes, and becoming terminal-pilled
Plus, the AI tell that’s exploded in company documents, a skill for creating product videos, and comics
OpenAI’s new model is a top-end senior engineer—and easy to talk to
Plus: Trust batteries, and how many agents we’ll have in the future
Plus: Vercel and Lovable’s security woes, and how to make your agent your watchdog
Turn your recordings into searchable context for agents
The more reliable AI gets, the less we check its work. Research explains why, and what to do about it.
Plus: Using NotebookLM to run the Pyramid Principle in reverse
Anthropic's latest Opus is more precise, more literal, and the best coding model we've tested on well-specified tasks—but it won't fill in the gaps for you anymore
AI has made software disorienting. It doesn’t have to be.
Plus: Why small models can't match Mythos, an AI workflow confidence check, Claude Code token tracking, our agent-muting plugin, the AI philosopher draft, and a mini-Vibe Check on Dia
The case against LLMs, and new words for our AI age
Clear your Mac of the files you don’t need. Keep the rest organized forever.
I'm running 44 AI agents across multiple projects. Each one is just a model pointed at a folder.
We use analytics and advertising tools by default. You can update this anytime.
Manage optional tracking categories. Necessary cookies stay on so the site can function.