Field notes on building AI-native products, context engineering, and the craft of shipping.
Eleven articles, 43 million views, one idea: design loops that prompt your agents. They all agree you need a verifier. Almost none of them are one.
Prompt engineering quietly gave way to context engineering. The catch: most teams doing it are doing it backwards.
Viktor and Martoshi make the AI-employee-in-Slack look like a company. We built the same shape on Vercel's Eve in one session.
AI collapsed the cost of building software. The bottleneck moved from creation to adoption, and most founders are still optimizing the solved side.
shadcn calls it scroll engineering. It is bigger than that. Users don't churn on your model, they churn on the chat UX around it.
npm versus shadcn is the wrong fight. How much of your component a team wants to own is their call, not yours. Ship the whole spectrum from one source.
Building your own Jira used to be insane. With AI writing the code and an MCP server wiring it to everything, the math flipped.
I rebuilt the Prompt Area homepage around the live component instead of copy about it. For a developer tool, the demo is not a section on the page. It is the page.
The best coding model in the world lasted three days before a government directive switched it off. The lesson is not 'use local models.' It is 'never couple your product to a model you are not allowed to keep.'
Stuffing every past message into context is not memory, it is hoarding. Real memory is knowing what to forget.
For twenty years teams ran a content management system. The next era runs on context management: what your AI knows before it writes a word.
Your prompts are not your moat. Your model is not your moat. The test suite that catches silent regressions is the thing nobody can copy.
Most 'we need a bigger model' complaints are context engineering problems in disguise. A smaller model with the right context beats a frontier model fed a junk drawer.
Choosing Postgres and a boring monolith looks lazy. It is the opposite. Here is how I think about innovation budget as a CTO.