Most TypeScript teams shopping for an agent framework don't need one. A single generateObject call covers classification, extraction, summarization, tagging — the 80% case for production LLM work in TS right now. But once the model starts deciding what to do next, surviving deploys, or coordinating with other agents, you start shopping. And the moment you do, you discover the TS agent ecosystem is
All frameworks are eventually replaced. React is probably the first that won’t be. It's not the best language out there, it's not the language developers love the most, it's the language the robots just won't quit. Request ChatGPT to develop a todo app for you. You'll receive React. Request Copilot to generate the basic structure of a component. React. Request Claude to design a prototype for a da
We had ArgoCD running perfectly. Every deployment was reconciled from Git. Drift detection worked. Rollbacks were one-click. Our GitOps setup was clean. Developers still couldn't provision a staging environment without pinging the platform team. That gap — between "GitOps in place" and "developers can actually self-serve" — is where most platform engineering teams get stuck. GitOps solves a real p
Anthropic now ships at least three different memory models inside the Claude product family, and they don't behave the same way. Claude.ai has a chat memory feature for Pro, Max, Team, and Enterprise users that summarizes prior conversations and injects that summary into new chats. Claude Code has CLAUDE.md files plus a separate "auto memory" directory the model writes to itself, both loaded at se
Part 2 of 5 in The New Engineering Contract - what it means to lead engineers when AI is doing more of the coding. Stripe never skipped the boring stuff. They ship 1,300 AI PRs a week. Amazon skipped it. Their storefront went down for six hours. Kent Beck wrote the answer in Extreme Programming Explained in 1999. We read it. Then chose velocity anyway. A friend of mine leads engineering at a funde