LLM-Powered Jest: Auto-Generate Tests That Actually Boost Your CoveragePicture this: you have a Node.js API with 20 or more endpoints, and your test coverage is sitting at 0%. The CI badge is red. Writing tests manually feels like tedious boilerplate that nobody wants toMar 24 · 8 min readphsantos.hashnode.dev
From Silence to Stream: Building Low-Latency AI with Node.js, React & WebSocketsA loading spinner is not a UX strategy. In my previous post, I argued that production AI behaves like a contract, not a conversation. We used Zod to keep LLM outputs from breaking Node.js systems, thaMar 8 · 9 min readphsantos.hashnode.dev
Ship Reliable AI: How Zod and Schema‑Driven Development Harden LLMIn 2026 the honeymoon of "talking" to AI is over. As Senior Software Engineers, we've learned a hard truth: software is not a conversation — it's a contract. The hype insists a 'perfect prompt' is allMar 2 · 6 min readphsantos.hashnode.dev
