PKPrashant Koiralainblog.prashantkoirala.info.np00AI agents need boring engineering3d ago · 31 min read · AI agent demos are easy to love. You type a goal. The agent thinks for a moment. It searches, writes, calls tools, edits files, creates a ticket, sends a message, and gives you a neat summary. For a fJoin discussion
PKPrashant Koiralainblog.prashantkoirala.info.np00Why TypeScript became the language of AI appsMay 10 · 24 min read · A few years ago, TypeScript was mostly described as a safer JavaScript. That description was true, but too small. In 2026, TypeScript is no longer just the language people use to make React code less Join discussion
PKPrashant Koiralainblog.prashantkoirala.info.np01AI changed the software supply chainMay 6 · 27 min read · Most developers still think of security as something that happens inside their own code. That used to be a useful mental model. You wrote code, tested it, scanned it, shipped it, and patched it when aVVarsha commented
PKPrashant Koiralainblog.prashantkoirala.info.np00Local first AI is coming back May 3 · 8 min read · AI on the web has mostly meant one thing: send user input to an API, wait for a cloud model, then render the answer. That model is not going away. Large frontier models still need serious compute. ButJoin discussion
PKPrashant Koiralainblog.prashantkoirala.info.np00MCP beyond the hypeMay 1 · 8 min read · AI agents are useful only when they can reach the world outside the chat box. They need files, calendars, databases, APIs, code repositories, search tools, and sometimes internal company systems. ThatJoin discussion
