web development
In the modern TypeScript ecosystem, we spend an enormous amount of energy ensuring our business logic is type-safe. We use strict null checks, exhaustive union types, and complex generics to ensure our code is robust. Yet, many of the world’s most experienced developers still leave the front door of
Artificial Intelligence (AI)
As a developer, there is nothing more frustrating than watching an AI agent go "rogue." You ask for a simple feature update, and suddenly, your Google Antigravity environment is suggesting libraries that don't exist or, even worse, refactoring 500 lines of perfectly functional code just for
JavaScript
I was mentoring a fresh Node.js dev yesterday who asked, "npm or npx, what's the difference?" I smiled and said: "Think of npm as your toolbox, you install tools to keep. npx is like borrowing one for a quick job, then returning it. Use
Artificial Intelligence (AI)
If you’ve been following my journey at Medevel.com, you know I’m obsessed with the intersection of AI engineering and open-source software. We talk about LLMs, Next.js, and Directus all the time. But today, I need to talk about the process. For months, I’ve been wrestling
Artificial Intelligence (AI)
Look, I've tried them all. Claude Code, Cursor, Antigravity, Copilot, the whole parade. They're powerful, sure. But if you're like me, a Linux lifer since late 90s, a neovim person, someone who cares where their data goes, you've probably felt that itch.
Artificial Intelligence (AI)
The era of "Vibe Coding", where we just throw loose natural language at an LLM and pray the output compiles, is officially dead. We are moving into the age of Agentic Engineering, a world where we don't just chat with AI; we architect autonomous systems that
React
I’ve spent the last decade jumping between frameworks like a digital nomad seeking the perfect home. I’ve lived through the rigid architecture of Angular, the approachable elegance of Vue, and even the "old-school" magic of Blaze. Each had its charm, but they always felt like they
healthcare AI
What is Phlox! Phlox is an open-source patient management system integrating AI-powered medical transcription, clinical note generation, and an AI chatbot interface. It's designed to run locally, utilizing local models for inference and transcription. Features * 100% Local & Private: Runs entirely on your machine with no third-party services
Artificial Intelligence (AI)
What is DeepTutor! DeepTutor is your free, self-hosted AI learning companion that actually remembers you. It adapts to your style, builds knowledge over time, and never sends a bill. With persistent memory, autonomous TutorBots, and a unified workspace for chat, research, quizzes, and visual math, it feels less like a
web development
As a doctor and a software developer, I’ve spent the last decade navigating two very different but equally complex systems: the human body and high-performance codebases. In medicine, we have organs that act like microservices (the heart does one job, the lungs another), but they are all connected to
Artificial Intelligence (AI)
If you’ve been hanging out on Tech Twitter or LinkedIn lately, you’ve probably heard the term "Vibe Coding." It sounds cool, right? It’s that magical flow state where you just describe a dream to an AI, hit "Generate," and, boom, you have a
AI Development
If you’ve been shipping code long enough, you know the feeling: you’re deep in a flow state, the terminal is humming, and suddenly you hit a wall. A cryptic error. A tangled dependency tree. A product requirement that changes at 11 PM. You spend hours debugging, context-switching, and