Fuzzwah's Agentic Coding Learnings

So remember how a month ago I was all in on Spec-Kit? Converting messy PRDs into structured specs, cutting scope by 40%, eliminating ambiguity? I was properly hooked on spec-driven development. Genuinely changed how I think about requirements.

Yeah. About that.

The Spec-Kit Maintenance Problem

I’d been watching the Spec-Kit GitHub repository for updates — new features, bug fixes, community activity. What I found instead was silence. A community discussion captured what a lot of us were feeling: 22 pull requests sitting open with zero commits merged in an entire month.

The sole official response from...
Continue reading →

I reckon one of the most common questions I get asked about agentic coding is “which tool should I use?” And honestly, the answer that took me too long to figure out is: all of them, depending on what you’re doing. After months of experimenting I’ve got some pretty strong opinions about when each tool shines, so let me walk you through it.

The Contenders

There are three main approaches I bounce between:

• VS Code + Copilot Chat — GitHub’s native agentic coding experience, deeply integrated into the editor with support for copilot-instructions.md files, workspace context...
  Continue reading →

Three weeks ago I found myself staring at three different “Product Requirements Documents” that were supposed to guide my development work. Each one written in a different style, with different levels of detail, and — most frustratingly — each left critical questions unanswered.

The first was essentially a wall of implementation details. It told me how to build the feature (database schemas, caching strategies, partitioning approaches) but buried the why so deep I had three different interpretations of what problem I was actually solving. The second was the opposite — eight pages of ambitious vision with phrases like “engaging experience”...
Continue reading →

I’ve been messing around with AI-assisted development for months now, and after a frankly embarrassing amount of tinkering I’ve landed on a setup that actually works. I can already feel your eyes preparing to glaze over, but stick with me — this stuff is genuinely exciting and has completely changed how I build things.

The Foundation: VS Code Insiders

I run VS Code Insiders rather than the stable release because:

• MCP support and Copilot improvements land here first
• It’s surprisingly stable for a daily build
• I can keep stable VS Code installed side-by-side for critical work if...
  Continue reading →

I’ve spent way too long messing around with MCP servers at this point, and one of the first decisions you hit when building or choosing one is the transport: STDIO or HTTP. Sounds like a boring infrastructure detail, right? Turns out it fundamentally changes how people actually use your server. Let me share what I’ve learnt building and deploying both.

STDIO Servers: The Automatic Advantage

The killer feature of STDIO MCP servers is dead simple: VS Code automatically starts them for you.

When a user adds your server to their settings.json:

{
				Continue reading →