Posts

GitHub Copilot Customization, Finally Explained

Image
  Agents, Skills, Hooks, Prompts, Custom Instructions, and GitHub Instructions—what they are, how they differ, and when to use each one GitHub Copilot is getting more powerful, but it is also getting more layered. If you have been exploring Copilot customization, you have probably run into a pile of terms that seem similar at first glance: Agent , Skill , Hook , Prompt , Custom Instructions , and GitHub Instructions . And that is where the confusion starts. They all shape how Copilot behaves, but they do very different jobs . If you do not separate them clearly in your mind, it becomes easy to misuse them. You end up trying to force one feature to solve a problem that another feature was designed to handle much better. This article is the practical guide I wish I had the first time I started thinking seriously about building a real Copilot workflow. By the end, you should be able to answer these questions with confidence: What is each feature actually for? How are they d...

Windows Just Got a Dock (For Free)

Image
  There’s a quiet revolution happening on Windows—and most developers are missing it. In the video above, the creator walks through the new Command Palette Dock in Microsoft PowerToys. At first glance, it looks like a simple macOS-style dock. But under the hood, it’s something much more powerful: It’s a developer-grade command launcher + customizable workspace hub And if you're someone optimizing workflows, AI tooling, and developer productivity—this is a big deal. What the Video Shows (Key Takeaways) 1. It’s Not Just a Dock — It’s a Command Surface The dock is actually an extension of the Command Palette , not just pinned apps. That means: You’re not limited to apps You can pin commands, scripts, tools, and extensions It becomes a workflow launcher , not just a shortcut bar This aligns perfectly with how modern dev environments are evolving: Less clicking → more intent-driven execution 2. Persistent, Always-On UI Unli...

Why AI Coding Demos Feel Magical While Real Projects Feel Hard

Image
  Why AI looks brilliant in demos, struggles in production, and delivers real value only when teams build the right operating system around it. If you have watched AI coding demos lately, you have probably seen something that looks almost unbelievable. A model spins up a feature in minutes. It creates a clean UI. It wires up some logic. It even explains itself confidently. The whole thing feels smooth, fast, and oddly effortless. Then you try to use the same approach on a real production application, and the experience changes immediately. Suddenly, the AI misses conventions, breaks patterns, invents abstractions, touches files it should not touch, and produces code that looks polished but does not really belong in your system. So what happened? The demos were not fake. They were just operating under kinder conditions. The hidden reason demos look so good AI tends to look brilliant in environments with very few constraints. A greenfield prototype, a standalone script, or ...

AI Didn’t Change Engineering Ethics — It Made Them Non-Negotiable

Image
A lot of developers are asking a simple question right now:  If AI is writing most of my code… do the rules still apply? It’s a fair question. When I say "engineering ethics," I mean the professional duty to ship software that is correct, secure, maintainable, and fair to users. After all, when you can generate a feature, fix a bug, and scaffold tests in minutes, it feels like the game has changed. But here’s the truth: AI didn’t change engineering ethics. It removed your excuses for ignoring them.   The Illusion of Speed AI gives us something we’ve never had before: ·        Near-instant code generation ·        Infinite “junior developer” capacity ·        The ability to ship faster than ever   And that’s exactly where the danger lies. Speed creates an illusion:  “If it works, it must be good enough.”   But working code is not the same as c...