Coding With David

There’s a moment that caught me off guard recently. Not a breakthrough in code. Not a clever refactor. Not even a production issue solved at 2 AM. It was something simpler—and much bigger. I realized I had fully accepted AI-driven development. The Workflow That Changed Everything I built a system that feels almost unreal when you step back and look at it. Here’s what happens: A bug or feature is created in Azure DevOps An application polls for new work When it finds an item, it: Creates a branch Writes or updates the code Generates tests Runs those tests Updates documentation Runs a separate agent for code review (with a report) If everything passes… creates a PR All of this is powered by a combination of: Agents Skills Prompts Tools In other words… a small army of AI doing what used to take hours (or days). The Unexpected Realization After watching this system run, I leaned back and had a surprising thought: “I can focus on being a so...

  If you spend any time reading about AI and software development, you’ll see the same concern over and over: “AI-generated code isn’t good enough.” It’s buggy. It’s inconsistent. It makes mistakes. And while all of that is true… It’s also not the real problem. We’re Arguing About the Wrong Thing Developers are focusing on: code quality correctness best practices But AI has already crossed an important threshold: Tools like GitHub Copilot can generate code that is: good enough often correct increasingly consistent Not perfect — but close enough that something else becomes the bigger issue. The Real Problem: Weak Intent AI doesn’t fail because it writes bad code. AI fails because: We give AI unclear instructions and expect precise outcomes. Think about how we typically prompt AI: “Create an API for notifications” “Build a dashboard” “Add validation” Those are not specifications. Th...

  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...

  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 ...

  Artificial intelligence has already begun transforming how software is built. Tools like AI coding assistants, autonomous agents, and AI-driven development environments can now generate working implementations in minutes. Tasks that once took hours—or days—can often be completed in a single interaction with an AI model. This rapid acceleration raises an inevitable question for the industry: How long will it take before software engineering becomes fully autonomous? The answer is not a single breakthrough moment. Autonomous engineering will emerge gradually in stages , each one shifting more responsibility from humans to machines while redefining the role of software engineers. Understanding these stages helps organizations prepare for the changes already underway. The Four Stages of AI-Driven Software Engineering Stage 1: AI-Assisted Engineering (Today – ~2027) This is where most teams operate today. Developers use AI tools to accelerate their workflow, b...