Category: Software Engineering
The LLM Is the New Runtime
Last week, I was playing with Pencil, a design tool that lives inside your IDE. You describe what you want, and it generates UI designs on a canvas that compile into clean code. It’s a solid tool. But the thing that caught my attention had nothing to do with design. Pencil doesn’t ship its own…
Read more…
Building with the GitHub Copilot SDK, Part 4 – Building Mermaid.js Diagrams
In my previous post, we used the Copilot SDK to build a Tracking tab and earned value chart for Chad’s Copilot (WhenIsDone). Copilot read our project data, updated the data model, and built a working SVG chart without breaking anything that was already there. In this post, I’m going to show you how I added…
Read more…
Building with the GitHub Copilot SDK, Part 3 – Tracking Project Progress
In my previous post, we covered how to wire up the @github/copilot-sdk inside an Electron and Angular desktop app. We got authentication working, built streaming into the UI, and kept sessions separated per workspace. In this post, we are going to use that foundation to do something different. Instead of just chatting with Copilot about…
Read more…
Building with the GitHub Copilot SDK, Part 2 – Wiring Up an Electron + Angular Desktop App
In my previous post, we discussed the initial setup of the new Copilot SDK. This post will cover how we actually hook up the official @github/copilot-sdk inside an Electron and Angular application. Why is this structure necessary? When building a desktop application, we want a clean separation of concerns. We need to run the SDK…
Read more…
Building with the GitHub Copilot SDK, Part 1 – Getting Started
Starting a new project with a fresh SDK is always an interesting way to spend a weekend. I’ve been digging into the new Copilot SDK from Microsoft, and it has the potential to change how we think about integrated AI. Here is a look at how to get it running and why I think the…
Read more…
Specialized Models Beat General LLMs (Sometimes)
Here’s a question I’ve been chewing on lately: could a custom-built model for JavaScript/TypeScript actually outperform a flagship, general-purpose LLM while using a fraction of the memory and cost? For a lot of real-world developer tasks, the answer in early 2026 is yes. Now, I’m not claiming specialists win everywhere. That would be silly. But…
Read more…
Pulling Data from Microsoft Access to CSV: What I Built and Why
I’ve always loved working with plain old CSVs for my analysis and scripting needs. They are simple, portable, and just work everywhere. So when I got handed a Microsoft Access database that I needed to break out into individual CSV files, I figured I’d whip up a little toolchain to handle it reliably on my…
Read more…
Putting a UI on My Access-to-CSV Converter
Once I got the command-line version working exactly how I wanted, I noticed I was doing the same thing over and over: pick an Access file, choose an output folder, hit run, then open Finder to dig through the CSVs. It worked great, but it felt a little clunky—especially if I wanted to share it…
Read more…
Agent Chat using LangChain Part 3 – Fun Examples
Now that we’ve covered the technical implementation (see Part 1 and Part 2), let’s see what this agent can actually do. Here are three examples that demonstrate how natural language interactions can replace tedious UI workflows—each one progressively more powerful. Example 1: Quick Lookups The simplest use case is finding information without navigating through menus….
Read more…
Agent Chat using LangChain Part 2 – Token Streaming with WebSockets
We all dislike typing a message to an AI agent and then just staring at a spinning loader for ten seconds with zero feedback. It feels slow and lifeless. In part 2 of this series, I’m going to walk you through how I added proper token streaming over WebSockets so users see the agent’s response…
Read more…