Category: Artificial Intelligence
Building with the GitHub Copilot SDK, Part 6 – Styling with CSS Design Tokens and Themes
In my previous post, I pulled Outlook calendar data into Chad’s Copilot and added time-allocation metrics that show how much of your week is already committed. That was about making the app useful. This post is about making it look good. You stare at this thing all day, so it better not just work —…
Read more…
Nobody Wants to Do Maintenance
“Another flaw in the human character is that everybody wants to build and nobody wants to do maintenance.” — Kurt Vonnegut Vonnegut wasn’t talking about software. But he could have been. Maintenance has always been the unglamorous part of the job. New features get roadmaps and launch announcements. Fixing that gnarly bug from 2019 gets…
Read more…
The Five Stages of Developer Grief
I have talked to a lot of developers over the past two years. Some are excited about AI coding tools. Most are not. A few are outright hostile. When I listen carefully to what they are saying, I hear something familiar. They are grieving. That is not a criticism. Grief is a reasonable response to…
Read more…
From Journey to Intention: The New UX Shift in the Age of AI
When I first entered the workforce as a graphic designer the industry was already in the middle of a major transformation. It was 1989, and digital technology was rapidly reshaping the commercial arts landscape. Desktop publishing had grown from a revolutionary experiment to a full-scale disruption. There was a real divide. The “old guard” held…
Read more…
Building with the GitHub Copilot SDK, Part 5: Pulling Calendar Data from Outlook
In my previous post, I added Mermaid.js diagram generation to the Design tab of Chad’s Copilot. Copilot read the workspace, generated valid diagram syntax from plain-language prompts, and made architecture docs something you’d actually keep up to date. This post is about something different. I wanted to pull in Outlook calendar data and make it…
Read more…
Generating Better Test Plans with AI Starts with Better Documentation
AI can help QA teams move faster, but only when it has the right context. When an AI-generated test plan feels too generic, too shallow, or misses obvious risks, the issue usually is not the model; it’s the input. If the only source material is a short ticket or a vague feature summary, the output…
Read more…
The Talent Pipeline Flush
Every few months, another headline drops: thousands of employees cut at a major tech company, paired with a statement about “repositioning for AI.” The numbers are staggering. The press releases are polished. And if you only read the headlines, you’d think these companies are shrinking. They’re not. They’re swapping one workforce for another, and the…
Read more…
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…
Don’t Panic, Adapt
If you work at a desk and use a computer, you’ve probably seen at least one headline in the last year telling you AI is coming for your job. The anxiety is real, and it’s not going away. But is the panic warranted? Let’s look at what the data actually says. A good example landed…
Read more…