The art of simplicity

For years, when a .NET developer said "I need the mediator pattern," the answer was almost automatically MediatR . Jimmy Bogard's library became the default so quickly that a lot of teams never really questioned it, they just added the NuGet package and moved on. That changed in 2025. MediatR moved to a commercial license, and suddenly "just add MediatR" wasn't a free decision anymore. That's a good moment to take a step back and look at what the mediator pattern actually is, and to point out something a lot of developers overlook: if you're already using MassTransit in your project, you already have a mediator implementation available. No extra package, no extra license to think about. Remark: Be aware that MassTransit switched to a commercial license as well starting from version 9. What is the mediator pattern? The mediator pattern is about decoupling the sender of a request from the thing that handles it. Instead of a controller or servi...

Recently I was watching one of my AI agents chew through a feature, and in the middle of its chain of thought it dropped: "Bribing the hamster." My first thought was that I was hallucinating instead of the AI model. My reaction was to check my coffee. My second was to find out what was actually going on. Turns out, it's not a hallucination. It's a feature. The setting behind it VS Code's Copilot Chat has a setting called chat.agent.thinking.phrases . Instead of a static "Thinking..." or "Working..." label while the agent is doing its multi-step work in the background, it rotates through a list of playful phrases. Here's what that setting looks like in practice: "chat.agent.thinking.phrases": { "mode": "replace", "phrases": [ "Bribing the hamster", "Reticulating splines", "Untangling the spaghetti" ] } Remark: "Reticulating splines" ...

As developer or architect, you make a lot of design decisions every day. You picked Redis for caching, or REST over GraphQL, ... . You move on after your decision was made, but in the back of your head a voice keeps asking "should I bother a colleague and ask for a second opinion?" , "what if I forgot something?" , "is this really the right choice?" The GitHub Copilot app can help you out with a (new) slash command: /spar . What /spar actually does /spar switches Copilot from "help me build this" to "convince me this is a bad idea." Instead of accepting your plan and generating code, it starts poking at your assumptions, asks about edge cases, and points out tradeoffs you may have skipped past. Remark: this is different from /plan , which helps you break a task down. /spar assumes you already have a plan and wants to stress-test it before you commit. How to use it Type /spar in the chat composer, followed by whatever...

Microsoft just released The Story of VS Code , an official documentary directed by Stefan Kingham that traces the editor's ten-year journey; from a small team in Zurich building a browser-based editor called Monaco, to the tool most of us now open dozens of times a day. Watching it made me think back on my own relationship with VS Code, which turns out to be more of a slow conversion than a sudden switch. Two editors, one workflow For most of my career I've been a Visual Studio guy. Full IDE, integrated debugger, the whole .NET toolchain in one window. That didn't change overnight. What did change is that VS Code quietly became my default for anything web-related — a bit of JavaScript here, a config file there, a quick edit to a YAML pipeline. For years I ran both editors side by side, each with its own job. Visual Studio for "real" application code, VS Code for everything lighter and faster. The extensions ecosystem got me curious I always liked what t...

In my previous post , I covered what Copilot Spaces are and how to set one up. Spaces live on github.com by default, but you don't have to leave your editor to use one. The GitHub MCP server exposes your Spaces as tools, so you can pull that curated context straight into VS Code. Prerequisites You'll need the remote GitHub MCP server configured for VS Code, and the copilot_spaces toolset explicitly enabled. It's not part of the default toolset. The easiest way is to install the GitHub extension in VS Code. This will also add the GitHub MCP server. But as I mentioned above, you will not find the copilot_spaces toolset out-of-the-box. You need to open up the MCP configuration and explicitly add it there. Add this to your .vscode/mcp.json (or your global MCP configuration): { "servers": { "github": { "type": "http", "url": "https://api.githubcopilot.com/mcp/", "headers"...

A lot of developers are using GitHub Copilot as their day-to-day agent harness. But most of them seem to be unaware that with a GitHub Copilot license comes more than a CLI and Visual Studio (Code) plugins. One thing you get access to are GitHub Copilot Spaces. GitHub Copilot what? Let me first explain what Spaces are and why they are useful. Why GitHub Copilot Spaces? If you've used Copilot Chat for a while, you recognize the pattern: you paste in the same background information for the third time this week. The same coding conventions, the same architecture decisions, the same "no, we don't use that library anymore" context. Close the conversation, and Copilot forgets all of it. Remark: Part of the answer can be found in building up your CONTEXT.md file and using the GitHub Memory feature but it’s not always the right solution. That's because source code lives in your repositories, requirements live in issues and pull requests, and team conventions o...

If you've built anything with the Microsoft Agent Framework (MAF), you'll notice that your tool calls can fill up the context window quite fast. A function that returns a list of 50 orders as JSON easily costs you a few hundred tokens on braces, quotes and repeated field names alone. That cost hits you twice: once on the way into the model as tool output, and again on every subsequent turn where that history gets replayed. That's where TOON (Token-Oriented Object Notation) comes in. Let's explore this. What TOON actually is TOON is a line-oriented, indentation-based encoding of the same data model JSON uses. It borrows YAML's indentation for nested objects and CSV's tabular layout for arrays of uniform objects. The trick is in that last part: if you have a list of objects that all share the same fields, TOON declares the field list once and then just streams the values, row by row, instead of repeating every key for every item. Take a small object like t...

There's a version of leadership that looks busy, looks needed, and looks like it's working but turns out to be the least effective version there is. This summer I read Bob Chapman's Everybody Matters , and one distinction from the book kept coming back to me weeks after I'd finished it: firefighting versus firelighting, as two fundamentally different modes of leadership.   Chapman's point is simple to state and harder to live by. A firefighting leader spends their energy reacting: jumping from one problem to the next, stepping in to rescue a team the moment something goes wrong. A firelighting leader does the opposite. They don't chase problems. They ignite something in people, so the problems get solved without the leader showing up with the extinguisher every time. In the book, the differences are listed like this: Firefighting: Reactive by nature . You wait for the smoke before you act. The leader becomes the bottleneck. Nothing moves unti...

Note: this is a follow-up to my post on monitoring GitHub Copilot Chat with the Aspire Dashboard. Same idea, different agent. Some developers on the team have switched (part-time) from Copilot Chat to Claude Code for their agentic work. Same question came up again: how much are we actually using it, what does it cost, and where does the time go in a session? Claude Code has its own OTel support, separate from Copilot's, so it needs its own setup — but it plugs into the exact same Aspire Dashboard we already had running. What Claude Code exports Claude Code emits three kinds of OTel signals: Metrics — session counts, token usage, cost, lines of code changed, active time Events — one event per prompt, per API call, per tool result, per permission decision Traces (beta) — a claude_code.interaction span per prompt, with claude_code.llm_request and claude_code.tool spans nested underneath Remark: traces are still beta. Metrics and events are the stable path ...

When talking to developers I get wildly different opinions about how "good" GitHub Copilot actually was for them. Some love it, some find it slow, some weren't sure it was doing anything useful at all(just kidding). The problem: nobody had any data. We were talking about token usage, latency and tool calls purely from gut feeling. GitHub Copilot can export all of that as OpenTelemetry traces, metrics and events. And the easiest way to look at it locally, without spinning up a cloud backend, is the Aspire Dashboard. Let's set that up. Why do we need this? Copilot isn't just autocomplete anymore. Every agent turn is a small orchestration: it calls a model, the model asks for tools, the tools run, the model answers. If you want to know where the time and the tokens go, you need to see that orchestration, not just the end result. That's exactly what the Open Telemetry integration gives you. Every agent interaction produces a span tree: invoke_agent copil...

If you search for "GitHub Copilot budget policy", most posts point you to cost centers: assign a budget to a cost center, map the cost center to a team or business unit, done. Clean story, except for one detail nobody mentions upfront — cost centers require a GitHub Enterprise Cloud account. That's not the same thing as being on the Copilot Enterprise plan; user-level budgets already work fine on Copilot Business. It's about the account type; a standalone Organization account doesn't have cost centers, and neither does GitHub Enterprise Server if you're self-hosted. If you're not on Enterprise Cloud, cost centers are off the table. We ran into exactly this. No Enterprise Cloud account, no cost centers, but still a real need to keep Copilot spend under control across a growing user base. Remark: if you do have GitHub Enterprise Cloud, cost centers are probably still the better fit. This post is for the rest of us. The starting point We have two...

Recently I got lost setting up Renovate against an internal NuGet feed. Dependency updates kept coming back with a 401, even though I had hostRules configured with credentials right there in renovate.json . No error, no obvious warning in the log that jumped out at me. Just an anonymous request going out where an authenticated one should have. Turns out the config was fine. The location wasn't. The problem The error itself didn't point anywhere near the config file: { "message": "Request failed with status code 401 (Unauthorized): GET https://tfs.vlm.be/tfs/DefaultCollection/_packaging/VLMFeed/nuget/v3/index.json", "response": { "statusCode": 401, "statusMessage": "Unauthorized", "body": "{\"$id\":\"1\",\"innerException\":null,\"message\":\"TF400813: Resource not available for anonymous access. Client authentication required.\",\...

In my effort to adopt an 'AI first' philosophy, I spend a lot of time automating my day-to-day activities and transforming them to skills. It's not the most exciting activity: I know exactly how to do a task, I've done it a dozen times by hand, but writing it down as a clean SKILL.md for an agent takes almost as long as just doing the task again. Microsoft created an open-source a tool that skips that step entirely: Skill Recorder . The idea is simple: you record yourself doing the task once, and it generates the skill for you. Sounds good? Let’s give it a try… What it actually does Skill Recorder is a desktop app (Electron, macOS-first with Windows 11 support) that captures a real work session on your screen: clicks, app and window switches, the pages you visit, clipboard snippets, and optionally your spoken narration. Nothing leaves your machine while you're recording. Capture, storage, frame extraction, and narration transcription all happen locally. T...