<feed xmlns="http://www.w3.org/2005/Atom"> <id>https://stefanstranger.github.io/</id><title>Stefan Stranger's Blog</title><subtitle>This is my personal blog. I work at Microsoft as a Consultant. You can find some of my open source projects on Github. I like to share my knowledge about AI, Azure, PowerShell and DevOps</subtitle> <updated>2026-03-09T13:09:03+01:00</updated> <author> <name>Stefan Stranger</name> <uri>https://stefanstranger.github.io/</uri> </author><link rel="self" type="application/atom+xml" href="https://stefanstranger.github.io/feed.xml"/><link rel="alternate" type="text/html" hreflang="en" href="https://stefanstranger.github.io/"/> <generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator> <rights> © 2026 Stefan Stranger </rights> <icon>/assets/img/favicons/favicon.ico</icon> <logo>/assets/img/favicons/favicon-96x96.png</logo> <entry><title>Which GitHub Copilot CLI Model Should You Use and When?</title><link href="https://stefanstranger.github.io/2026/03/07/WhichGitHubCopilotCLIModelShouldYouUseandWhen/" rel="alternate" type="text/html" title="Which GitHub Copilot CLI Model Should You Use and When?" /><published>2026-03-07T00:00:00+01:00</published> <updated>2026-03-07T00:00:00+01:00</updated> <id>https://stefanstranger.github.io/2026/03/07/WhichGitHubCopilotCLIModelShouldYouUseandWhen/</id> <content type="text/html" src="https://stefanstranger.github.io/2026/03/07/WhichGitHubCopilotCLIModelShouldYouUseandWhen/" /> <author> <name>Stefan Stranger</name> </author> <category term="AI" /> <category term="Github Copilot" /> <category term="AI Models" /> <summary>TL;DR I used the LLM Council technique to have all 17 GitHub Copilot CLI models anonymously evaluate themselves and each other. Key findings: Opus models = deep reasoning, architecture decisions, “the expensive senior engineer” Sonnet models = balanced capability/speed, good default for most coding tasks Haiku / Mini models = fast execution for simple, well-defined tasks Codex models...</summary> </entry> <entry><title>What are AI Agent Evaluators and Why They Matter</title><link href="https://stefanstranger.github.io/2026/01/07/WhatareAIAgentEvaluatorsandWhyTheyMatter/" rel="alternate" type="text/html" title="What are AI Agent Evaluators and Why They Matter" /><published>2026-01-07T00:00:00+01:00</published> <updated>2026-01-07T00:00:00+01:00</updated> <id>https://stefanstranger.github.io/2026/01/07/WhatareAIAgentEvaluatorsandWhyTheyMatter/</id> <content type="text/html" src="https://stefanstranger.github.io/2026/01/07/WhatareAIAgentEvaluatorsandWhyTheyMatter/" /> <author> <name>Stefan Stranger</name> </author> <category term="AI" /> <category term="Agentic AI" /> <category term="Observability" /> <summary>Introduction I recently bought the book Designing Multi-Agent Systems: Principles, Patterns, and Implementation for AI Agents by Victor Dibia. In chapter 10 “Evaluating Multi-Agent Systems” he discusses how to build evaluation frameworks with LLM-as-judge and metrics. This was a new topic for me and wanted to learn more about what Agent Evaluators are and why they matter. This is why I wrot...</summary> </entry> <entry><title>How to use Agent Skills in Github Copilot</title><link href="https://stefanstranger.github.io/2025/12/29/AgentSkillsInGithubCopilot/" rel="alternate" type="text/html" title="How to use Agent Skills in Github Copilot" /><published>2025-12-29T00:00:00+01:00</published> <updated>2025-12-29T00:00:00+01:00</updated> <id>https://stefanstranger.github.io/2025/12/29/AgentSkillsInGithubCopilot/</id> <content type="text/html" src="https://stefanstranger.github.io/2025/12/29/AgentSkillsInGithubCopilot/" /> <author> <name>Stefan Stranger</name> </author> <category term="AI" /> <category term="Coding" /> <category term="Github Copilot" /> <summary>Introduction Why use Skills? Github Copilot and Agent Skills Getting Started with Agent Skills 1. Create a Skills Directory 2. Create a Subdirectory for Each Skill 3. Create a SKILL.md File 4. Add Resources (Optional) Example SKILL.md File Helper Scripts Reference scripts/check_uv.py scripts/setup_project.ps1 scripts/create_p...</summary> </entry> <entry><title>Simplifying Azure Verified Module Discovery with Model Context Protocol</title><link href="https://stefanstranger.github.io/2025/11/14/avm-mcp-server/" rel="alternate" type="text/html" title="Simplifying Azure Verified Module Discovery with Model Context Protocol" /><published>2025-11-14T00:00:00+01:00</published> <updated>2025-11-14T00:00:00+01:00</updated> <id>https://stefanstranger.github.io/2025/11/14/avm-mcp-server/</id> <content type="text/html" src="https://stefanstranger.github.io/2025/11/14/avm-mcp-server/" /> <author> <name>Stefan Stranger</name> </author> <category term="Azure" /> <category term="AI" /> <category term="Infrastructure as Code" /> <summary>Introduction What is the Azure Verified Modules MCP Server? Why Did I Create This MCP Server? How Does the AVM MCP Server Work? Key Features Comparison with Microsoft Bicep MCP Server When to Use Each Server Usage Scenarios Discovering the Right Module Understanding Module Parameters Programmatic Integration Getting Started ...</summary> </entry> <entry><title>Revolutionize Your VanMoof Experience with the VanMoof MCP Server</title><link href="https://stefanstranger.github.io/2025/04/25/VanMoofMCPServer/" rel="alternate" type="text/html" title="Revolutionize Your VanMoof Experience with the VanMoof MCP Server" /><published>2025-04-25T00:00:00+02:00</published> <updated>2025-04-25T00:00:00+02:00</updated> <id>https://stefanstranger.github.io/2025/04/25/VanMoofMCPServer/</id> <content type="text/html" src="https://stefanstranger.github.io/2025/04/25/VanMoofMCPServer/" /> <author> <name>Stefan Stranger</name> </author> <category term="AI" /> <category term="Bikes" /> <category term="Development" /> <summary>Introduction Imagine having your AI assistant provide real-time insights about your VanMoof bike rides. With the new VanMoof MCP Server, this is now a reality. In this blog post, I’ll walk you through how the VanMoof MCP Server bridges the gap between your AI assistant and your VanMoof bike, allowing you to access bike details and riding stats effortlessly. Unlock the Power of AI with VanMoof ...</summary> </entry> </feed>
