<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>2026-10-11T11:11:02+02:00</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>From Jev to Microsoft-Decision-1</title><link href="https://stefanstranger.github.io/2026/10/10/FromJevToMicrosoftDecision/" rel="alternate" type="text/html" title="From Jev to Microsoft-Decision-1" /><published>2026-10-10T00:00:00+02:00</published> <updated>2026-10-10T00:00:00+02:00</updated> <id>https://stefanstranger.github.io/2026/10/10/FromJevToMicrosoftDecision/</id> <content type="text/html" src="https://stefanstranger.github.io/2026/10/10/FromJevToMicrosoftDecision/" /> <author> <name>Stefan Stranger</name> </author> <category term="AI" /> <category term="AI Models" /> <category term="Automation" /> <summary>Introduction There has been quite some hype about Jev AI, one of the first “new” decision models. If we read their blog post “Jev: The System One Model for Fast, Calibrated AI Decisions”, they called their decision model a System One Model, which they got from the two modes of human thinking, where System 1 is fast, intuitive, and automatic. E.g. you use this to decide if an email is spam or n...</summary> </entry> <entry><title>AI Tools I use daily</title><link href="https://stefanstranger.github.io/2026/08/14/AIToolsIUseDaily/" rel="alternate" type="text/html" title="AI Tools I use daily" /><published>2026-08-14T00:00:00+02:00</published> <updated>2026-08-14T00:00:00+02:00</updated> <id>https://stefanstranger.github.io/2026/08/14/AIToolsIUseDaily/</id> <content type="text/html" src="https://stefanstranger.github.io/2026/08/14/AIToolsIUseDaily/" /> <author> <name>Stefan Stranger</name> </author> <category term="AI" /> <category term="Agents" /> <category term="Tools" /> <category term="Python" /> <category term="Commandline" /> <category term="Automation" /> <summary>Introduction I always like to see which tools people are using in their day to day activities. In the past I watched for the blog posts from Scott Hanselman and the tools he is using. He has not published any new list of tools lately, but one of the latest tools he showed during our internal Microsoft MCAPS Tech Connect event was Handy. It is a free and open source app for speech to text, whic...</summary> </entry> <entry><title>Scout + LLM-Wiki - Building a Second Brain That My Agents Can Read</title><link href="https://stefanstranger.github.io/2026/07/22/LLM-Wiki-Scout/" rel="alternate" type="text/html" title="Scout + LLM-Wiki - Building a Second Brain That My Agents Can Read" /><published>2026-07-22T00:00:00+02:00</published> <updated>2026-07-22T00:00:00+02:00</updated> <id>https://stefanstranger.github.io/2026/07/22/LLM-Wiki-Scout/</id> <content type="text/html" src="https://stefanstranger.github.io/2026/07/22/LLM-Wiki-Scout/" /> <author> <name>Stefan Stranger</name> </author> <category term="AI" /> <category term="Agents" /> <category term="Knowledge Management" /> <summary>Introduction I have been running two experiments side by side for a while now. One is a personal knowledge wiki that I want both me and my agents to read. The other is Scout, Microsoft’s enterprise take on the OpenClaw-style always-on agent, where a small crew of named AI teammates helps me get work done. This week I finally wired the two together, and it turned out to be a lot more useful tha...</summary> </entry> <entry><title>Building an Harness Agent with Microsoft Agent Framework</title><link href="https://stefanstranger.github.io/2026/06/26/BuildingAnHarnessAgentWithMicrosoftAgentFramework/" rel="alternate" type="text/html" title="Building an Harness Agent with Microsoft Agent Framework" /><published>2026-06-26T00:00:00+02:00</published> <updated>2026-06-26T00:00:00+02:00</updated> <id>https://stefanstranger.github.io/2026/06/26/BuildingAnHarnessAgentWithMicrosoftAgentFramework/</id> <content type="text/html" src="https://stefanstranger.github.io/2026/06/26/BuildingAnHarnessAgentWithMicrosoftAgentFramework/" /> <author> <name>Stefan Stranger</name> </author> <category term="AI" /> <category term="Microsoft Agent Framework" /> <category term="Agents" /> <summary>Introduction I was at AgentCon Utrecht yesterday. Eduard van Valkenburg a Senior Software Engineer at Microsoft - CoreAI and Semantic Kernel &amp;amp; Agent Framework team demoed the Microsoft Agent Framework v1.0, and the Harness Agent pattern was the thing that stuck with me most on the drive home. I’ve been building agentic solutions for a while now, from CrewAI investment analysis workflows t...</summary> </entry> <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> </feed>
