TL;DR: Vibe coding is great for PoCs and miserable for real projects. I had Claude write 55,000 lines of code for me in about eight weeks and learned that skills and claude.md are not sufficient. At the bottom of this post there’s a plugin that packages the method I developed. It gives traceable, fully documented […]
Category: Uncategorized
Next Level Vibe Coding
Specification-First Agentic Development optimizes working with coding agents via treating specifications as the main artifact. Coding agents forget, misinterpret, and lose context. While CLAUDE.md combined with skills improve the behavior, it is not sufficient. TL;DR When wanting to keep track about feature implementation with any AI as an assistent, have a look at the github […]
Can You Defend Your AI’s Decisions?
Why Multi-Agent Systems Must Be Sequential in Agent Smith. Most multi-agent demos look impressive. Five agents discussing a problem, contradicting each other, refining ideas, eventually converging on a solution. It feels like watching a real engineering team at work. But it isn’t. Imagine a development team working like this. It’s a room where everyone talks […]
What Do You Want to Do, Claude?
Part 1 of a series about what happens when you stop giving AI instructions and start listening. I’ve been coding since 1985. Commodore 64, assembler, then decades of .net, cloud, Terraform, Big Data. I run my own consulting business. I’ve been around long enough to not get easily impressed by technology. So let’s try something […]
Azure Function Dependency Injection with AutoFac: Autofac on Functions
Autofac on Azure Functions. Azure still keeps evoling a lot. The next new and hot thing is Azure Functions. What makes Azure Function attractive? In the past six months I did have a look onto Azure Functions more often, but was on one hand pretty busy with a move to a different company and on the […]
GetDependsOnNetStandard task failed unexpectedly – Nuget Package Manager Visual Studio 2017 Magic.
Yesterday I got a message from a collegue of mine that building a solution with Visual Studio failed ungracefully. He directly got the sources from git freshly, there was no interaction by him. I checked my last commits and couldn’t see anything that was wrong. So I just got all the sources in a new place and […]
Bad Image Exception on Azure Service Fabric Unit Tests
I just experienced this System.BadImageFormatException. Could not load file or assembly ‘System.Fabric, Version=5.0.0.0, Culture=neutral, PublicKeyToken=31bf3856ad364e35’ or one of its dependencies. An attempt was made to load a program with an incorrect format. The unit test shall test a Azure Service Bus connection. Yes, sure it is a unit test and the service bus connection actually should […]
Do you start with the data or with the test?
I recently had some discussions about TDD. I personally never tried to accomplish the procedure seriously. So I wanted to invest a little time to understand if it does fit to my needs, especially if it is more effective in short and long term perspective. I wanted to use a simple example. Not too complex and […]
Handy time measurement with Windsor Castle AOP
This is a good old issue, how to know where the program spends most of its time? If you want to spend the money, the best profiling tool from my point of view is still JetBrains’ DotTrace. You’ll get a lot of information down on method level, great stuff. But how can the program execution time be […]
Funny (VBA) features in SAP BEx
Recently I had to deal with good old VBA. The product I had to do a bugfix/ heavy testing for is completely written in C#, but automates Office. Mostly Excel, but also PowerPoint all running as a service. I had the pleasure to implement an automatic logon with Excel for BEx. BEx, aka SAP Business […]