Blog & Articles

Gute Last, schlechte Last

Mehr Struktur, mehr Output, mehr Erschöpfung. Spec-driven Development hat mir zwar bessere Ergebnisse mit KI-Agenten beschert, aber auch gleichzeitig die Freude am Bauen genommen. Über gute Last, schlechte Last und versteckte Kosten, die keiner einplant.

Blog Post

Where AI Helps (and Hurts) Across Different Coding Scenarios

Where does LLM-assisted software development improve developer productivity—and where does it fall short? Instead of treating AI in software development as a one-dimensional productivity booster, we explore the question across several dimensions suggested by a Stanford-adjacent study: project maturity, task complexity, and the popularity of the programming language. The goal is to create a more realistic expectation baseline for both software developers and leaders—well away from today’s hype.

Blog Post

Spec-Driven Architecture: When Agents Build, Architecture Must Speak

SDD describes how a system is built. SDA describes how systems fit together

Blog Post

REST Beats MCP

Instead of using dedicated APIs, agents can operate existing web applications directly. Like humans, they rely on the most consistent implementation of hypermedia and benefit from existing context, validation, and access controls. Using an expense report as an example, I show how agents can automate complex, context-dependent tasks—without having to implement new APIs.

Blog Post

Spec-Driven Development is Domain-Driven Design’s Impatient Cousin

Spec-driven development tools like BMAD promise to fix the requirements bottleneck that agentic development teams face. But is it actually a good fit for your organisation?

Article

The right size of a Data Product

Autonomous Data Product Heuristics

Blog Post

Agents good in the end?

Software development consists of a constant chain of trade-offs. As long as I’ve been building systems, there have always been things you don’t do despite wanting to do them. But now, with agents, we can fulfill all our dreams and finally build everything we always wanted and had the feeling we were missing. Spoiler alert: we shouldn’t do that.

Blog Post

Understanding AI Coding Patterns Through Cognitive Load Theory

AI coding assistants either severely harm learning or enhance it beyond manual coding—depending entirely on interaction patterns. A recent study reveals six distinct patterns with dramatically different outcomes. We’ll examine why through cognitive psychology and explore the study’s limitations.

Article

Ein Überblick der AI-assistierten Softwareentwicklung in 2026

Orientierung für Verwirrte

Article

Features für einen schnelleren JVM-Start

In diesem Artikel wollen wir uns mit dem Kritikpunkt der langsamen Startzeit der JVM beschäftigen. Dazu schauen wir uns an, was eigentlich beim Start passiert und mit welchen schon vorhandenen oder in Zukunft kommenden Features die Startzeit verbessert werden kann.

Article

Neuland reloaded

When Angela Merkel said in 2013 that the internet is ‘Neuland’ (uncharted territory) for all of us, the amusement online was considerable. Viewed from some temporal and substantive distance, one can now recognize a perspective from which she was indeed correct.

Blog Post

From Vibe Coder to Code Owner

Blog Post

I sandboxed my coding agents. Now I control their network.

I want my AI coding agents to work independently, but I don’t want them to have unrestricted access to the internet. In this post, I describe how I routed all network traffic from my development sandbox through a strict proxy allowlist, allowing only a small set of explicitly approved domains. This setup finally gave me enough confidence to loosen the guardrails without constantly staying in the loop.

Article

Jeder kann Architekt sein!

Und jede natürlich auch. In diesem Artikel zeige ich, dass die Architektenrolle andere Kompetenzen verlangt, als viele annehmen.

Blog Post

Your Database Table is an awful API

Is database integration still a thing?

Blog Post

Let’s Not Normalize Insecure AI Assistants

AI assistants like OpenClaw promise convenience, autonomy, and increasingly personalized help. But beneath that promise lies an architecture that quietly combines private data, internet access, and exposure to untrusted content—the lethal trifecta of security risk. Sandboxing and physical isolation help, but they don’t address the core problem. As we add more capabilities, the potential blast radius only grows. This post is a case for slowing down, questioning defaults, and refusing to normalize insecure architectures.

Blog Post

Die persönliche KI ist schon da

Drei Wochen mit OpenClaw auf einem Raspberry Pi und ein Blick darauf, was auf die Softwarearchitektur zukommt.

Blog Post

What to Do While the AI Is Thinking

How deep work, multitasking, and code reviews change as we delegate tasks to AI

Blog Post

AI and Elaboration: Which Coding Patterns Build Understanding?

AI tools let you complete coding tasks without connecting new information to your existing mental models—a cognitive process known as elaboration that is crucial for building understanding. But some AI interaction patterns preserve this elaboration while others bypass it entirely. Let’s explore what elaboration is, why it helps with learning, and how we can use AI tools in a way that helps with this process rather than circumventing it.

Blog Post

Fetch-Tools vs. Browser-Rendering in Agenten-Setups

„Eine URL abrufen“ klingt trivial, kann aber innerhalb eines Agenten schnell chaotisch werden. Ein Teil der Verwirrung entsteht durch Dokumentation, die nicht sauber trennt, was die einzelnen Web-Tools eigentlich leisten.

Blog Post

Leave It Better Than You Found It

An Unexpected Architecture Win

Blog Post

I sandboxed my coding agents. You should too.

LLM coding agents are extremely powerful because they can run programs on our computers using our permissions. However, this same power also makes us very vulnerable. It only takes one mistake or one prompt injection to compromise the whole system.

Blog Post

Why not scatter @Transactional everywhere?

@Transactional — great when you know when not to use it. Use it consciously instead of sprinkling it everywhere!

Article

Was, da geht noch mehr? Noch mehr Besonderheiten von und mit Java

Blog Post

From FOMO to Focus

AI is on every agenda – but where do you start? Many companies launch multiple AI initiatives in parallel, driven by the fear of missing out. The result: scattered resources, lack of prioritization, and unclear business impact. AI Opportunity Mapping provides a solution: it systematically guides you from vague AI visions to concrete, prioritized use cases with real business value. In five steps, teams develop AI opportunities in a structured way and make well-founded decisions. The result: focus instead of FOMO, clarity instead of chaos.