Blog & Articles

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.

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

Spec-Driven Development gives agents a clear foundation for implementation. What it doesn’t solve is how a portfolio of systems stays coherent. Spec-Driven Architecture applies the same principle at the architecture level, using contracts as versioned boundaries and guarantees—enforceable in agentic workflows and in the CI/CD pipeline.

REST Beats MCP

How AI agents actually benefit from hypermedia

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?

The right size of a Data Product

Setting the boundaries of data products incorrectly can lead to integration issues, unclear ownership and duplicated logic. This guide offers practical heuristics for creating data products of the right size.

Agents good in the end?

A story of unleashed productivity and mental load

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.

Ein Überblick der AI-assistierten Softwareentwicklung in 2026

Birgitta Boeckeler (ThoughtWorks), Heinrich Hartmann (Zalando) und Sven Johann haben sich über den aktuellen Status der AI-assisted Software Entwicklung unterhalten: was ist wirklich Wichtiges in 2025 passiert? Welche stabilen Muster können wir ableiten? Was gibt Orientierung und Einordnung? Und natürlich ein paar Einblicke in den Future of Software Engineering Retreat in Utah an dem Birgitta teilgenommen hat. Die Unterhaltung gibt es natürlich auch als Podcast. Dieser Artikel ist aber eine menschlich kuratierte Zusammenfassung.

Features für einen schnelleren JVM-Start

Class Data Sharing, Project Leyden, CraC und mehr

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.

From Vibe Coder to Code Owner

AI agents generate thousands of lines of code in no time. If you want to fully leverage their potential, you can no longer review every single line – but you’re still responsible for the software. How do you take ownership of code you haven’t fully read? The answer lies in the agent harness: a system of deterministic checks, AI reviews, and targeted human review that enforces quality instead of hoping for it.

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

Restricting network access for AI coding agents with a proxy allowlist

Jeder kann Architekt sein!

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

Your Database Table is an awful API

A shared database table can feel like the ultimate shortcut: no API design, no contracts - just a schema. The catch is that this convenience quietly turns into friction: it blurs boundaries, slows change, and makes independent evolution harder than it needs to be. This article looks at why tables (and data-model-shaped “generated APIs”) are such a tempting trap - and what better integration boundaries look like.

Let’s Not Normalize Insecure AI Assistants

How the Lethal Trifecta Makes Today’s AI Assistants Unsafe by Design

Die persönliche KI ist schon da

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

What to Do While the AI Is Thinking

AI can write code while we wait — but that doesn’t mean we suddenly have free time. Whether we should think, multitask, review, or rest depends on what kind of work we are doing.

AI and Elaboration: Which Coding Patterns Build Understanding?

Developing with AI through the cognitive Lens

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.

Leave It Better Than You Found It

Leave your code better than you found it. This advice, also known as the Scout Rule, sounds so simple, but what does it look like in practice? This is the story of how I followed the advice and cleaned up a fat controller along the way, and how this unexpectedly enabled us to handle new requirements quickly and with minimal effort. It’s a lesson in habits and continuous architecture.

I sandboxed my coding agents. You should too.

My Lima VM + JetBrains Gateway setup for safe agentic development

Why not scatter @Transactional everywhere?

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

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

Bereits vor ein paar Jahren haben wir uns Dinge angeschaut, die in Java funktionieren, aber sehr ungewöhnlich sind. Diese Liste werden wir in dieser Folge des Praktikers ergänzen.

From FOMO to Focus

Clear Priorities in the AI Jungle with AI Opportunity Mapping

Speed vs. Skill

Every AI coding tool promises the same thing: unprecedented speed, effortless productivity, freedom from tedious work. The pitch is compelling. But what if feeling more productive and being more capable aren’t the same thing? Research shows that automation makes us feel more productive while eroding our skills. Let’s examine this tension through the lens of cognitive psychology.