Wat ons bezighoudt
Onze laatste inzichten over AI, software development en architectuur. We schrijven in het Engels voor een breder bereik.
Hardening Docker Containers for Autonomous Claude Code
Hardening Docker Containers for Autonomous Claude Code
From Sandbox Struggles to Docker Bliss: Running Headless Claude Code in Production
How we built a fully automated GitHub ticket pipeline — and the isolation journey that made it reliable.
Koog for Java: JetBrains Ships an Enterprise AI Agent Framework for the JVM
JetBrains brings Koog — their Kotlin-born AI agent framework — to Java, giving enterprise teams a production-grade alternative to Python-based agent tooling.
Why Did Your AI Agent Call That Tool? Spring AI Has an Answer
How Spring AI's Tool Argument Augmenter lets you capture and expose the reasoning behind LLM tool call decisions — making AI agent behavior auditable and debuggable in production.
Claude Code Review: AI checking AI
Anthropic shipped a multi-agent code review feature for Claude Code. We look at what it does, why it matters, and what it means for engineering teams.
Unboxing Java 26: What Developers Need to Know Before Upgrading
Java 26 lands with HTTP/3 support, ahead-of-time object caching for any GC, and several removals — here's what changed since JDK 25 and what to watch out for.
Evaluating Spring AI Applications with Dokimos
A hands-on guide to evaluating LLM-powered Spring AI applications using Dokimos — from faithfulness checks to hallucination detection in your CI pipeline.
GitHub Claudomator: How We Let Claude Code Handle Our Entire Dev Backlog
An automated pipeline that picks up GitHub tickets, plans and implements them using Claude Code, and delivers ready-to-review pull requests.