Current topics, practical solutions, and fresh ideas: On the HMS blog, you'll learn how companies successfully use data and analytics.
AI Agents in Software Development: How to Work Successfully with Copilot
How can AI agents like GitHub Copilot be meaningfully integrated into everyday development work without losing sight of code quality? Using his personal workflow as an example, Robin Mader demonstrates how to delegate tasks to agents in a targeted manner, systematically review results, and combine human expertise with AI support. A practical look at how humans and AI collaborate in modern software development.
Coding Agents in Software Development: 5 Insights from AI-Powered Projects
Coding agents speed up software development—but what happens when code is no longer the biggest bottleneck? Five insights from an HMS project show why understanding the problem, early prototyping, and rapid feedback are crucial to the success of AI-powered software projects.
On-Premises LLMs in the Enterprise: When Is On-Premises Deployment Worth It?
Local LLMs offer businesses new opportunities for greater data sovereignty and control. Learn how local language models compare to cloud AI in terms of cost, performance, and security, and find out which operating model best suits your needs.
AI-Friendly Architecture: How to Keep AI Coding Agents Under Control in a Project
AI coding agents work reliably only if they can navigate the codebase and adhere to established development processes. Christoph Bergen and Robert Bauer explain the role that architecture, documentation, automated tests, and an advanced agent harness play in this process.
Reliable Coding Agents in Practice: Insights from the Superpowers Workflow
AI coding agents don't become reliable simply by using better models. Using the Superpowers workflow as an example, this article shows how context, testing, reviews, and clear decision-making processes contribute to reproducible results.
Loop Engineering: How Reliable AI Coding Agents Are Created
How Do AI Coding Agents Become Reliable? This article explains how Loop Engineering uses feedback, testing, and clear termination conditions to turn one-off model responses into controlled, adaptive workflows.
Thread Safety in Python: What Changes with Free-Threaded Python
Free-threaded Python enables true parallel thread execution, thereby changing the requirements for modern Python applications. This article explains where race conditions can arise and how to develop thread-safe Python code using locks, queues, events, and other synchronization mechanisms.
SPN Connect and the World Tour 2025 demonstrated that industries such as pharmaceuticals, media, and logistics are already using AI, AISQL, and Cortex to deliver measurable added value. How can these technologies be used responsibly and in a way that yields measurable results today?
