The Evolution of Design Patterns in the Age of AI by Miro Wengner [16.03.2026]
The remarkable growth of artificial intelligence, particularly Large Language Models (LLMs) and AI-assisted coding, in recent years has introduced new challenges to software development. While LLMs can generate valuable outputs and code solutions, human oversight has become essential to prevent codebase deterioration, unexpected behaviors, and security vulnerabilities. Although the Gang of Four made significant contributions by identifying common software design challenges that businesses faced in the past, the technology landscape has evolved considerably. The widespread adoption of agentic AI systems has fundamentally changed how we approach software development, necessitating a fresh perspective on established practices. This evolution leads to an important conclusion: traditional design patterns and anti-patterns must be reconsidered in light of AI-driven development practices. This presentation will demonstrate how to enhance delivery flow and strengthen fast-feedback loops while identifying bottlenecks and eliminating obstacles from codebases. During the presentation, we will examine the characteristics of several anti-patterns that have emerged in AI-assisted development and explore how to transform them into effective design patterns that meet modern business requirements. --- About the speaker Miro is a distinguished engineer, AI scientist, architect, and team lead with a deep passion for resilient distributed systems and software craftsmanship. As a Java Champion and OpenJDK Committer (JFR), he contributes to the core of the Java ecosystem. His technical leadership has delivered measurable impact across diverse organization, achieving major gains in performance, architectural robustness, and cost efficiency. Miro is a contributor to open-source projects including Robo4J, Pi4J, and OpenTracing, and a trusted speaker at top international conferences. Miro is also focusing on the use and application of agentic AI systems based not only on LLM models across industries. With a proven track record, deep technical insight, and a collaborative mindset, Miro is an invaluable asset for any organization building innovative, high-performance systems, Java platforms and frameworks. Contact him on LinkedIn / mwengner ------ JUG Munich 📣 Infos about upcoming talks https://jugm.de/ 📹 Watch videos of previous talks / @javausergroupmunich ✉️ Become a member [email protected] 👉 Attend next events https://www.meetup.com/java-user-grou... --- Video recorded and edited by Ivan Milosavljević 🌐 https://thejavaguy.org/ 𝕏 / _the_java_guy_ 🦋 https://bsky.app/profile/thejavaguy.b... 𝐢𝐧 / thejavaguy1 📹 / @thejavaguy

Reaction to Jake Van Clief's Folder System (The Best AI Training Video Ever Made, Prove Me Wrong)
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLDbV4izF3i-wxevCVIn7FJjoy1vlA)
Yann LeCun's $1B Bet Against LLMs [Part 1]

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

Key questions& insights ANYbotics Part 5 @ the Robotics Roadshow Vienna

Stanford CS153 Frontier Systems | Scale, AGI, and the Future of Everything

AI hype is starting to sound like religion | Tim O'Reilly

Modern Architecture 101 for New Engineers & Forgetful Experts - Jerry Nixon - NDC Copenhagen 2025

Why AI Can Never Escape Turing's 1936 Proof

Andrej Karpathy: Software Is Changing (Again)

Claude Fable 5 is BANNED. What to do?

How To Think SO CLEARLY People Assume You're A Genius

This is not the AI we were promised | The Royal Society

Don't learn AI Agents without Learning these Fundamentals

Demis Hassabis: Agents, AGI & The Next Big Scientific Breakthrough

Mo Gawdat: The Skill You Need in the Age of AI

If Prime Numbers Become Increasingly Rare, Then Why Do They Keep Showing Up In Pairs?

"New Form of Imperialism": Renowned U.N. Scientist on AI Boom's Huge Water, Carbon & Land Footprint

I Made Opus 4.8 and Fable 5 Build the Same App (RAW RESULTS)

The French Do Not Care About Work

