Skip to content

Details

Join in with the latest Amsterdam JUG Meetup at Gustav Mahlerlaan 10, 1082 PP Amsterdam.

Agenda:

  • 18:00: Doors open and food and drinks.
  • 18:30 - 19:15: "A Lambda and JobRunr is All You Need for Distributed and Durable (Batch) Processing!" by Ronald Dehuysser
  • 19:15 - 20:00: "Building a Durable AI Agent Platform with Spring AI and Temporal" by Andrei Sulyz
  • 20:00 - 20:45: Topic to be announced by Max van Deursen
  • 21:00: The end

Abstracts:

"A Lambda and JobRunr is All You Need for Distributed and Durable (Batch) Processing!" by Ronald Dehuysser

Are you struggling with CPU-intensive tasks, high I/O work, or do you need to schedule background jobs without blocking the rest of your system? I often see teams building a scheduling solution themselves, severely underestimating the complexity of running jobs asynchronously. A costly endeavour, especially with a simple, free and open-source solution readily available.

During this entertaining session, I will introduce you to JobRunr: the ultimate open-source library for background processing in Java, recommended by ThoughtWorks. By transforming Java lambdas into distributed background tasks, JobRunr allows you to run any job at any time and on any JVM. We'll delve into its diverse features such as job persistence, durable executions, automatic retries, scalability (hello k8s), and the integrated dashboard to provide you with a good grasp of the possibilities.

After this session, you’ll have a good idea of what JobRunr is, how it does its magic and how it will allow you to focus on delivering value to your end users instead of implementing scheduling over and over again.

"Building a Durable AI Agent Platform with Spring AI and Temporal" by Andrei Sulyz

A prototype AI agent fits into a single service. In production, agent loops run for minutes or hours, wait for humans, call dozens of internal systems, and are needed by many teams at once. A crash in the middle means lost progress and paying for every LLM call again.

How do you make agent loops resume after Worker crashes, pod restarts and deployments? How does an agent safely call tools that live in other teams' isolated services? And how do you offer durable agentic capabilities to every team, whatever language they write in?

In this session, we'll walk through the architecture of a durable agentic platform built with Spring AI and Temporal, illustrated by the evolution of Stuart, our AI agent.

We'll cover two key aspects:

  • Durable, distributed agent loops: How the Temporal Spring AI integration makes model calls and tool executions durable using Temporal Activities, allowing workflows to recover from failures without restarting the entire agent loop.
  • An agentic platform with Temporal Nexus: How to build a shared platform where product teams expose their own domain tools and workflows as Nexus services, deployed independently and written in any Temporal SDK-supported language.

The talk is aimed at backend engineers, software architects, and tech leads building AI agents or distributed systems.

Related topics

You may also like