This Week in Spring - November 18th, 2025

Hi, Spring fans! I'm thrilled to be in New York City for an exciting week of joint presentations on Spring AI + Bedrock and Spring Boot with the legendary James Ward.

First up: we'll present a workshop at the AI Native Dev Conf today, then speak at the Garden State JUG tonight, then deliver a talk tomorrow at the conference, and finally speak at the New York Java SIG tomorrow night. It might be cold out, but we're bringing the heat!

You know who else is bringing the heat? The Spring team, of course! This past week saw Spring Framework 7 go GA, and with it a whole release train of new releases that will eventually culminate in Spring Boot 4. Once Spring Boot 4 is released, Spring AI, Spring Modulith, and Spring Cloud will all be able to release as well. Watch this space — spring.io/blog — for a ton of new releases this week culminating on the 20th with Spring Boot 4.0.0! (For more on what comes when, check out the Spring Calendar…

Hi, Spring fans! In this installment, I sit down with the legendary Bruce Eckel, who has probably forgotten more about programming languages than I will ever know, and whose book Thinking in Java helped launch me into a career.

This is a new blog post in the Road to GA series, this time sharing an update on the status of the null-safety support across the Spring portfolio, as a follow-up of my previous related blog post Null Safety in Spring applications with JSpecify and NullAway and related Spring I/O talk.

Are we fixing “the billion dollar mistake”?

Yes, we are! And by “we”, I mean the organizations involved in the JSpecify projects, the Spring team, and you, Spring developers who are going to upgrade to Spring Boot 4.

That said, I don’t think “the billion dollar mistake” was the invention of the null reference that Tony Hoare apologized for. I think the real mistake was to not express it explicitly in the type system, as this is the implicit nature of the nullability that causes so many NullPointerException…

The challenge of evaluating Large Language Model (LLM) outputs is critical for notoriously non-deterministic AI applications, especially as they move into production.

Traditional metrics like ROUGE and BLEU fall short when assessing the nuanced, contextual responses that modern LLMs produce. Human evaluation, while accurate, is expensive, slow, and doesn't scale.

Enter LLM-as-a-Judge - a powerful technique that uses LLMs themselves to evaluate the quality of AI-generated content. Research shows that sophisticated judge models can align with human judgment up to 85%, which is actually higher…

Hi, Spring fans! Welcome to another installment of This Week in Spring! As I write this I am preparing for a flight to North Carolina (first in flight!). This week's going to be busy, but next week even busier still! I'll be at AI By The Bay (in San Francisco), AI Native Dev Con (in NYC), and QCon SF (in SF). All in five days! It's going to be a ton of fun but I can't wait.

Why am I so busy? Because Spring's kind of a big thing and it should be and I want to share it. Which brings us to this week's roundup. So, without further ado, let's dive right into it!

• Good news everybody! Spring AI 1.1.0 RC1 is available now!
• yet another amazing post from Spring AI legend Christian Tsolov, this one on using Spring AI and an LLM as a judge
• Spring Boot 4.0.0 RC2 is now available
• Spring Tools 4.32.2 is available now
• in last week's installment of A Bootiful Podcast, I talked to the amazing Vaadin team
• this is so cool! I love it when this sort of stuff happens. thanks to the power of a good framework, optimizations in one place can result in huge improvements across the board!
• Hey, we just released the next set of GAs for Micrometer and Micrometer Tracing! This means that the Boot 4.0 generation's release train has just started. Micrometer 1.16.0 and …

Hi, Spring fans! In this installment, I had the privilege to sit down with Vaadin legends Joonas Lehtinen, Marcus Hellberg, and Leif Åstrand at the amazing Vaadin Create 2025 event in Frankfurt, Germany.

This is a new blog post in the Road to GA series, this time updating everyone on the plans to integrate Spring gRPC with Spring Boot 4. The original plan was to move the autoconfiguration from Spring gRPC into Spring Boot in time for the 4.0 release. Unfortunately we haven't been able to find the time to merge that change, but the good news is that we have instead added support for Spring Boot 4 to the existing Spring gRPC project, and are planning a 1.0 release in the coming days. This arrangement will continue until the merge can finally happen, most likely in an early milestone of Spring…

Hi, Spring fans! Welcome to another all-out installment of This Week in Spring wherein we attempt to recap all that's new and novel in the wild, wacky, and wonderful world of Springdom. And this week, I'm doing so from an airport in Switzerland, en route to Malmo, Sweden, for the amazing Oredev conference. If you're gonna be there, don't be shy: say hi!

We've got a lot to cover and I've got a flight to catch so let's dive right into it, shall we?

• Create Self-Improving AI Agents Using Spring AI Recursive Advisors - read this! This is super cool. Well done, Spring AI team!
• Spring for GraphQL 2.0.0 RC2 is now available
• Speaking of Spring AI, Spring AI 1.1.0-M4 is available now
• Spring Data 2025.1.0 RC2 is available today
• yet another riveting installment on the road to GA, this post looking at the newly modularized Spring Boot 4 architecture](https://spring.io/blog/2025/10/28/modularizing-spring-boot)
• Spring Framework 7 RC3 is available now!
• The AI space has a benchmarking problem, …

The Spring AI ChatClient offers a fluent API for communicating with an AI model. The fluent API provides methods for building the constituent parts of a prompt that gets passed to the AI model as input.

Advisors are a key part of the fluent API that intercept, modify, and enhance AI-driven interactions. The key benefits include encapsulating common Generative AI patterns, transforming data sent to and from Large Language Models (LLMs), and providing portability across various models and use cases.

Advisors process ChatClientRequest and ChatClientResponse objects. The framework chains advisors by their getOrder() values (lower values execute first), with the final…