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…

Hi, Spring fans! In this installment, we talk to my friend and Elastic's developer advocate extraordinairre Philip Krenn on the state of logging

In our previous blog post about Anthropic prompt caching, we explored how prompt caching dramatically reduces API costs and latency by reusing previously processed prompt content. We introduced Spring AI's five strategic caching patterns for Anthropic Claude models and showed how they automatically handle cache breakpoint placement while respecting the 4-breakpoint limit.

AWS Bedrock brings prompt caching to a broader ecosystem—supporting both Claude models (accessed via Bedrock) and Amazon's own Nova family. If you're considering Bedrock or already using it, you'll find the same Spring AI…

I'd like to introduce two new projects that are part of the Spring AI Community GitHub organization: Spring AI Agents, and Spring AI Bench. These two projects focus on using agentic coding tools—tools you likely already have in your enterprise.

In 2025 AI coding agents have matured to the point that they need to be seriously considered for enterprise Java development and general SDLC tasks. CLI Tools like Claude Code, Google’s Gemini CLI, Amazon Q Developer, and OpenAI’s assistants are examples from leading large AI labs, but there are also smaller startups and open-source options. These…