subtitle: "LLM-Agnostic Skills That Run in Your Environment"

Agent Skills are modular folders of instructions, scripts, and resources that AI agents can discover and load on demand. Instead of hardcoding knowledge into prompts or creating specialized tools for every task, skills provide a flexible way to extend agent capabilities.

Spring AI's implementation brings Agent Skills to the Java ecosystem, ensuring LLM portability—define your skills once and use them with OpenAI, Anthropic, Google Gemini, or any other supported model.

This is the first post in our Spring AI Agentic Patterns series. This series explores the spring-ai-agent-utils toolkit—an extensive set of agentic patterns for Spring AI, inspired by Claude Code. We'll cover Agent Skills (this post…

Hi, Spring fans! In this installment, I have the privilege of sitting down and talking to the legendary Rob Winch, lead of Spring Security, Spring Session, and the amazing Testjars project.

Hi, Spring fans, to the first installment of This Week in Spring in the new year and, roughly, the fifteenth anniversary edition of this series! I've been writing these blogs since the first week of January of 2011, and I am proud to say that I haven't (so far) missed a single week! I've always published it on Tuesday (with some fuzziness around whose Tuesday, as I tend to bounce around the globe a fair bit). I want to thank, as I always do, Spring cofounder Keith Donald for this wonderful and simple idea. He dropped it in my lap and said to give it a shot, and I've never looked back. He's no…

In this episode, I talk with Mark Thomas, the legendary and highly prolific committer to Apache Tomcat. Happy New Year!

Hi, Spring fans! Can you believe it? It's already the 30th of December! I celebrated Christmas with my family in Los Angeles, then we jumped on a flight headed for Southeast Asia to ring in the New Year with more friends and family. I'm sitting at a café in the sweltering city of Kuala Lumpur, Malaysia as I write this - looking back fondly at the last week of, and the entire year of, 2025.

That's right! It's time for my yearly tradition of retroactive year-end navel‑gazing and analysis; it's time for This Year in Spring, where we review the good, the great, and the amazing: the top five best…

Back in September 2016, nearly a decade ago now, we introduced Spring Vault as a integration layer for HashiCorp Vault within Spring applications, complemented by Spring Cloud Vault for Spring Boot arrangements. The core idea has always been straightforward: Externalizing secrets to encrypted Vault storage to reduce application-side complexity considerably, especially by leveraging Vault's secure primitives for communication and authentication.

VaultTemplate and its reactive counterpart ReactiveVaultTemplate have served us well, providing a familiar Java-based programming interface for…

Hi Spring fans, and happy holidays! I'm delighted to be joined again on this episode by my friend and fellow harbinger of doom (in the best possible way), Nate Schutta — co-author of the wonderful book Foundations of Software Engineering!

Happy holidays, everyone! The year may be winding down, but the Spring ecosystem continues unabated. We’re now a few weeks past the generational Spring Boot 4.0 release in November, and there have been tons of releases (and patches) since then. There’s also equal excitement reflected in posts from the community, so we’ve got a lot to dig into this week. So, without further ado…

• In last week’s installment of A Bootiful Podcast, I talked to the legendary Spring cofounder Juergen Hoeller
  https://spring.io/blog/2025/12/18/a-bootiful-podcast-juergen-hoeller
• Next-level Kotlin support in Spring Boot 4
  https://spring.io/blog/2025/12/18/next-level-kotlin-support-in-spring-boot-4
• Spring Shell 4.0.0-RC1 available now
  https://spring.io/blog/2025/12/19/spring-shell-4-0-0-rc1-released
• Spring Modulith 2.0.1, 1.4.6, and 1.3.12 released
  https://spring.io/blog/2025/12/20/spring-modulith-2-0-1-1-4-6-and-1-3-12-released
• Spring Tools 5 released
  …

When building AI agents with tool calling capabilities, developers often need insights into why an LLM chose a particular tool—not just which tool it selected. Understanding the model's reasoning process is important for debugging, observability, and building trustworthy AI systems.

Spring AI now (2.0.0-SNAPSHOT/1.1.3-SNAPSHOT) includes the Tool Argument Augmenter feature that enables dynamic augmentation of tool input schemas with additional arguments before sending tool definitions to the LLM. This allows AI applications to capture extra information from the model—such as reasoning, inner…