hi, Spring fans! In this installment I have the privilege of talking to JetBrains legend Marco Behler

Hi, Spring fans! This week I'm in northern Europe. I went on the Vaadin cruise from Finland to Sweden, gave a talk on a boat, then arrived in Stockholm in time for the amazing JFokus 2026 event where I had the privilege yesterday of doing a deep dive with my pal James Ward on Spring AI and agentic patterns (some of which we also look at in this very roundup). Later today, I'm doing a talk introducing the new Spring Boot 4 support. Busy day, so let's dive right into this roundup!

• Spring gRPC 1.0.2 available now
• want your AI agents to be more intelligent? Check out this amazing new blog from the Spring AI team introducing Agent2Agent (A2A) support
• In last week's episode of A Bootiful Podcast, I talked to Java developer advocate Billy Korando
• Spring Cloud 2025.1.1 has been released
• and yet another blog form the Spring AI team, this one announcing agent skills support
• ... and this one introduces the subagent orchestration pattern with Spring AI
• Spring Shell 4.0.1 is out
• did you see InfoQ's Spring roundup?
• Makin-san has a nice blog post on instrumenting a DataSource…

Hi, Spring (and Java) fans! In this episode I am beyond delighted to talk Java developer advocate and longtime friend of the show Billy Korando about the latest-and-greatest in the Java ecosystem.

The Agent2Agent (A2A) Protocol is an open standard for seamless AI agent communication. It enables agents to discover capabilities, exchange messages, and coordinate workflows across platforms—regardless of their implementation.

Spring AI A2A integrates the A2A Java SDK with Spring AI through Spring Boot autoconfiguration. It seamlessly connects the A2A protocol with Spring AI's ChatClient and tools, enabling you to expose your agents as A2A servers.

This post is part of the Spring AI Agentic Patterns series. While previous posts covered making individual agents more capable (Agent Skills, AskUserQuestionTool, TodoWriteTool, Sub-agent orchestration), this post shows how the A2A Protocol enables agents to…

In this blog, we show how using Spring AI, we can integrate with Anthropic's Native Skills API for Cloud-Based Document Generation and Custom Skills.

Spring AI adds support for Anthropic's Agent Skills — modular capabilities that let Claude generate actual files rather than text descriptions. With Skills enabled, Claude produces real Excel spreadsheets, PowerPoint presentations, Word documents, and PDFs that you can download and use directly.

This post covers how Spring AI integrates with Skills, including both pre-built Skills and Custom Skills for organization-specific document generation.

…

Instead of one generalist agent doing everything, delegate to specialized agents. This keeps context windows focused—preventing the clutter that degrades performance.

Task tool, part of the spring-ai-agent-utils toolkit, is a portable, model-agnostic Spring AI implementation inspired by Claude Code's subagents. It enables hierarchical agent architectures where specialized subagents handle focused tasks in dedicated context windows, returning only essential results to the parent. Beyond Claude's markdown-based format, the architecture is extensible—supporting A2A and other agentic protocols…

Hi, Spring fans! Welcome to another installment of This Week in Spring! As I write this, I cannot believe we're nearly at the end of the month! Time sure flies.

• Spring AI 2.0.0-M2 is available now
• Spring Modulith 2.1 M1, 2.0.2, and 1.4.7 released
• In last week's installment of A Bootiful Podcast, I talked to JetBrains legend Dmitry Jemerov
• Spring Boot 3.5.10 is available now
• Spring Boot 4.0.2 is available now
• Spring Boot 4.1.0-M1 is available now
• Spring Batch 6.0.2 available now
• Spring Integration 7.1.0-M1 is available now
• Spring AI Agentic Patterns (pt. 3): Why Your AI Agent Forgets Tasks (and How to Fix It)
• Have you heard of WiseMapping? It's a fully open-source mind-mapping software suite with a web and desktop client and a backend written in Spring Boot. Neat…

Hi, Spring and IntelliJ IDEA fans! This week we celebrate 25 years of Jetbrains IntelliJ IDEA, and who better to talk to us about its evolution than Dmitry Jemerov, whose been a contributor and developer for the project since 2003!

Have you ever asked an AI agent to perform a complex multi-step task, only to find it skipped a critical step halfway through? You're not alone.

Research shows that LLMs struggle with "lost in the middle" failures—forgetting tasks buried in long contexts. When your agent juggles file edits, test execution, and documentation updates, important steps can silently disappear. One solution, inspired by Claude Code, is to make planning explicit and observable with the help of a dedicated TodoWrite tool. The result: agents that never skip steps and workflows you can observe in real-time.

This is Part 3 of our Spring AI Agentic Patterns series. We've covered Agent Skills for modular capabilities and AskUserQuestionTool for interactive workflows. Now we explore how TodoWriteTool…