# Spring AI 2.0 Brings Bedrock AgentCore to Java

URL: https://3ammarketer.com/news/spring-ai-agentcore-autonomous-agents
Published: 2026-11-12

> Spring AI 2.0 and the Spring AI AgentCore SDK establish a production stack for autonomous agents on Java JDK 21 and Spring Boot 4.x, moving past legacy Bedrock setups.

Spring AI 2.0 and spring-ai-agentcore 2.0 require Java JDK 21 and run with Spring Boot 4.x, modernizing how engineering teams deploy production Java agents. The release integrates the Spring AI AgentCore SDK, an open source library connecting Amazon Bedrock AgentCore infrastructure directly to the Spring AI ecosystem. This pattern shifts development away from Amazon Bedrock Agents Classic, which no longer allows new sign-ups. [1][2][3][4]

## Anthropic workflows versus Bedrock AgentCore primitives

![aws.amazon.com page on build autonomous ai agents](https://dygolixznokmekyvajbb.supabase.co/storage/v1/object/public/images/content/b549c18f5daec08532f2b043.png)

Anthropic distinguishes between agentic workflows and true autonomous agents. Workflows orchestrate large language models and tools through predefined code paths, whereas autonomous agents dynamically direct their own processes and tool execution. Operating in a goal-directed loop until a task finishes requires 3 core primitives: planning, tool use, and memory, as detailed in our guide on [autonomous AI agents runtimes and costs](/blog/autonomous-ai-agents-runtimes-costs). Tool design also governs reasoning requirements, as general-purpose tools demand more powerful language model reasoning capabilities than specialized tools. [1][5][6]

## Implementing the Spring AI 2.0 stack

The Spring AI 2.x.x mainline branch requires Java JDK 21 alongside Spring Boot 4.x. Inside this runtime, Spring AI provides an Advisors API designed to encapsulate recurring Generative AI patterns and transform data moving to and from language models while maintaining functional portability. The Spring AI framework supports major providers, including Anthropic, OpenAI, Amazon Bedrock, Google, Ollama, Mistral AI, and DeepSeek. [1][2]

## Designing for multi-agent coordination

For complex document workloads, Amazon outlines an Intelligent Document Processing (IDP) architecture running five specialist agents: Lawyer, Mortgage, Insurance, Tax, and General. A ClassifierAgent ingests incoming documents and routes them to the appropriate specialist based on classification rules. To optimize latency across multiple specialists, the system applies a parallel fan-out pattern. This coordination pattern concurrently dispatches one request to multiple specialist agents and aggregates their outputs before triggering a downstream rules engine. [1]

## Operationalizing the AgentCore runtime contract

Amazon Bedrock AgentCore provides a model-agnostic and framework-agnostic platform built to operate agents at scale. Teams evaluating infrastructure alongside [self-hosted AI agents](/blog/self-hosted-ai-agents) must satisfy the AgentCore runtime hosting contract by having their Spring Boot application expose two specific endpoints: /invocations for task routing and /ping for operational health checks. For fleet management, the AgentCore infrastructure supplies native monitoring and observability in a standardized OpenTelemetry compatible format. [1][7]

Our read: For Java teams running enterprise microservices, building on Spring AI 2.0 with the AgentCore runtime is the supported path. With Bedrock Agents Classic closed to new sign-ups, greenfield projects on AWS start on the AgentCore SDK and JDK 21.

Limit: The provided documentation does not report throughput benchmarks, token consumption rates, or per-invocation pricing models for running multi-agent fan-out workloads inside the AgentCore runtime.

## Sources

1. [Build autonomous AI agents with Amazon Bedrock and Spring AI | Artificial Intelligence](https://aws.amazon.com/blogs/machine-learning/build-autonomous-ai-agents-with-amazon-bedrock-and-spring-ai/)
2. [GitHub - spring-projects/spring-ai: An Application Framework for AI Engineering · GitHub](https://github.com/spring-projects/spring-ai)
3. [Java | Artificial Intelligence](https://aws.amazon.com/blogs/machine-learning/category/programing-language/java/)
4. [Automate tasks in your application using AI agents - Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/agents.html)
5. [Building effective AI agents \ Anthropic](https://www.anthropic.com/research/building-effective-agents)
6. [Designing tools for autonomous AI Agents | AWS Builder Center](https://builder.aws.com/content/2kZc4CuOGKY4Vwj5AmDEgkDQakr/designing-tools-for-autonomous-ai-agents)
7. [Building production-ready AI Agents with Spring AI, Embabel and Amazon Bedrock AgentCore - AWS User Group Dusseldorf 2026 | PDF](https://www.slideshare.net/slideshow/building-production-ready-ai-agents-with-spring-ai-embabel-and-amazon-bedrock-agentcore-aws-user-group-dusseldorf-2026/288594086)
