Training course · AI Agent Development · Java & Spring

AI Agent Development for Java and Spring Developers

Build AI agents professionally: architectures, tool use, agent SDKs, LangGraph, memory, evals, guardrails and deployment.

Duration
2 days (14 hrs)
Format
Online or on-site
Language
German or English
Participants
open dates or exclusive for your team
Certificate
Certificate of attendance

Overview

“AI Agent Development for Java and Spring Developers” is designed for roles such as Java back-end developers using Spring Boot or Jakarta EE, Teams modernising legacy Java applications and Software architects for enterprise and microservice landscapes and shows step by step how to use AI Agent Development productively, safely and transparently in Java & Spring – from the fundamentals to advanced workflows.

AI agents go beyond conventional chatbots: they break tasks down, call tools and APIs, evaluate the results and keep iterating until a goal is met. In this two-day course you learn to build such systems so that they work reliably, transparently and safely in day-to-day business. You compare architectural patterns ranging from simple workflows through the agent loop to multi-agent systems, and you implement them hands-on with the Claude Agent SDK, the OpenAI Agents SDK and LangGraph.

The focus is not on a quick demo but on the path to production. You design tool interfaces and context deliberately, connect tools via the Model Context Protocol, plan short-term and long-term memory and build evaluations that surface regressions early. On top of that come guardrails against prompt injection and harmful actions, human-in-the-loop approvals, tracing, cost control and deployment. By the end you can judge when an agent is worthwhile, when a deterministic workflow is enough and which framework fits your project.

Java and Spring carry business-critical systems in many organisations: banking back ends, ERP integrations, public-sector applications and large microservice estates. These systems have often grown over many years, and modernisation never stops. AI coding assistants and agents change the heaviest routine work in particular: major Spring Boot upgrades including the javax-to-jakarta switch, JUnit and Mockito tests for poorly covered code, refactorings towards records and modern language features, and analysis of stack traces and Hibernate issues. Clear guardrails are essential: build tool, module structure, architecture rules and test strategy all need to be in context. This course shows you how to use agents productively and in a controlled way in Maven or Gradle projects.

The course is delivered live – either online in a virtual classroom or on-site in our training rooms in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart and Kaiserslautern. We can also run it exclusively for your team.

Who is this course for?

  • Java back-end developers using Spring Boot or Jakarta EE
  • Teams modernising legacy Java applications
  • Software architects for enterprise and microservice landscapes
  • Developers in banking, insurance and the public sector
  • Tech leads responsible for upgrades and technical debt

Typical challenges we address

  • Laborious framework and JDK upgrades with numerous breaking changes
  • Large legacy codebases with low test coverage and tight coupling
  • Hard-to-analyse performance issues in JPA, Hibernate and transactions
  • Heavy boilerplate in configuration, mapping and interface code

What you will be able to do

  • You choose the right pattern for a task, from a fixed workflow to an autonomous agent.
  • You design tools and context so that agents work reliably and cost-effectively.
  • You implement agents with the Claude Agent SDK, the OpenAI Agents SDK or LangGraph.
  • You set up evaluations and tracing to measure quality and detect regressions.
  • Use AI agents for Spring Boot upgrades, refactorings and test generation in Maven and Gradle projects.
  • Diagnose Hibernate, performance and production issues faster with AI support.
  • Embed architecture rules and quality standards so that generated Java code adheres to them reliably.

Course outline

Day 1

Module 1 Agent architectures and design patterns
  • Workflows versus agents: prompt chaining, routing, parallelisation, orchestrator-worker
  • The agent loop: plan, act, observe, reflect
  • Multi-agent systems, subagents and handoffs between agents
  • Criteria for choosing model, framework and level of autonomy
Module 2 Tool use and context engineering
  • Function calling and structured outputs with JSON Schema
  • Designing good tools: granularity, naming, error messages, idempotency
  • Connecting and reusing tools via MCP servers
  • Managing the context window: summarisation, compaction, retrieval and prompt caching
Module 3 Frameworks in practice
  • Claude Agent SDK: agent loop, tools, subagents, permissions and hooks
  • OpenAI Agents SDK: agents, handoffs, guardrails and tracing
  • LangGraph: stateful graphs, checkpointing and human-in-the-loop
  • Side-by-side comparison on the same task and criteria for choosing a framework
Module 4 Memory, evals and observability
  • Short-term and long-term memory, storage strategies and forgetting
  • Evaluation datasets, LLM-as-a-judge and task-based success metrics
  • Tracing tool calls, token usage and latency
  • Regression testing when prompts, models or tools change

Day 2

Module 5 Guardrails, security and deployment
  • Protecting against prompt injection, data exfiltration and over-privileged tools
  • Input and output checks, approval steps and sandboxing
  • Deploying as a service, asynchronous execution, retries and cost limits
  • Governance, audit logging and requirements under GDPR and the EU AI Act
Module 6 Practice lab: Java & Spring
  • Driving a Spring Boot upgrade
  • Generating JUnit and Mockito tests
  • Refactoring legacy code
  • Analysing JPA and Hibernate issues
  • REST APIs and interfaces
  • Making sense of stack traces and production errors
Module 7 Data protection, quality & transfer to daily work
  • Java systems often run in regulated sectors: agree with information security and data protection which code may be sent to external models, and take requirements such as DORA, NIS2 or national banking IT rules into account. Generated code and new Maven dependencies should be checked for licences and known vulnerabilities and recorded in an SBOM.
  • Ground rules for safe AI use in your team
  • Checking results: facts, sources, tests and the four-eyes principle
  • Personal action plan for the next 30 days
  • Open questions, outlook and resources for further learning

Practical scenarios from your field

Driving a Spring Boot upgrade

The agent analyses dependencies, applies OpenRewrite recipes, switches javax packages to jakarta, adapts deprecated configuration and security setups and iterates over build and tests until the application is green again.

Generating JUnit and Mockito tests

Services and controllers get unit tests with JUnit and Mockito plus slice tests using WebMvcTest or DataJpaTest. The AI deliberately raises coverage on critical paths and documents test assumptions.

Refactoring legacy code

Large classes are split up, DTOs turned into records, null checks replaced with Optional and streams used where they help. Existing tests safeguard behaviour at every step.

Analysing JPA and Hibernate issues

The AI reads SQL logs and stack traces, spots N+1 queries, LazyInitializationExceptions and poor fetch strategies, and proposes entity graphs, projections or index changes. Each optimisation is backed by SQL logs.

REST APIs and interfaces

OpenAPI specifications are turned into controllers, DTOs, MapStruct mappers and Bean Validation, complete with consistent error handling via ControllerAdvice and integration tests. Existing package and naming conventions are respected.

Making sense of stack traces and production errors

Long stack traces, thread dumps and log excerpts are summarised, the likely root cause is narrowed down and a reproducing test case plus fix is proposed.

Possible hands-on projects

Spring Boot microservice

A REST service with Spring Data JPA, Flyway migrations, Bean Validation, Actuator endpoints and Testcontainers tests, developed entirely by an AI agent from a specification.

Dependency report for Maven and Gradle

A command-line tool that analyses build files, lists outdated and vulnerable libraries and describes upgrade paths along with expected breaking changes.

Architecture rule checks

An ArchUnit test suite that automatically enforces your project’s layering rules, package dependencies and naming conventions and runs in the CI pipeline.

Prerequisites

Solid programming skills in Python or TypeScript, experience with REST APIs and some hands-on experience with LLM APIs or AI assistants. In-depth Java knowledge and practical experience with Spring Boot or Jakarta EE, Maven or Gradle and Git.

Technical requirements

A laptop with Python or Node.js, Git and a code editor, plus API access to at least one LLM provider such as Anthropic or OpenAI. Credentials for the exercises can be provided if needed.

Data protection & compliance

Java systems often run in regulated sectors: agree with information security and data protection which code may be sent to external models, and take requirements such as DORA, NIS2 or national banking IT rules into account. Generated code and new Maven dependencies should be checked for licences and known vulnerabilities and recorded in an SBOM.

Suggested dates

All dates are suggestions – your preferred date is always possible.

  • Wed, 25 November 2026 – Thu, 26 November 2026 Online Request
  • Thu, 10 December 2026 – Fri, 11 December 2026 Bremen Request
  • Tue, 12 January 2027 – Wed, 13 January 2027 Online Request
  • Tue, 19 January 2027 – Wed, 20 January 2027 Salzburg Request
  • Tue, 26 January 2027 – Wed, 27 January 2027 Online Request
  • Tue, 2 February 2027 – Wed, 3 February 2027 Kaiserslautern Request

Frequently asked questions

Which agent framework should we use?

It depends on your model strategy, the level of control you need and your team’s skills. Vendor SDKs offer a lean start with tightly integrated features, while LangGraph gives you finer control over state and flow. In the course you solve the same task with several frameworks and derive clear selection criteria for your own project.

How do you stop an agent from taking wrong or dangerous actions?

With several layers of protection: narrowly scoped tools with minimal permissions, input and output validation, approval steps for critical actions, sandboxing and continuous evaluation. Prompt injection via external content is treated as a realistic threat. You practise these measures directly on your own agent.

Does every automation need an agent?

No. Many tasks are handled more reliably, cheaply and transparently by a fixed workflow of a few LLM calls. Agents pay off when the solution path cannot be planned in advance and the system must react flexibly to intermediate results. We train exactly this trade-off using practical examples.

Can an AI agent carry out a major Spring Boot upgrade on its own?

An agent can take on much of the mechanical work – package switches, configuration changes and iteratively fixing compile and test failures – especially when combined with OpenRewrite. Architecture decisions, functional sign-off and testing in realistic environments remain the team’s job. On the course you practise this workflow on a sample project.

Is AI-assisted coding allowed in regulated environments?

In principle yes, but with clear rules. What matters is the choice of provider and operating model, contractual commitments on data use, approval processes and traceable reviews. We discuss how banks, insurers and public authorities typically approach this and which questions you should settle with your information security team.

How much does “AI Agent Development for Java and Spring Developers” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 2 training day(s) with a live trainer, course materials, a lab environment and a certificate of attendance.

Can I suggest my own date?

Yes. Our suggested dates are just a guide. In the request form you can always describe your preferred date or period in free text – we check availability and confirm within one working day.

Is the course online or on-site?

Both are possible: live online in a virtual classroom or on-site in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart or Kaiserslautern. We can also run the course exclusively for your team.

More courses for Java and Spring Developers

More AI Agent Development courses

All 30 AI Agent Development courses

AI Agent Development · MunichAI Agent Development · SalzburgAI Agent Development · BerlinAI Agent Development · AugsburgAI Agent Development · HanoverAI Agent Development · BremenAI Agent Development · StuttgartAI Agent Development · KaiserslauternAI Agent Development · Online