DaShaun Carter

Agentic AI Workflows with Embabel

We have all seen the “Hello, World” of Spring AI: sending a prompt and getting a response. But as we move toward production, the real challenge is not the LLM call; it is the workflow. How do you ensure an agent does not loop infinitely? How do you coordinate multiple tools without a mess of “if-else” blocks? And how do we keep our Java-centric domain models at the heart of the AI’s reasoning?

Enter Embabel, a new JVM-based framework from Rod Johnson (creator of Spring) designed to bring discipline to agentic AI. Unlike Python-centric alternatives, Embabel is built on the philosophy of strong typing, OODA loops (Observe, Orient, Decide, Act), and Goal-Oriented Action Planning (GOAP).

In this session, we will go beyond basic RAG and explore how to build “digital workers” that can actually plan. You will learn: How to turn your existing Spring Beans into AI Actions.

The shift from imperative coding to Goal-Oriented orchestration.

How Embabel uses DICE (Domain-Integrated Context Engineering) to give agents true domain knowledge.

Why the JVM is actually the best place to run mission-critical AI agents.

Join us for a code-heavy look at the future of Java backend development. We are moving to a world where our systems do not just respond to requests, but actively work to achieve goals.

Engineering Autonomous Agents with Embabel and Spring

The “Hello, World” of Spring AI involves sending a prompt and receiving a text response. This is no longer enough for production. To build enterprise grade AI, we must move beyond simple request and response cycles toward autonomous agents capable of reasoning, planning, and executing complex workflows. The challenge is doing this without losing the type safety, observability, and domain driven design that makes the Java ecosystem the backbone of enterprise software.

Join us for a three hour deep dive into Embabel, the new JVM framework from Rod Johnson designed for disciplined agentic AI. This workshop moves past the “if-else” mess of basic orchestration and introduces an architecture based on OODA loops and Goal Oriented Action Planning (GOAP).

Part 1: From Prompting to Planning (90 Minutes)
In the first half, we move from imperative logic to Goal Oriented orchestration. You will learn the core philosophy of Embabel and how it uses the OODA loop (Observe, Orient, Decide, Act) to maintain stateful awareness. This module focuses heavily on DICE (Domain-Integrated Context Engineering) which allows you to move beyond simple RAG by injecting your existing Java domain models directly into the agent’s reasoning process. You will learn the planning mindset by defining clear goals rather than rigid paths, allowing the AI to navigate your business rules dynamically.

Part 2: Building the Digital Worker (90 Minutes)
The second half is a hands-on lab where we turn theory into a functioning agent. We will explore the process of turning your existing Spring Beans into AI Actions by defining preconditions and effects so that Embabel can construct plans without infinite loops. We will also address what happens when an LLM hallucinates or a tool fails. This includes exploring advanced patterns for error handling and plan repair to demonstrate why the JVM is the superior environment for mission critical AI.

By the end of this workshop, you will have built a functional Digital Worker capable of navigating a complex domain and interacting with real Spring managed services. You will leave with a local prototype and a blueprint for bringing agentic AI to your organization. Participants should have experience with Spring Boot and Java or Kotlin as well as a laptop with a JDK 17+ environment.

Stop just calling APIs and start building workers. This workshop provides a code heavy look at the future of Java backend development where systems do not just respond to requests but actively work to achieve goals.

Engineering Autonomous Agents with Embabel and Spring

The “Hello, World” of Spring AI involves sending a prompt and receiving a text response. This is no longer enough for production. To build enterprise grade AI, we must move beyond simple request and response cycles toward autonomous agents capable of reasoning, planning, and executing complex workflows. The challenge is doing this without losing the type safety, observability, and domain driven design that makes the Java ecosystem the backbone of enterprise software.

Join us for a three hour deep dive into Embabel, the new JVM framework from Rod Johnson designed for disciplined agentic AI. This workshop moves past the “if-else” mess of basic orchestration and introduces an architecture based on OODA loops and Goal Oriented Action Planning (GOAP).

Part 1: From Prompting to Planning (90 Minutes)
In the first half, we move from imperative logic to Goal Oriented orchestration. You will learn the core philosophy of Embabel and how it uses the OODA loop (Observe, Orient, Decide, Act) to maintain stateful awareness. This module focuses heavily on DICE (Domain-Integrated Context Engineering) which allows you to move beyond simple RAG by injecting your existing Java domain models directly into the agent’s reasoning process. You will learn the planning mindset by defining clear goals rather than rigid paths, allowing the AI to navigate your business rules dynamically.

Part 2: Building the Digital Worker (90 Minutes)
The second half is a hands-on lab where we turn theory into a functioning agent. We will explore the process of turning your existing Spring Beans into AI Actions by defining preconditions and effects so that Embabel can construct plans without infinite loops. We will also address what happens when an LLM hallucinates or a tool fails. This includes exploring advanced patterns for error handling and plan repair to demonstrate why the JVM is the superior environment for mission critical AI.

By the end of this workshop, you will have built a functional Digital Worker capable of navigating a complex domain and interacting with real Spring managed services. You will leave with a local prototype and a blueprint for bringing agentic AI to your organization. Participants should have experience with Spring Boot and Java or Kotlin as well as a laptop with a JDK 17+ environment.

Stop just calling APIs and start building workers. This workshop provides a code heavy look at the future of Java backend development where systems do not just respond to requests but actively work to achieve goals.