Craig Walls

In this example-driven session, we'll take a look at how to build both explicit agentic workflows using Spring AI as well as defining autonomous agents using Embabel.

Over the past few years, we've seen the buzz around Generative AI evolve from simple prompts, to document- and tool-augmented prompts, to more formalized collections of tools and prompts in Model Context Protocol (MCP). And for awhile now, agents are all the buzz. Unfortunately, this has presented a paradox wherein everyone knows what agents are and at the same time, nobody knows what agents are.

Regardless of what you think an agent is, it's clear that agents are the most useful when they are able to work within the ecosystems of existing enterprise systems. Since many enterprise systems are based in Java, it would make sense to develop agents in Java so that they can take advantage of prior work that has been developed in Java and the skillsets that were involved. In short, it's unnecessary to develop in Python if you don't already have Python in play in such a system.

Fortunately, frameworks such as Spring AI make easy work of integrating Generative AI in Java. And applying agentic workflow patterns in Java is just as easy. What's more, an agentic framework such as Embabel (which is built on Spring and Spring AI) make developing autonomous, self-planning agents in Java as straightforward as it is to develop web applications or APIs in Java.

By now, you've no doubt noticed that Generative AI is making waves across many industries. In between all of the hype and doubt, there are several use cases for Generative AI in many software projects. Whether it be as simple as building a live chat to help your users or using AI to analyze data and provide recommendations, Generative AI is becoming a key piece of software architecture.

So how can you implement Generative AI in your projects? Let me introduce you to Spring AI.

For over two decades, the Spring Framework and its immense portfolio of projects has been making complex problems easy for Java developers. And now with the new Spring AI project, adding Generative AI to your Spring Boot projects couldn't be easier! Spring AI brings an AI client and templated prompting that handles all of the ceremony necessary to communicate with common AI APIs (such as OpenAI and Azure OpenAI). And with Spring Boot autoconfiguration, you'll be able to get straight to the point of asking questions and getting answers your application needs.

In this handson workshop, you'll build a complete Spring AIenabled application applying such techniques as prompt templating, Retrieval Augmented Generation (RAG), conversational history, and tools invocation. You'll also learn prompt engineering techniques that can help your application get the best results with minimal “hallucinations” while minimizing cost.

Although Java originally promised to write once, run anywhere, it failed to fully deliver on that promise. As developers, we can develop, test, and build our applications into WAR or executable JAR files and then toss them over the wall to a Java application server and Java runtime that we have no control over, giving us zero confidence that the application will behave the same as when we tested it.

Containers fulfill the write-once, run anywhere promise that Java wasn't able to, by packaging the runtime and even the operating system along with our application, giving greater control and confidence that the application will function the same anywhere it is run. Additionally, containers afford several other benefits, including easy scaling, efficiency in terms of resource utilization, and security by isolating containers from their host system and from other containers.

While deploying Spring applications in containers has always been possible, Spring Boot 2.3 makes it easier to containerize our applications and run them in container architectures such as Kubernetes. Spring Boot 2.3's support for containerization includes two options: Creating containers based on buildpacks or using layers as a means of modularizing and reducing the size of our application deployments. Moreover, new components in the Spring ecosystem can make your Spring applications Kubernetes-savvy so that they can take advantage of what a containerized architecture has to offer.

In this hands-on workshop, learn how to build Spring applications that can be deployed as containers in a Kubernetes cluster. You'll not only build your Spring application as an image that can be deployed in Kubernetes, but you'll also learn how to take advantage of Spring's first-class support for container-based applications, including graceful shutdown, liveness and readiness probes, and ConfigMap-based property sources.

In this hands-on workshop, you'll learn to create voice-first applications for both Amazon's Alexa and Google's Assistant platforms. In addition, we'll also cover creating visual UIs to accompany the voice-first applications (for devices such as Echo Show).

No prior experience with voice applications is required and you do not even need to own a home assistant device to get started. Elementary experience with NodeJS is required. You'll also need developer accounts for both AWS and Google.

The way we communicate with our applications is an ever-evolving experience. Punch cards gave way to keyboards. Typing on keyboards was then supplemented by pointing and clicking with a mouse. And touch screens on our phones, tablets, and computers are now a common means of communicating with applications.

These all lack one thing, however: They aren’t natural.

As humans, we often communicate with each other through speech. If you were to walk up to another human and start tapping them, you’d likely be tapped (or punched) in response. But when we talk to our applications, we communicate on the machine’s terms, with keyboards, mice, and touch screens. Even though we may use these same devices to communicate with other humans, it’s really the machine we are communicating with—​and those machines relay what we type, click, and tap to another human using a similar device.

Voice user-interfaces (Voice UIs) enable us to communicate with our application in a human way. They give our applications the means to communicate to us on our terms, using voice. With a voice UI, we can converse with our applications in much the same way we might talk with our friends.

Voice UIs are truly the next logical step in the evolution of human-computer interaction. And this evolutionary step is long overdue. For as long as most of us can remember, science fiction has promised us the ability to talk to our computers. The robot from Lost in Space, the Enterprise computer on Star Trek, Iron Man’s Jarvis, and HAL 9000 (okay, maybe a bad example) are just a few well-recognized examples of science fiction promising a future where humans and computers would talk to each other.

Our computers are far more powerful today than the writers of science fiction would have imagined. And the tablet that Captain Picard used in his ready room on Star Trek: The Next Generation is now available with the iPad and other tablet devices. But only recently have voice assistants such as Alexa and Google Assistant given us the talking computer promised to us by science-fiction.

In this example-driven session, you'll learn how to build an MCP server in Java using Spring AI, integrate it with clients such as Claude Code and Cursor, and even create your own MCP clients.

On their own, Large Language Models (LLMs) are only able to generate responses based on their training. While their training may be vast, it will not include any actual data from your organization's databases and systems. What's more, an LLM may be able to answer questions, they are unable to actually interact with your enterprise and take action.

Enter Model Context Protocol (MCP). MCP defines a standard with which you can collection a set of related tools, prompts, and resources and make those available to an LLM to make use of. With MCP, your LLMs will be able to interact with databases, APIs, and other components in your enterprise to get things done.

Building and using MCP in Java has never been easier than it is now with Spring AI. Spring AI introduced support for MCP in its 1.0 release and improved upon it tremendously in Spring AI 1.1.

Most of the buzz around Generative AI has been how it is able to understand and respond to natural language prompts. But largely, those prompts have been typed in by a user and the responses have come back in textual form.

While humans often communicate with each other in a similar way via text messages and emails, natural interaction takes place across many modes of communication, including talking, hearing, seeing, and showing.

In this session, you'll see how to add sight and sound to your Spring AI applications. You'll learn how to build applications that can both talk and hear what your users say as “see” what your users show them (via images) and produce responses in graphic form.

The Spring Framework transformed enterprise Java development nearly two decades ago, making it easier to achieve common things such as transactions, security, loose-coupling, and much more Over the years, Spring has continued to rise to every challenge Java developers face, most recently addressing subjects such as reactive programming, cloud computing, and container deployment in Kubernetes. Meanwhile, Spring Boot makes easy work of Spring by employing (among other things) auto-configuration, runtime insight and management, and a practical convention for specifying application properties.

The releases of Spring Framework 6 and Spring Boot 3 bring exciting and useful new capabilities. With features like native compilation, improved observability and tracing, support for HTTP problem details, and declarative HTTP clients, as well as baselining on Java 17 and Jakarta EE 9, Spring is ready for a new generation of application development.

In this workshop, you'll start with a very simple Spring Boot application and learn to grow it into a fully functional application including a web front-end and data persistence. And you'll get hands-on experience with some of the most exciting new features in Spring 6 and Spring Boot 3.

Modern application observability involves tracking key metrics and tracing the flow of an application, even across service boundaries. Spring Boot 3 introduced some powerful metrics and tracing capabilities based on Micrometer to open a window into your application's inner-workings.

Among the things you might want to keep an eye on in your Generative AI applications are how many interactions and how much time is spent with vector stores and AI provider APIs and, of course, how many tokens are being spent by your application. And being able to trace the flow of prompts, data, and responses through your application can help identify problems and bottlenecks.

Great news! Spring AI comes equipped to record metrics and tracing information through Micrometer. In this session, you'll learn how to put Spring AI observability to work for you. You'll learn about the metrics it exposes as well as the keys you can use to build dashboards and tracing to build a window into your Generative AI applications.

In this session, we'll cover several useful prompt engineering techniques as well as some emerging patterns that are categorized within the “Agentic AI” space and see how to go beyond simple Q&A to turn your LLM of choice into a powerful ally in achieving your goals.

At it's core, Generative AI is about submitting a prompt to an LLM-backed API and getting some response back. But within that interaction there is a lot of nuance, particularly with regard to the prompt itself.

It's important to know how to write effective prompts, choosing the right wording and being clear about your expectations, to get the best responses from an LLM. This is often called “prompt engineering” and includes several patterns and techniques that have emerged in the Gen AI space.

By now, you've no doubt noticed that Generative AI is making waves across many industries. In between all of the hype and doubt, there are several use cases for Generative AI in many software projects. Whether it be as simple as building a live chat to help your users or using AI to analyze data and provide recommendations, Generative AI is becoming a key piece of software architecture.

So how can you implement Generative AI in your projects? Let me introduce you to Spring AI.

For over two decades, the Spring Framework and its immense portfolio of projects has been making complex problems easy for Java developers. And now with the new Spring AI project, adding Generative AI to your Spring Boot projects couldn't be easier! Spring AI brings an AI client and templated prompting that handles all of the ceremony necessary to communicate with common AI APIs (such as OpenAI and Azure OpenAI). And with Spring Boot auto-configuration, you'll be able to get straight to the point of asking questions and getting answers your application needs.

In this session, we'll consider a handful of use cases for Generative AI and see how to implement them with Spring AI. We'll start simple, then build up to some more advanced uses of Spring AI that employ your application's own data when generating answers.