Daniel Oh
Supercharge Agentic AI Apps: A DevEx-Driven Approach to Cloud-Native Scaffolding
#1about 5 minutes
Understanding the evolution and autonomy of agentic AI
Agentic AI evolves from traditional AI by autonomously deciding which external tools and resources to use, unlike systems with predefined workflows.
#2about 3 minutes
Exploring frameworks for building agentic AI applications in Java
While Python has many agentic AI frameworks, Java developers can combine tools like Quarkus, Spring AI, and LangChain4j to build similar applications.
#3about 5 minutes
Scaffolding a new agentic AI project with Quarkus
Use the Quarkus application generator to quickly create a new project with dependencies for OpenAI and MCP, then run it in development mode for live coding.
#4about 3 minutes
Defining the agent's behavior with a Java interface
A simple Java interface with LangChain4j annotations and a carefully crafted system prompt can instruct the AI model to autonomously utilize any available tools.
#5about 5 minutes
Configuring and auto-starting MCP servers in Quarkus
Configure external tools like search, maps, and messaging by defining MCP servers in the application properties file, which Quarkus automatically downloads and runs.
#6about 4 minutes
Demonstrating a multi-tool agent finding and sharing information
A live demonstration shows the agent autonomously using search, maps, and Slack tools to fulfill a complex user request for finding and sharing restaurant recommendations.
#7about 3 minutes
Using software templates to share agentic AI applications
Simplify multi-agent development and collaboration by using an Internal Developer Platform (IDP) like Backstage, with Quarkus automatically generating software templates from your project.
#8about 2 minutes
The future roadmap for MCP and key takeaways
The MCP roadmap includes a server registry and multi-modal support, and the key takeaway is that Quarkus simplifies complex agentic AI development for Java developers.
Related jobs
Jobs that call for the skills explored in this talk.
Matching moments
14:46 MIN
Demoing an AI assistant for infrastructure as code
Forget Developer Platforms, Think Developer Productivity!
15:53 MIN
The shift from developer experience to AI experience
Postgres in the Age of AI (and Devin)
33:43 MIN
Deploying reactive apps and key takeaways
Development of reactive applications with Quarkus
28:16 MIN
The conceptual shift in modern AI development
On a Secret Mission: Developing AI Agents
24:34 MIN
Demo of an AI assistant using LangChain4j and Quarkus
Create AI-Infused Java Apps with LangChain4j
19:56 MIN
Adopting a modern tech stack for faster development
How to Destroy a Monolith?
00:03 MIN
Integrating generative AI into Java applications with LangChain4j
Infusing Generative AI in your Java Apps with LangChain4j
26:03 MIN
Demo of scaffolding an AI app with Developer Hub
Developer Experience, Platform Engineering and AI powered Apps
Featured Partners
Related Videos
29:18Create AI-Infused Java Apps with LangChain4j
Daniel Oh & Kevin Dubois
30:01Agentic AI Systems for Critical Workloads
Mario Fusco
39:11Agents for the Sake of Happiness
Thomas Dohmke
32:02Infusing Generative AI in your Java Apps with LangChain4j
Kevin Dubois
28:21Developer Joy with Quarkus
Daniel Oh
41:17Application Modernization Leveraging Gen-AI for Automated Code Transformation
Syed M Shaaf
27:43Reimagining the Developer Experience: The AI Advantage
Anu Bharadwaj & Tobias Schlottke
29:03On a Secret Mission: Developing AI Agents
Jörg Neumann
From learning to earning
Jobs that call for the skills explored in this talk.
