Breaktime Tech Talks

Ep51: Exploring AI Agents + Agentic GraphRAG in Java

In this episode, I delve into the world of agents, discussing my experience with Spring AI tool calling. I share my approach to vector search and graph retrieval tools, address JSON deserialization, and avoid manual boilerplate - the code of which is all available in a Github repository branch. Plus, 1.0 updates to the main branch of the repository using traditional/manual GraphRAG. I wrap up with a recent content piece by Christoffer Bergman from Neo4j, which explores agentic AI frameworks with Java and Neo4j and the differences between traditional and agentic GraphRAG approaches.
P.S. Don't forget to leave your feedback/suggestions for BTT in this form!
 
00:00 Introduction to Breaktime Tech Talks
00:54 Exploring Spring AI Tool Calling
01:20 Understanding Agentic Frameworks
02:13 Hands-On with Vector Search and Graph Retrieval
02:36 Challenges and Solutions in Tool Functionality
04:02 Updates and Future Plans
05:01 Agentic AI with Java and Neo4j
08:06 Conclusion and Recap

Ep50: GraphRAG with Advisors + Spring AI Concepts

It's the 50th episode of Breaktime Tech Talks! And to celebrate, I launched a podcast feedback form for you, my listeners.
In this 50th episode, follow my latest explorations into Spring AI and GraphRAG. I delve into my attempts to streamline the manual GraphRAG process using Spring AI advisors and tools, sharing the challenges I'm facing, specifically with context parsing from one advisor to the next. I also update the Spring AI starter kit to the 1.0 GA release and recap my Neo4j developer certification livestream. To wrap up, I highlight the Spring AI documentation's AI Concepts page that beautifully blends a blog-post style with key project information.

Ep49: Moving toward AI Tools/Agents + Local RAG app with Quarkus

This week, I simplified my Langchain4j project with improved prompt variable injection. Then hear my perspective on the role of tools vs. agents in AI workflows—looking at how structured processes differ from autonomous systems, especially in the context of Java frameworks and GraphRAG.
Get an inside scoop on how I use different AI coding tools: IntelliJ IDEA for in-flow coding, VS Code with agent mode for problem-solving, and ChatGPT for summarizing and refining content.
Lastly, hear highlights from an article on building a local RAG app with Quarkus—clear diagrams and step-by-step breakdown of ingestion vs. retrieval workflows.

Ep48: Java GraphRAG and Langchain4j 1.0 + Thoughts on conversational interfaces

This week, there were quite a few things I learned:
Common steps for implementing GraphRAG in Java using Spring AI and Langchain4j, highlighting key differences in setup and customization.
Study prep updates and help on the Neo4j Developer Certification for June!
Celebrate Langchain4j’s 1.0 release.
Two thought-provoking articles—one on enhancing RAG with graphs, and another analyzing the effectiveness of voice-based interfaces.
For a high-level review of steps for GraphRAG in Java, upcoming step-by-step help for prepping to take the Neo4j certification, Langchain4j GA news, and keeping up on tech content, this episode has you covered!

Ep47: Langchain4j GraphRAG Friction + MCP Authorization Headaches

 
In this episode, I share some hands-on insights from building apps with Langchain4j using Quarkus and Neo4j, and compare it with Spring AI—especially around how each framework handles vector search and GraphRAG workflows. Spoiler: customization in Langchain4j feels a bit clunky.
I also dig into one article's critical take on the MCP authorization spec and why its current approach to security is misaligned with how enterprises actually structure identity and access. The article I discuss breaks down both the architectural intentions and the practical enterprise concerns—token handling, overhead, and developer friction.
If you’re working at the intersection of GenAI infrastructure and enterprise systems, this one’s for you.
 

Ep46: Quarkus Neo4j Application + Development Lessons Learned

In this episode, we dive into the Quarkus framework with a code repository and an article about development lessons learned. Topics covered include:
🔗 Building a starter application with Quarkus Neo4j and the Object Graph Mapper (OGM).
📝 Exploring similarities and differences between Quarkus and Spring frameworks.
📑 Resources for building with Quarkus and Neo4j - blog post and documentation.
📚 Key takeaways from an article on developer philosophy, touching on code rewrites, estimation challenges, and the importance of automation and edge cases.
Whether just curious or writing code, we all learn and face similar development challenges!

Ep45: Exploring Java Frameworks + Launch of Spring AI 1.0

In this episode, I have some exciting technical updates, along with insights from my recent work and learning. Topics covered include:
📝 Neo4j Java Driver & Object Mapping – My latest blog post and upcoming updates to the GraphAcademy Java courses.
🧪 Framework-less Java Apps – Experiments in building Java applications without a framework and comparing with tools like Spring and others.
🔧 Code Refactoring Strategy – Lessons learned on managing updates in stages for cleaner version control and project maintenance.
🤖 Spring AI 1.0 Release – Highlights from the official launch, including an AWS blog post on architecture insights, real-world examples, and key resources for getting started with AI in Java.
Whether you're deep into Java development or just exploring the intersection of frameworks and AI, there's something here for you!

Ep44: Updates in Java tools + MCP and Security

In this episode, we dive into three key updates from the world of Java development and emerging tech standards:
First, walk through a new feature in the Neo4j Java driver (v5.28.5) that enables lightweight object mapping. I’ve set up a sample code repository showcasing how to return Cypher query results directly into your Java domain objects—no full-blown OGM needed. It’s a big improvement, but with a few gotchas you’ll want to understand.
Next, we take a look at Jackson Jr, a lightweight version of the popular Jackson library. If you're working in resource-constrained environments or want faster startup times, this stripped-down data processor might be just what your project needs.
Finally, we revisit Model Context Protocol (MCP) security, following up on concerns raised in Episode 42. I share two recent articles that highlight current security limitations in MCP and practical tips for developers looking to build safely with it today, even before full support matures.
Whether you're optimizing your Java stack or exploring AI protocols, there’s something in this episode for you.

Ep43: MCP Java SDK + Naive RAG vs GraphRAG

In this episode, we dive into the latest upgrades in Neo4j tooling, along with recent bug fixes and enhancements in the LLM Knowledge Graph Builder. We also explore a new preview feature for Java object mapping in the Neo4j Java driver and check out the MCP Java SDK. Next, we highlight the new "Using Neo4j with Java" course on GraphAcademy and unpack a compelling Weaviate article on RAG vs. GraphRAG, featuring Microsoft’s GraphRAG methodology.Whether you're a Java dev, graph enthusiast, or AI-curious, there's something in here for you!

Ep42: RAG and Java + AI-generated content and MCP

Star Wars Day is nearly here, and this episode is stacked with tech goodness to celebrate! I’m diving into highlights from the Neo4j ecosystem, starting with an early look at the Using Neo4j with Java course—perfect for getting started with the Java driver in a framework-less setup.
Also in this episode:
⚙️ Behind-the-scenes of APOC + Pinecone integration
✨ Part 2 of my Intro to Retrieval Augmented Generation series
🎥 My recent guest spot on Neo4j Live, discussing the Developer’s Guide to Building a Knowledge Graph
🤖 A fascinating series on an AI content experiment from Mark Heckler
📚 Michael Hunger’s must-read blog on the Model Context Protocol (MCP)
May the Fourth be with you!