Breaktime Tech Talks

Ep70: Devnexus Conference Recap + No-LLM Agentic Workflow

Hear my recent experience at the Devnexus conference in Atlanta, where I delivered two sessions and connected with so many amazing people!
Devnexus session 1: "Agents, Tools, and MCP, Oh My! Next Level AI Concepts for Developers" — a redesigned solo talk breaking down AI building blocks (agents, tool calls, context management, memory, and MCP) so developers can mix and match components for their own stack.
Key takeaway: AI systems are much more than just the LLM — developers play a critical role in designing the surrounding architecture.
Devnexus session 2: "Supercharging Applications with Java, Graphs, and a Touch of AI" (code repo 1, code repo 2) — a joint session with Erin Schnabel building an LLM-powered role-playing game using Langchain4j, Quarkus, and Neo4j.
Multiple approaches: plain LLM chat, prompt engineering, and RAG with Neo4j as the vector/graph store, chunking documents while preserving structure via graph relationships.
Our "Three Cs" challenge: Continuity (maintaining storyline), Context (growing context window), and Creativity (keeping the LLM on track without going off the rails).
Splitting responsibilities between the LLM and a deterministic engine significantly improved results — a pattern developers should consider for complex AI apps.
App redesign with an agentic architecture: dice roll, narration, suggestion, checkpoint, and recap agents — with the last three running concurrently for better performance.
Markdown file (in one app) for agentic memory, enabling easy edits, rollbacks, and incremental indexing during live gameplay.
Content spotlight: "No Keys, No LLM — Building a Wikidata Definition API with Embabel" — an article showcasing an agentic Java application that uses zero LLM. Embabel (a Java agentic framework) handles planning and execution with structured inputs/outputs, no external or local model required.
Could the no-LLM agent pattern see broader adoption, or is it a niche experiment?
New episodes will now use platform-agnostic Podfollow links.
New blog post on jmhreif.com about Cypher AI procedures.

Ep69: Growth through Challenge + Rise of Agentic AI

Jennifer shares highlights from a week full of spontaneity and preparation.
Highlights:
The Bootiful Podcast (Coffee + Software) with Josh Long
Impromptu livestream with Josh on building a Spring + Neo4j application with just 10 minutes prep
Participated in an X Space panel on the rise of agentic AI with experts from AWS, Nvidia, and Brokk
Final preparations for two Devnexus sessions and other activities
The reality of setting boundaries as a developer advocate
Content highlights: Brock AI-native coding platform and DICE knowledge graph library for Java
Key Themes: Growth through unexpected challenges, maintaining quality over quantity, and leaning into spontaneous opportunities
Links:
The Bootiful Podcast episode
Coffee + Software livestream with Josh recording
X Space recording on The Rise of Agentic AI
Brokk YouTube video
Embabel DICE GitHub project
Next Week: Devnexus in Atlanta! Visit the Neo4j booth.

Ep68: Career Highlights + OGM Alternatives

In this episode, hear my reflections on eight years as a Developer Advocate at Neo4j - learning in public, teaching before feeling “ready”, and navigating the constant balance between deep technical work and community engagement. Get updates on what I'm currently focused on: upcoming events, writing a more complex chapter of the Java book, sharpening Cypher skills, and exploring an article that challenges the default use of Object Graph Mappers (OGMs) in graph applications.
Highlights
8 Years in Advocacy
Learning fast by presenting and teaching
Balancing deep work, travel, and ad hoc collaboration
Adapting to the accelerating pace of tech and AI
Current Projects
Preparing for Devnexus and upcoming virtual events
Contributing to Road to NODES AI workshops
Writing a more advanced Java book chapter (avoiding the editing loop)
Intentionally improving Cypher skills through deeper practice
Rethinking OGMs
Exploring the article “The Very Slowly Ticking Time Bomb, Your Graph Persistent Stack”
Questioning whether OGMs add unnecessary translation layers in graph apps
Considering alternatives
Expanding the toolbox — no one-size-fits-all solution
Events
Devnexus (Atlanta, GA)
San Francisco Bay ACM (Virtual Event)
Road to NODES AI Workshops (Free, virtual)

Ep67: Conference Recap + Cypher Query Patterns

Fresh back from Jfokus in Stockholm! This week, I'm sharing highlights from the conference and diving into advanced Cypher techniques that make graph databases shine.
Highlights:
Jfokus 2025 recap: Viking themes, inspiring community, and lots of content
Book writing updates and upcoming March events
Combination of outlining and writing in my process
Joint session prep is stretching my application development skills
Content: 10 things that are easier in Cypher than in SQL
Why aggregation without GROUP BY changed everything for me
Pattern comprehension, map projections, and where to level up
Key takeaway: Graph databases excel at path patterns and relationships.
Resources mentioned:
"10 Things You Can Do With Cypher That Are Hard With SQL" by Michael Hunger

Ep66: Neo4j Data Loading at Scale + Vector Search Filtering

Hear about my hard-won lessons from loading a large-scale book dataset into Neo4j with Ollama embeddings, plus a preview of exciting new vector search features.
Highlights:
Data Loading Battle Stories
Fixing Ollama OpenAI endpoint issues (drop the /v1 suffix!)
Choosing embedding models with adequate context windows (nomic-embed-text: 8,192 tokens)
Optimizing batch sizes and memory configuration
Using EXPLAIN to identify and eliminate Cypher eager operations
Error handling with ON ERROR CONTINUE for partial loads (achieved 83% coverage)
Neo4j 2026.01 Preview: Vector Search with Filters Three new approaches that combine vector search with Cypher filtering in a single query:
Vector Search + Keyword Filters
Cypher After Vector (post-filtering GraphRAG)
Cypher Before Vector (pre-filtering on subgraphs)
No more two-step application logic for Graph RAG!
Context Graph demo app:
Level of detail and perspectives you can view of the context graph and interactions with agents
Event
I will be at Jfokus in Stockholm next week!

Ep65: RAG Filtering + Context Graphs with Neo4j

This week has been a whirlwind. From starting a new RAG project to getting involved in other community events, there is so much to learn and do. This week had the following highlights:
🎤 Glasgow Meetup Adventures Navigating venue challenges, DJ booth speaking setups, and live coding without a mic stand—lessons in developer advocacy resilience.
🔍 RAG Experimentation Working with Quarkus to ingest unstructured data into Neo4j. Exploring filtering strategies and data model alignment for better retrieval.
💡 Live Interaction Tracer Combining naive RAG with a graph-based interaction tracer—early progress on a promising approach.
🧠 Context Graphs Deep Dive Why context graphs matter for AI: documenting the "how" and "why" behind data decisions, not just snapshots in time. Perfect for providing business logic and tacit knowledge to AI systems.
Resources
Hands-on with Context Graphs and Neo4j by William Lyon
William Lyon's podcast episode (previous month)
Context Graphs demo application
Lots of 2026 projects kicking off—stay tuned for updates on RAG experiments, context graph implementations, and upcoming events!

Ep64: Neo4j Vector Migration + Learning in the AI Era

Welcome back to Breaktime Tech Talks for 2026! In this episode, dive into the technical challenges I faced with GenAI procedure migrations, and the workarounds needed for Ollama embeddings. Then, explore the evolving landscape in the age of AI, including new terms like AEO (Answer Engine Optimization) that are changing how we think about discoverability.
Highlights:
Neo4j Vector Migration: Understanding the shift from list-based storage to the new vector data type in Neo4j
GenAI Procedures Evolution: Navigating multiple versions of GenAI procedures and their current limitations (v2025.11.2)
Ollama Workarounds: Using APOC library procedures when bleeding-edge syntax doesn't support your use case
Large-Scale Data Loading: Loading 2+ million books from the Goodreads dataset
Learning vs. Creating: Finding balance between content consumption and production in a rapidly evolving tech landscape
Lenny's Podcast: "The Leadership Skill AI Can't Replace" with Molly Graham
Lenny's Podcast: "The Ultimate Guide to AEO: How to Get ChatGPT to Recommend Your Product" with Ethan Smith

Ep63: MCP Integration Success + Advancing Semantic Search

Welcome to Breaktime Tech Talks! In this episode, get my latest breakthroughs and insights with Quarkus and Langchain4j, a new vector data type in Neo4j, and details on other projects and events I'm working on.
Highlights:
MCP Integration Success. Integrating MCP with Quarkus and Langchain4j (Github project). I overcame dependency issues and implemented custom wrapper methods for RAG tools.
Advancing Semantic Search. Dive into the new native vector data type in Neo4j, as introduced in a recent developer blog post. One benefit of this new data type for vector search includes data integrity, plus it includes nice migration from the old list format.
AI-First Java Book. Hear about my upcoming book, "AI First Java," co-written to help newcomers learn Java with an AI-first approach. I share my perspective on teaching foundational programming concepts in the age of AI-powered tools.
Upcoming Events. Preview my speaking engagements for early 2026, including the Glasgow meetup, Jfokus, and Devnexus.
Podcast Updates: Hear my thoughts on future guests and feel free to add your thoughts in the BTT feedback form.

Ep62: Quarkus Langchain4j Updates + Production-Ready Agents on JVM

In this episode, hear my latest adventures in the world of Java development, focusing on integrating Langchain4j with Quarkus, tackling dependency management, and exploring the evolving landscape of generative AI in production systems. Plus, I highlight upcoming community events and must-watch videos for developers.
Highlights:
Langchain4j + Quarkus: Read-Only Database Success & Dependency Challenges - progress on a read-only Neo4j database with Langchain4j and Quarkus, caveats around configuration, and the "dependency hell" encountered when adding the MCP server for text-to-Cypher capabilities.Project link: Langchain4j Quarkus Graph RAG app
Upcoming Events
O'Reilly Graph RAG Fundamentals workshop (virtual, Dec 18)
Global Big Data Conference (virtual, Dec 15th)
Recommended Videos
"Gen AI Grows Up: Building Production Ready Agents on the JVM" by Rod Johnson (GOTO Chicago 2025)
Focus: Integrating generative AI into existing Java business solutions, and the new open source project Embabel.
"Spring in Autumn with Neo4j" by Gerrit Meier (NODES 2025)
Focus: Spring projects and frameworks for integrating with Neo4j, plus tips for other tech stacks.

Ep61: William Lyon on Knowledge Graphs + Agentic Memory

For the first time ever, Jennifer welcomes a guest to the show! William Lyon gives us a deep dive into the evolving world of AI agents, knowledge graphs, and the concept of memory in artificial intelligence.
Episode highlights:
William’s career journey: from Neo4j to startups and back again
The role of knowledge graphs in agentic memory and reasoning
Types of memory in AI agents: episodic, procedural, and more
How knowledge graphs can model both user-facing and operational memory
The importance of domain-specific data modeling for AI memory systems
William’s AI Memory Landscape project: cataloging tools, frameworks, and services in the AI agent memory space
Contributions to the project are open, so submit a PR or request!
Advice for developers architecting AI agents with memory
Other referenced links:
GraphStuff.FM podcast
AI Memory Landscape project: https://ai-memory-landscape.netlify.app/
Connect with William Lyon:
Website: https://lyonwj.com/