Breaktime Tech Talks

In this episode, I reflect on career growth in tech after speaking with a group of students, along with a few technical topics I explored this week — from Cypher optimization to scaling graph databases.
💡 Highlights
Career growth isn’t linear — most skills come from experimenting, saying yes to opportunities, and building over time rather than formal training
Project ideas come from doing — exploring tools, creating content, and solving real problems often reveal what to learn next
Cypher optimization (GraphAcademy) — hands-on practice with EXPLAIN, PROFILE, and query tuning reinforces key performance concepts
Neo4j Infinigraph — a new approach to scaling graphs by separating graph structure from large property data, improving performance and scalability (plus, NODES AI website and NODES AI YouTube playlist)
A reminder that progress comes from building, exploring, and iterating — not waiting for the perfect plan.

Back from a short holiday, I caught up on a few things this week — including the inevitable yak shaving.
Highlights:
📖 Book Progress: wrapped up another chapter draft. I've been finding that blocking larger chunks of dedicated time makes a real difference for focus and momentum, although getting started is still the hardest part.
🎓 Neo4j Educator Program: spent time refreshing slide decks, resource links, emails, and tutorials for the program. Still more to do, but happy with the progress. (Also worth knowing: the Neo4j Startup Program now offers Aura cloud database credits depending on your stage.)
🐃 Yak Shave of the Week: had to clear disk space on my laptop just to run required software updates — for the second time recently. Frustrating but necessary.
Content:
📚 Learning: Neo4j: The Definitive Guide – Ch. 5 (Query Analysis & Tuning) A fantastic chapter covering how the Cypher Query Planner works (Pipeline, Slotted, and Parallel), plus deep dives into EXPLAIN and PROFILE for query optimization. Exactly the kind of under-the-hood content I've been looking for.
💬 Reading: "Does Language Still Matter in the Age of AI?" — David Parry A great read on why structured, verbose languages actually perform better in AI code generation — and are easier to review. Language expertise is still very much worth developing.

My recap of virtual presentations, live streams, and workshop support — sharing wins, lessons from a humbling live coding session, and a fascinating article on solving long-running LLM memory problems.
Highlights:
Delivered a virtual meetup for the San Francisco ACM on building knowledge graphs with the Neo4j GraphRAG Python package (code repository)
Helped as a TA during a Road to Nodes AI workshop covering MCP server integrations with Neo4j.
Attempted a live stream refactoring Postgres to Neo4j using OGM — ran into challenges that revealed documentation gaps and learning opportunities
Progress on the AI Java book with a productive working session
Shared a blog post by James Dunham: "Long Running LLM Conversations Need Working Memory, Not Just More Context" — which mirrors issues encountered in a prior RPG project where LLMs lost story continuity over time
Upcoming: Road to Nodes AI workshop on long-term memory & agentic workflows (free, virtual)
Upcoming: NODES AI virtual conference — April 15th (free)

This week, I share hard-won lessons from building a GraphRAG application with Neo4j in Python, plus standout tips from Lize Raes's Devoxx Belgium talk on taking Langchain4j apps to production.
GraphRAG with Neo4j
Built a Python GraphRAG app using the Neo4j GraphRAG package — knowledge graph construction, retrievers (vector, graph, text-to-cypher), and agentic orchestration
Key lesson: don't let the LLM decide your entire data model. Providing node types, relationship types, and patterns as boundaries dramatically improves results
Expect iteration — retrieval testing will send you back to refine your KG construction
Github code: Neo4j GraphRAG Python package
Langchain4j for Production (Lize Raes, Devoxx Belgium)
Wrap RAG as an agent tool for multi-call retrieval instead of single-shot pipelines
Filter available tools programmatically by domain to keep agents focused
Wire sub-agents as @Tool for clean multi-agent orchestration
Use immediate responses to skip the LLM summarization hop — saves tokens and latency
13-step walkthrough for production-grade agentic systems
YouTube link: Level Up Your Langchain4j Apps for Production (Lize Raes, Devoxx Belgium 2025)

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.

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.

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)

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

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!

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!