Avsnitt
-
In this episode, I sit down with Roie Schwaber-Cohen, a software engineer and developer advocate at Pinecone, to talk about smarter ways to build with AI — without burning through tokens or your patience!
What we cover:
Why agentic AI systems burn so many tokens (and ways to combat it)How Pinecone's Nexus pre-explores retrieval paths so agents don't have to discover them at runtime, cutting latency and token usageThe problem with naive RAG ("Franken answers") and why domain-level separation of your documents mattersHow Pinecone Marketplace lets non-developers connect structured and unstructured data sources to build production-ready AI appsWhy semantic similarity isn't the same as correctness, and how document introspection helps agents ask better questionsLinks & Resources:
PineconePinecone Marketplace (recently announced)Pinecone NexusRoie on LinkedIn -
I'm back after a couple of weeks of hiatus with a packed update. From a major book deadline to enterprise graph hackathons, summer is anything but slow.
AI-First Java Book. First six chapters officially submitted. They cover concept progression, real-world problem solving, and a developer's career journeyCustomer Graph Hackathons. First hands-on event with Neo4j at an enterprise customer site, and another one coming next weekGraphRAG Fundamentals Training. Rescheduled on O'Reilly Learning Platform; available to sign upNeo4j CLI. New tool for interacting with Neo4j from the command line, with agent skill support for coding tools like ClaudeAgent Instruction Protocol. Open-source repo that turns skill specs into YAML-based execution graphs modeled as process flowsBuilding Agents in Java with Embabel. Dan Vega's walkthrough of this Java AI framework. It covers actions, plans, goals, and reusable components for enterprise agentsLots of exciting things in motion — grab the links in the show notes and happy coding!
-
Saknas det avsnitt?
-
A packed week of travel, debugging, writing, and reading. I share what I learned and ran into this week as a developer.
Highlights:
🗣️ Spoke at the JavaMUG (Java Metroplex User Group) meetup in Dallas — highly recommended for Dallas-area developers!🐛 Discovered a bug in Spring AI's Neo4j chat memory integration with the latest Spring Boot — workaround is to use in-memory storage for now.📖 Working on a Java book chapter covering OOP concepts (abstraction, encapsulation, polymorphism) with a focus on practical, use-case-driven learningEvent updates:📅 Session from the AI Agents conference is now on YouTubeGraphRAG Fundamentals O'Reilly course rescheduled to June in APAC timezoneNODES CFP open until June 15th📝 Two recommended reads:"MCP, Skills, and Agents" by David Cramer"LLMs and Your Career" by Phil Eaton -
A quieter week, but still full of forward motion — from clearing the Neo4j developer blog backlog and making progress on the upcoming Java book, to lining up upcoming speaking events. Plus, two developer-focused content pieces I hope you enjoy as much as I did.
This Week's Updates:
Rescheduling the GraphRAG Fundamentals training (likely June, APAC-friendly time zones)Cleared a backlog of community submissions for the Neo4j Developer Blog — open to anyone with a Medium accountCypher/SQL injection understanding from Neo4j Definitive Guide bookWriting progress on a new AI-first Java learning book, drawing on literary aspirations and music pedagogy principles for a fresh teaching approachNew speaking opportunities coming in May and June — stay tunedContent Pieces:
"Batching Like a Pro" by Gemma Lamont — A detailed feature comparison of apoc.periodic.iterate vs. native Cypher CALL IN TRANSACTIONS, covering memory tracking, error handling, query planning, concurrency, entity rebinding, and retry strategies. The gap has largely closed — native Cypher is nearly on par.NODES AI videos now on YouTube — All session recordings from Nodes AI are publicly available. Link in the show notes. -
This week, I prepped for upcoming events, tweaked and strategized some existing processes, and found more data on how defining a schema can produce better knowledge graph construction.
Highlights:Prepped for two upcoming events: a Graph RAG Fundamentals training on O'Reilly Learning Platform and a session at a virtual AI Agents conference.Updating repositories for the workshop surfaced a chain-reaction lesson: upgrading frameworks leads to data changes, which require config updates, which require prompt rewrites.Key takeaway — don't pin your apps to latest for AI models, just as you wouldn't for Docker image tags. Tie to a specific version so updates don't cascade unexpectedly.Also revisited my tech blogging workflow and built a template script to eliminate boilerplate setup, shaving time off the writing process without sacrificing the actual content creation.New blog post on agents, tools, and MCP published in the process!On the Neo4j side, I touched on the Neo4j Educator Program and how learning patterns among new developers are shifting — happy to accept feedback from educators teaching graphs.This week's article is Hands-on KG Relation Resolution by Mike Dillinger. It examines knowledge graph construction and why defining a narrowed schema produces cleaner, more understandable graphs. Without boundaries, LLMs and NLP processes generate overly granular, spaghetti-like structures. -
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.
💡 HighlightsCareer 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 opportunitiesProgress on the AI Java book with a productive working sessionShared 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 timeUpcoming: 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 orchestrationKey lesson: don't let the LLM decide your entire data model. Providing node types, relationship types, and patterns as boundaries dramatically improves resultsExpect iteration — retrieval testing will send you back to refine your KG constructionGithub code: Neo4j GraphRAG Python packageLangchain4j for Production (Lize Raes, Devoxx Belgium)
Wrap RAG as an agent tool for multi-call retrieval instead of single-shot pipelinesFilter available tools programmatically by domain to keep agents focusedWire sub-agents as @Tool for clean multi-agent orchestrationUse immediate responses to skip the LLM summarization hop — saves tokens and latency13-step walkthrough for production-grade agentic systemsYouTube 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 LongImpromptu livestream with Josh on building a Spring + Neo4j application with just 10 minutes prepParticipated in an X Space panel on the rise of agentic AI with experts from AWS, Nvidia, and BrokkFinal preparations for two Devnexus sessions and other activitiesThe reality of setting boundaries as a developer advocateContent highlights: Brock AI-native coding platform and DICE knowledge graph library for JavaKey Themes: Growth through unexpected challenges, maintaining quality over quantity, and leaning into spontaneous opportunities
Links:
The Bootiful Podcast episodeCoffee + Software livestream with Josh recordingX Space recording on The Rise of Agentic AIBrokk YouTube videoEmbabel DICE GitHub projectNext 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.
Highlights8 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
EventsDevnexus (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 contentBook writing updates and upcoming March eventsCombination of outlining and writing in my processJoint session prep is stretching my application development skillsContent: 10 things that are easier in Cypher than in SQLWhy aggregation without GROUP BY changed everything for mePattern comprehension, map projections, and where to level upKey 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 configurationUsing EXPLAIN to identify and eliminate Cypher eager operationsError 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 FiltersCypher 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 agentsEventI 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.
ResourcesHands-on with Context Graphs and Neo4j by William LyonWilliam Lyon's podcast episode (previous month)Context Graphs demo applicationLots of 2026 projects kicking off—stay tuned for updates on RAG experiments, context graph implementations, and upcoming events!
-
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 Neo4jGenAI 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 caseLarge-Scale Data Loading: Loading 2+ million books from the Goodreads datasetLearning vs. Creating: Finding balance between content consumption and production in a rapidly evolving tech landscapeLenny's Podcast: "The Leadership Skill AI Can't Replace" with Molly GrahamLenny's Podcast: "The Ultimate Guide to AEO: How to Get ChatGPT to Recommend Your Product" with Ethan Smith -
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.
-
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 appUpcoming 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. -
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 againThe role of knowledge graphs in agentic memory and reasoningTypes of memory in AI agents: episodic, procedural, and moreHow knowledge graphs can model both user-facing and operational memoryThe importance of domain-specific data modeling for AI memory systemsWilliam’s AI Memory Landscape project: cataloging tools, frameworks, and services in the AI agent memory spaceContributions to the project are open, so submit a PR or request!Advice for developers architecting AI agents with memoryOther referenced links:
GraphStuff.FM podcastAI Memory Landscape project: https://ai-memory-landscape.netlify.app/Connect with William Lyon:
Website: https://lyonwj.com/ -
Welcome to Breaktime Tech Talks! In this episode, dive into the latest updates and challenges in the world of developer tools, AI, and graph databases.
Episode Highlights:
Overcoming technical hurdles with Langchain4j and Neo4j, including the new support for read-only Neo4j databases in vector indexing (Github feature pull request).Navigating versioning headaches and framework differences between Spring AI and Quarkus for AI-powered applications.Lessons learned from hands-on work with Neo4j GraphAcademy courses (GraphAcademy GenAI Fundamentals), including AI and knowledge graphs.Key takeaways from the Andrej Karpathy interview (YouTube interview link), including:The strengths and limitations of large language models (LLMs) for developers.The concept of the “decade of agents” and how agents are shaping the future tech stack.The importance of teaching as a way to deepen technical understanding.Upcoming events and workshops:Neo4j Fundamentals & GenAI hands-on workshop (learn more about workshop) – December 11th, virtual and free.GraphRAG Fundamentals course on O’Reilly (course details) – December 18th.NODES 2025 conference session recordings now available (full YouTube playlist). - Visa fler
