Breaktime Tech Talks

In this episode, Jennifer recaps her Northeast US Java User Group tour and dives into the week's biggest tech release of Jev (a new System 1 model) along with Neo4j NODES 2026, upcoming projects, and two must-read blog posts.
Java User Group tour: shout-out to Northeast US JUG tour groups! TriJUG (Raleigh), Charlotte JUG, and a combined Richmond JUG / GraphRVA provided experiences that smashed it out of the park.
NODES 2026 agenda now live: Neo4j's annual online developer conference returns November 12th, featuring all in-depth technical sessions (no lightning talks this year). Pre-event "Road to NODES" workshops begin around October 1st (seven sessions available).
Java book milestone: All chapters submitted; editing and publishing prep remain.
Jev — a new System 1 Model: Released early this week. Rather than outputting text, Jev focuses on decision probabilities and traditional ML calculations. Potential use cases include database query planning, deterministic agent tool selection, and much more!
Jev operations use three modes — choice (pick best from a list), noul (score 0–1 for truthfulness), and score (numeric scoring).
Spring AI support: Spring AI already has integration for Jev; blog post linked in notes.
Upcoming explorations: Jev, RAG pipeline benchmarking, multi-agent applications, MCP security & access restrictions, and guardrails for agentic systems.
Blog post — The startup’s guide to getting started building on Neo4j Aura: Pradeep Ponduri's walkthrough on provisioning Aura instances via CLI, plus training and GraphRAG library resources for startups.
Blog post — Navigating a Neo4j Knowledge Graph with Jev: Michael Hunger's early exploration of Jev with Neo4j, including demo code and pros/cons.
Thanks for listening, and happy coding!

Jennifer Reif talks with Dr. Robert Kerstein, a prosthodontist with 42 years of experience researching the T-Scan bite computer.
T-Scan uses pressure-mapping sensors to measure bite force, timing, and friction. It's the same Tekscan sensor tech used in aerospace, automotive, and robotics.
Software records bite dynamics like a movie, enabling data-driven analysis instead of subjective guesswork with traditional paper and ink.
Recurring tracking lets clinicians compare recordings over time to catch changes early.
Effective use requires hands-on, chair-side training, just like developers need real keyboard time with a new tool.
Emerging research shows the bite communicates directly with the brain and cranial nerves, linking dental mechanics to neurology.
The T-Scan incorporates AI to flag problem areas in bite data, but medical device regulations prohibit it from making diagnoses. This is a key constraint for developers building AI into medical tools.
Resources:
Website: Dr. Robert Kerstein
Tekscan: Digital Occlusal Analysis
Resources: DTR Providers | Digital Occlusion Seminars
Thanks for listening and happy coding!

Jennifer shares updates on her upcoming AI First Java book, fall event prep, and spring 2027 conference abstracts. Key topics this episode:
GraphAcademy makeover. Neo4j's learning platform now features browser-based code environments, auto-generated API keys, AI-assisted data modeling, and public datasets for self-paced learning.
GraphRAG workshop. Jennifer recently delivered a virtual workshop on generative AI and GraphRAG using the updated GraphAcademy platform.
Graph Summit NYC. Neo4j's flagship event featuring a brand-new hands-on workshop format where attendees build a working project.
Upcoming events. Northeast JUG tour in late September (Raleigh, NC; Charlotte, NC; Richmond, VA) and a RAG benchmarking webinar in the works.
"Building Software is Learning". Thorsten Ball's article on shortening the feedback loop between building and validating requirements, and why iterative development matters even more in the age of AI coding tools.
Real-world example. Jennifer shares how writing her book's capstone project with Claude reinforced the need for upfront context, boundaries, and tight iteration when working with AI.
Thanks for listening, and happy coding!

This week, I took a detour with a different kind of productivity and share highlights from two must-read articles on AI-era software development.
My "brain sabbatical": a strategy day for deep focus, ideation, and conference abstract brainstorming.
Upcoming events:
Intro to AI Workshop (Sep 3)
GraphSummit NYC (Sep 17)
Northeast US meetup tour (Sep 21–23, Raleigh, Charlotte, Richmond)
"Domain Knowledge Is the Leverage" by Beshr Kayali Reinholdsson: practices like TDD and DDD are more relevant than ever in the AI coding era
Spec-driven development: specs as living decision documents, not page-count exercises
Tests matter more than ever. AI-generated code still needs independent verification.
"Coding Is Solved, Software Is Not" by Gao: writing code is no longer the bottleneck; context, specs, verification, and human checkpoints are
Confirmation bias risk: AI-generated test suites may just validate the implementation the agent already chose
Key takeaway: developers are spending more time on design decisions, domain clarity, and proving the right thing was built
Thanks for listening, and happy coding!

I'm back after some time off and excited to catch you up on everything that's been happening. This week, hear updates on the Java book, some upcoming fall events, and dive into two articles that challenge how we think about AI in development and architecture.
The Java book is in its final chapters. It now incorporates Claude, planning mode, and a capstone project so developers walk away with something personal and useful
Feeling out of touch with the industry's pace? Me too! Balancing competing priorities is a real challenge
Fall events ahead: Java User Group tours (East Coast in September, Southeast in November), plus new guest episodes and 2027 conference abstracts
Article 1: "You Need AI That Reduces Maintenance Costs" by James Shore. AI boosts front-end productivity, but what about long-term maintenance costs?
Maybe we should "shift right" just a bit — plan for your future self, not just immediate output
Article 2: "AI versus Microservices" by Michael T. Nygard. AI tools speed up development but cause merge conflicts, governance gaps, and ownership sprawl
The monolith vs. microservices debate extends beyond tech. Streaming services and cloud backups follow the same pendulum
More data points lead to better architecture decisions, whether in AI processes or everyday life
Thanks for listening, and happy coding!

In this episode, I sit down with John Willis, author of The DevOps Handbook and Rebels of Reason. We discuss how lessons from John's five decades of technology shifts apply to organizations the AI era.
Highlights:
The "fluorescence" of AI: why the hype is blinding and what we keep forgetting
Patterns from Linux, cloud, and DevOps that repeat with every tech shift
Ideation hackathons: a structured approach to organizational AI adoption
Data provenance risks and why throwing tools at non-technical teams is dangerous
Buy vs. build: open weight vs. public models and the hybrid approach
"Code is the new assembler": will developers still write code?
AI model drift: what happens when a model upgrade breaks your application
Agentic AI, kill switches, and the efficiency-thoroughness trade-off
Links and Resources:
John's AI CIO newsletter
John's Amazon Author Portal
John on LinkedIn

This week, hear the latest updates on writing the Java book and prepping meetup tours, as well as a thought-provoking article on developer cognition in the age of AI.
Deep dive into lambdas: concise, one-line rules for sorting, filtering, and transforming data
Streams explained: pipelines that apply lambda rules across collections of items
Lambdas + streams as examples of declarative programming vs. imperative for-loops
Writing progress update: caught up after a slow start framing the new chapter
Virtual meetup event! Happening next week for the Miami Java User Group. Join us!
Discussion of an article on cognitive offloading vs. cognitive surrender with AI tools (Cognitive Surrender by Addy Osmani)
Key point: while easier to copy/paste or let AI, we suffer without comprehension.
The "calibration question": are you forming your own view, or just adopting the AI's?
Takeaway: use AI to delegate and enhance your work, not to replace critical thinking

In this episode, hear my latest writing progress on the Java book, a couple of new DZone blog posts, and upcoming meetups and podcast guests. I also dig into an article on how AI is reshaping developer relations.
Made strong progress on the Java book, wrapping up one chapter and starting the next
Published a new blog post on DZone about the agents architecture (first of several planned installments)
Colleague Akmal Chaudhri published a DZone post on Spring AI, Neo4j, and Goodreads data — check it out!
Meetup tours coming up: Florida groups in November, North Carolina groups in September (details soon)
Virtual talk for the Miami JUG on GraphRAG/RAG coming up later this month (event link here)
New podcast guests starting to line up for the coming weeks
Discussed the article "Developer Relations After the Cheat Code Machine" by Sunil Pai
Explored how "watch me work" content reflects a shift in how developers learn implicit knowledge
Reflected on how DevRel's core mission remains the same, even as the format evolves

Recap of my week, with several different topics where I expanded my knowledge or surfaced some recurring patterns in my efforts.
Highlights:
Repeated prompt iteration can cause LLMs to get stuck in unhelpful loops or produce slightly different code on reruns. Restoring to a checkpoint helps reset context and regenerate cleaner output.
A personal AI workflow shortcut: using chat models to brain dump and organize ideas into structure before writing.
Pet projects. Alongside expanding a Goodreads project, there's a potential new personal improvement app idea
Other tasks: session review for NODES conference, upcoming refresh work on a Knowledge Graph e-book, and plans for short-form video content.
Article: “Read Less, Steer More” by Ezyang on mentoring code reading, using LLMs to explain code, avoiding auto-accept edits, and writing code by hand when learning fundamentals.

This week included reviewing abstracts for NODES developer conference returning this fall, making progress on the book, and other exciting things happening within the team.Highlights:
Schedule for Neo4j’s free virtual NODES is in the process as we review and select sessions. Register now!
Progress on the Java book with an aggressive schedule that is challenging, but manageable.
Several colleagues are at the AI Engineer World’s Fair in California, so stop by to see them!
Neo4j launched a major refresh to the GraphAcademy site, featuring a new design, AI-forward learning features.
Hear my thoughts on Andy Coenen’s article “The Software Industrial Revolution". AI may reduce software costs, increase software consumption, disrupt monopolies, and potentially improve costs and experiences in areas like healthcare.