This Week in Neo4j: Knowledge Graph, Life Sciences, GraphRAG, NODES, Startups and more Neo4j announced dedicated field engineers for startups and released a new edition of its weekly newsletter covering knowledge graph maintenance, a GraphRAG semantic layer built from BigQuery and GCP Knowledge Catalogue, and the upcoming GraphTalk Pharma & Life Sciences event on July 2 featuring practitioner talks from Bayer, BASF, and Insel Spital Bern. This Week in Neo4j: Knowledge Graph, Life Sciences, GraphRAG, NODES, Startups and more Staff Community Manager 5 min read Welcome to This Week in Neo4j, your fix for news from the world of graph databases If you’re building with Neo4j at a startup, we now have dedicated field engineers ready to talk schema design, production scaling and getting your prototype moving. This edition also covers how to keep your agent’s knowledge graph clean as it scales; a GraphRAG semantic layer built from BigQuery and GCP Knowledge Catalogue; all NODES AI sessions browsable in the Neo4j Showroom and GraphTalk Pharma & Life Sciences on July 2, with practitioner talks from Bayer, BASF, Insel Spital Bern and more. Share your experiences and influence the future of Neo4j products: Join the Neo4j User Research panel https://message.neo4j.com/NzEwLVJSQy0zMzUAAAGZN8qvbggSloC9gXkMyg5KMvlV10ryIrNUXCa QC8dLTLXTjPbtfIiUvrsfzG2kLxc3ReSbQM= It’s a chance to connect directly with product development teams, get paid compensation, hear about what we are working on and more Happy Graphing, Alexander Erdl COMING UP Livestream : Virtual Graph: Graph Intelligence for Your Existing Data https://www.linkedin.com/events/7463138239621734402 on June 23, AI Governor: Quality gates for agentic workflows https://www.youtube.com/live/Wb UOg93BLM on June 25 & GraphTalk pharma & life sciences https://events.neo4j.com/graphtalkpharmalifesciencesde on July 2 Conferences : Find us at MLCon, Munich https://mlconference.ai/munich/ on June 23-25, AI Engineer World’s Fair, San Francisco https://www.ai.engineer/worldsfair/2026 on June 29 – July 2, AWS Summit, Washington D.C. https://aws.amazon.com/events/summits/washington-dc/ on June 30 – July 1 & WeAreDevelopers, Berlin https://www.wearedevelopers.com/world-congress on July 8-10 Meetup : Meet us in Munich, DE https://eventmanager.deinerfolg.ai/event/1/munich-ai-conference-by-maikers on June 26, Gurgaon, IN https://www.meetup.com/graphdb-delhi-ncr/events/315211010/ on June 27, San Francisco, US https://luma.com/neo4j-0v66 on June 28, San Francisco, US https://luma.com/8rw9j9t5 on June 30, San Francisco, US https://luma.com/neo4j-3f49 on July 1 & London, UK https://www.eventbrite.co.uk/e/ljc-meetup-at-neo4j-smarter-search-with-spring-ai-and-neo4j-tickets-1991379537804 on July 2, Berlin, DE https://globalai.community/e/7lns53g4 on July 8 All Neo4j Events : Webinars and More https://neo4j.com/events/ FEATURED COMMUNITY MEMBER: Johannes Sommer https://www.linkedin.com/in/johannes-sommer-a7b829139 Johannes Sommer https://www.linkedin.com/in/johannes-sommer-a7b829139 Johannes is Co-Founder of SemVec AI and the architect of one of Germany’s most active AI practitioner networks. Connect with him on LinkedIn https://www.linkedin.com/in/johannes-sommer-a7b829139 . He has one of the first confirmed sessions at NODES 2026 https://neo4j.com/nodes/ “Using semvec AI for detecting agentic drifts”, where he will present a hybrid architecture combining SemVec AI’s Persistent Semantic State with Neo4j’s graph-based knowledge representation to detect and recover from semantic drift autonomously. KNOWLEDGE GRAPH: How to Keep Your AI Agent’s Knowledge Graph Clean https://www.decodingai.com/p/keep-knowledge-graph-clean Paul Iusztin’s follow-up to his agent memory architecture piece focuses on the part most tutorials skip: keeping the graph clean as it grows. He separates entity resolution from deduplication, explains why collapsing the two is what silently corrupts graphs and adds two safety nets: a human review queue modelled as pending SAME AS edges in the graph itself and a nightly dream pass that re-runs deduplication over recently ingested nodes to catch concurrent-write collisions. LIFE SCIENCES: GraphTalk pharma & life sciences https://events.neo4j.com/graphtalkpharmalifesciencesde GraphTalk Pharma & Life Sciences returns on July 2 – again as a hybrid event so that you can join in person or online. The day follows the pharma product life cycle with practitioner talks from Bayer GraphRAG for drug target discovery , KWS Group explainable candidate gene identification , BASF knowledge graphs for non-model plants , Insel Spital Bern multilingual EHR mapping in Neo4j and more. GRAPHRAG: Build a Semantic Layer from GCP with Neocarta https://neo4j.com/blog/genai/build-a-semantic-layer-from-gcp-with-neocarta/ Alex Gilmore walks through Neocarta, a Neo4j Labs Python library that builds a graph-backed semantic layer by pulling schema metadata from BigQuery and business glossary terms from GCP Knowledge Catalogue – two CLI commands, and you have a traversable graph of databases, tables, columns and business terms with vector and full-text indexes built in. The post then wires the result to an MCP server so that any agent can perform a hybrid semantic search across your data landscape, rather than dumping raw schemas into the context window. NODES: Neo4j Showroom https://www.alaniconnect.com/room/neo4j Alani Connect lets you discover curated talks, groundbreaking research and visionary leaders and connects you to the ideas, people and solutions driving real change. The Neo4j Showroom by Athulya Anil, William Lyon & Ashok Vishwakarma has all the sessions from NODES AI https://neo4j.com/nodes-ai/ for you to explore. STARTUPS: Now available: Dedicated Neo4j field engineers empowering AI startups https://neo4j.com/blog/startups/now-available-dedicated-neo4j-field-engineers-empowering-ai-startups/ Brian O’Keefe explains what he’s hearing from founders: credits are fine, but what they actually need is a real technical conversation about schema design, production scaling and getting a prototype running fast enough to convince sceptical co-founders. We want to give startup founders the right tools and support to succeed when building with Neo4j. From now on, I will also showcase a few of our Startup Program Members https://neo4j.com/startup-program/ – First up: QuantumSpace https://neo4j.com/customer-stories/quantumspace/ QuantumSpace is using Neo4j AuraDB to combat art forgery by extracting up to 60,000 data points from a single painting. They map elements such as colour, brushstroke physics and historical provenance as a graph. The relationships between these data points help establish authenticity, with Neo4j serving as their knowledge layer to connect verifiable facts with inferred signals such as tonal similarity and geographic context. What began as a thesis experiment has now attracted interest from the fashion industry, automotive sector, and even a European space agency. CONTINUOUS LEARNING GraphAcademy : Join the “ Cup https://cup.graphacademy.neo4j.com/ “, complete Courses and win prizes Learn on Your Schedule : Go deeper into graph intelligence on Neo4j’s On-Demand webinar library https://neo4j.com/events/on-demand/? event level=intermediate Workshops : Join our virtual classrooms workshops from Fundamentals to GenAI https://neo4j.com/events/? event type=workshops New Webinar : Build the ontology at the core of your semantic layer – Americas https://go.neo4j.com/WBR-EDU-260625-Ontology-driven-semantic-layer Registration.html , Europe, Middle East & Africa https://go.neo4j.com/WBR-EDU-260625-Ontology-driven-semantic-layer-EMEA Registration.html , Asia Pacific https://go.neo4j.com/WBR-EDU-260625-Ontology-driven-semantic-layer-APAC Registration.html POST OF THE WEEK: Spring I/O https://bsky.app/profile/springio.net 🍃 Thinking in Relationships: Practical Graph Database Modelling in Java with Neo4j by @paulienvanalst.bsky.social @ Spring I/O 2026 ▶️ Video: youtu.be/ImdfQzopSkg 🔗 Slides: www.slideshare.net/slideshow/pr… springio26 — Spring I/O @springio.net 9. Juni 2026 um 18:40 Please share it if you like it