i am going to publish an english version too :-) IT-Spektrum, sigs.de/artikel/der-macintos… #LLMs #AgenticAI #DataPipelines #GQL #KnowledgeGraphs #Ontologies #GraphDBs #Reasoning #Microservices #DDD #NeuroSymbolic #Cypher #SPARQL

🧠 Organizational Knowledge Graphs LLMs — the powerful institutional memory layer that preserves critical knowledge beyond individual employees, reduces loss from attrition, accelerates onboarding/problem-solving, and enables smarter decisions at scale. Just read this excellent capstone technical white paper from @aasaitech on building living enterprise knowledge graphs (equipment, processes, failures, decisions, people, SOPs) enhanced with LLMs for natural language querying, multi-hop reasoning (GraphRAG), summarization, generation, and explanation. Key highlights: • Full lifecycle: Ingest → Extract → Build → Enrich → Query/Reason → Update & Learn → Share & Scale • Industrial impact: Faster RCA, maintenance resolution, compliance/auditability, operational excellence, knowledge resilience • Practical example: Natural language questions over connected historical incidents, manuals, sensor data, and tribal knowledge This is a vital culmination of the entire series — turning RAG, GraphRAG, agents, long-term memory, hybrid AI, and observability into persistent, evolving enterprise memory systems for manufacturing and edge orchestration. Full white paper infographic: x.com/aasaitech/status/20656… How are you building institutional memory in your organization — knowledge graphs with GraphRAG, hybrid vector KG systems, or still fragmented document/search approaches? #KnowledgeGraphs #GraphRAG #InstitutionalMemory #IndustrialAI #EnterpriseAI #AgenticAI #ManufacturingAI #EdgeAI

today i learnt about graph rag and a little about neo4j database. graph rag uses knowledge graph which is semantic network and connect real world entites. knowledge graph involves 3 things 1. nodes -> any object , place ,person or any noun 2.edges -> an edges defines the relationship between the nodes 3.labels -> basically the name of relationship example -> virat kohli is captain of indian cricket team. virat kholi , indian cricket team = nodes captain = label of edge of relationship. also got introduced to cypher queries. pretty cool stuff, definitely want to explore this more. #graphrag #neo4j #knowledgegraphs #rag #aiengineering #generativeai #llm #machinelearning #buildinpublic

#KnowledgeGraphs: The Real #GameChanger … but Hard to Build and Maintain by Thilo Hermann thilo-hermann.medium.com/kno…

Join thousands of developers, AI engineers, and data pros at NODES 2026, a free 24-hour conference diving deep into talks about the latest advances in engineering better intelligence. Learn directly from your fellow developers in technical sessions on real-world implementations, advanced tooling, and innovative models. The call for papers is open until June 15. To Know More : buff.ly/CdcNAK8 #AnalyticsandStatistics #MachineLearning #Node #graph #Applicationsoftware #KnowledgeGraphs #Architecture #AIEngineering #graphs #DataIntelligence

Excited to share that Datavid will be at @ksummitdublin 2026 🚀 From semantic search to knowledge graphs, we’re helping enterprises build trusted, AI-ready knowledge foundations. Looking forward to conversations around this year’s theme: “Humans in the Loop.” 📍 Trinity College Dublin 🗓️ 29–30 June See you in Dublin 👋 datav.id/49EVjW5 #KnowledgeSummitDublin26 #EnterpriseAI #KnowledgeGraphs #Datavid

The Early Bird clock is ticking. ⏱️ In just 3 days, ticket prices for #CDL26 will increase across all pass types - including All-Access, Day Passes, and Remote. This is your final window to join us at the Leonardo Royal Hotel London Tower Bridge while saving 30%. What’s on the table: ✅ Technical deep-dives into Knowledge Graphs and LLMs. ✅ Hands-on Masterclasses. ✅ Networking with the world’s top data architects. Don’t wait for the deadline. Save 30% and book your pass today. 👉 2026.connected-data.london/c… #CDL26 #ConnectedData #KnowledgeGraphs #DataScience #AI #GraphDB #Analytics #SemTech #EmergingTech #EnterpriseData #DataStrategy #AIArchitecture

Link: linkeddata.uriburner.com/DAV… #ABAC #KnowledgeGraphs #ContextGraph #Business #AI

Here’s another HTML infographic, loosely coupled with a knowledge graph deployed as a Semantic Web, focused on the World Cup. It’s packed with interesting insights, statistics, and connections. Just click and explore, as usual. linkeddata.uriburner.com/DAV… #KnowledgeGraphs #LinkedData #SemanticWeb #WorldCup2026 #VirtuosoRDSBMS

Our paper "Gradient-Based Join Ordering" (with @maribelacosta ) will be presented at IJCAI 2026! Join ordering, deciding the order in which to evaluate the joins of a database query, is a classic and discrete NP-hard problem, and one of the most important in any database engine. Current engines approach it using discrete algorithms like dynamic programming, greedy heuristics, or genetic algorithms. In our new paper, we explored a different option. If the cost model is differentiable (e.g., a neural network), why not search using a gradient? For that, we relax discrete query plans into a soft adjacency matrix, i.e., a continuous superposition of plans, and descend the cost landscape directly via gradient descent. Differentiable structural penalties (degree constraints, acyclicity, left-linearity) combined with temperature annealing ensure the optimization converges to a valid, discrete plan. Interestingly, although the cost model is only ever trained on valid, discrete plans, the relaxed space between them turns out to be smooth and informative — the local gradient reliably points towards better plans. Key results on two standard benchmarks: • Plan quality matches and often surpasses discrete baselines • Only ~10 cost model evaluations are needed, vs. hundreds for randomized search • Runtime of 40–200 ms with more favorable scaling in query size than greedy search We think this is a first step towards query optimizers that treat plan search as continuous optimization rather than combinatorial enumeration. #IJCAI2026 #QueryOptimization #DatabaseSystems #GraphNeuralNetworks #KnowledgeGraphs

The future of aviation search is answer-driven. AEO helps aircraft manufacturers, MRO providers, leasing companies, and aviation service firms become trusted sources for AI-powered search engines by optimizing technical content, entity relationships, safety information, and procurement insights for maximum visibility, authority, and discoverability across digital ecosystems. #AEO #AISEO #AviationIndustry #AircraftTechnology #MRO #EntitySEO #KnowledgeGraphs #DigitalAviation #AnswerEngineOptimization

💡 AI can generate answers. But can organizations trust them? In our next issue, we explore what it takes to build AI people can trust, not just adopt, including Roche’s approach to accurate, contextual policy guidance. 📩 Subscribe here: datav.id/4dXdUPG #EnterpriseAI #KnowledgeGraphs #AI

Everyone is building AI agents. Almost nobody is building AI accountability. Today's agents can retrieve information, generate answers, and take actions. But ask them: • Why did you make this decision? • Which facts did you use? • What was the reasoning path? • Can I audit this later? Most have no answer. That's why we built Semantica. An open-source intelligence layer for AI systems featuring: 🧠 Context Graphs 🔍 Full Provenance ⚖️ Decision Intelligence 🕸️ Knowledge Graphs 🤖 Agent Memory ⏳ Temporal Reasoning 📚 Ontology Reasoning ⭐ 1,200 GitHub stars 👥 21 contributors 🚀 Growing fast GitHub: github.com/semantica-agi/sem… If you believe AI should be explainable, auditable, and trustworthy, please star the repo and share it with your network. #AIAgents #AgenticAI #GraphRAG #KnowledgeGraphs #OpenSourceAI #LLMs

Programme Update: New Speakers from Gartner, Scania and Google 🎤 The Connected Data London 2026 programme continues to expand. We are pleased to introduce our latest speaker additions for our 10th anniversary event in London: Vinay Balasubramaniam (Google): Director of Product Management for BigQuery, our Gold Sponsor. He will discuss the BigQuery Core SQL Engine, price performance and advanced analytics covering vector search, graph analytics and AI co processing, drawing on his extensive background leading enterprise platform strategy. Afraz Jaffri (Gartner): A VP Analyst delivering strategic market insights on the intersection of AI, context and knowledge graphs. He will break down how to implement graph based solutions for reliable agentic systems, drawing on a decade of experience advising enterprise leaders on data platform strategy. Bei Li (Google): A founder of Spanner Graph and BigQuery Graph from our Gold Sponsor team. He will share the technical vision and engineering development behind both graph systems since their inception, alongside insights from building foundational data infrastructure for Google Search and Ads. Nikos Trokanas (Scania Group): An Ontology Architect specialising in knowledge graphs, ontology engineering and generative AI integration. He will share practical insights from his 15 years of experience delivering semantic infrastructure across the automotive, finance and biomedical sectors. Read more about our speakers and their upcoming sessions: 👉 2026.connected-data.london/?… #CDL26 #ConnectedData #KnowledgeGraphs #DataArchitecture #Gartner #Scania #Google #BigQuery #AI Ps. Early Bird pricing ends Monday 15 June. Book your ticket now for the lowest rate: 👉 2026.connected-data.london/

Ontologies aren't disappearing in the age of AI agents. They're becoming the layer that helps agents retrieve, remember, validate, and act. A great read from @cyberandy: eu1.hubs.ly/H0v-Ymp0 #AI #KnowledgeGraphs

Why every AI workflow learns in isolation—and how I moved from static skills to a shared, governed knowledge graph that compounds as the work teaches me. #densemem #aimemory #knowledgegraphs markhuang.ai/blog/centralize…

مع تزايد اعتماد المؤسسات على المنتجات الرقمية الذكية، لم يعد تخزين البيانات وحده كافيًا لتحقيق القيمة المرجوة منها. فالتحدي الحقيقي يكمن في القدرة على ربط البيانات القادمة من أنظمة متعددة، وفهم العلاقات بينها، واستخلاص المعرفة التي تدعم اتخاذ القرار في الوقت الفعلي. وهنا تبرز أهمية Enterprise Knowledge Graphs (EKGs) كأحد أهم المكونات المعمارية الحديثة للأنظمة الذكية واسعة النطاق. تستعرض هذه المقالة كيفية تحسين الرسوم البيانية المعرفية المؤسسية لتلبية متطلبات المنصات الرقمية القابلة للتوسع، مع التركيز على التحديات العملية التي تواجه المؤسسات عند الانتقال من النماذج التجريبية إلى بيئات الإنتاج الفعلية. توضح المقالة كيف أصبحت الرسوم البيانية المعرفية عنصرًا أساسيًا في العديد من التطبيقات الحديثة، مثل أنظمة التوصية، وكشف الاحتيال، والتخصيص الذكي للمحتوى، ومحركات البحث المؤسسية. فمن خلال تمثيل البيانات على شكل كيانات وعلاقات مترابطة، يمكن للمؤسسات بناء فهم أعمق للسياق وتحسين جودة التحليلات والقرارات المدعومة بالبيانات. كما تناقش مجموعة من الاستراتيجيات العملية لتحسين الأداء وقابلية التوسع، بما في ذلك اعتماد البنى الهجينة بدلاً من الاعتماد على مخزن رسوم بيانية واحد، وتقنيات تقسيم البيانات (Partitioning) لتقليل تكلفة الاستعلامات الموزعة، وإدارة عمليات الاستدلال الدلالي (Semantic Inference) دون التأثير على زمن الاستجابة. وتسلط المقالة الضوء أيضًا على أهمية تحسين خطط تنفيذ الاستعلامات، ومراقبة الأنظمة بشكل مستمر عبر آليات Observability المتقدمة، باعتبارها عناصر أساسية للحفاظ على الأداء والاستقرار في البيئات الإنتاجية الكبيرة. ما يميز هذا الطرح أنه يركز على الخبرات العملية والدروس المستفادة من تطبيقات مؤسسية حقيقية، بدلاً من الاكتفاء بالمفاهيم النظرية. لذلك تعد المقالة مرجعًا مهمًا لمهندسي البيانات، ومهندسي المنصات، ومهندسي الذكاء الاصطناعي، وقادة التحول الرقمي الذين يعملون على بناء أنظمة تعتمد على المعرفة والسياق لتحقيق مزيد من الذكاء التشغيلي وقابلية التوسع. freecodecamp.org/news/how-to… #برمجة #تقنية #KnowledgeGraphs

Join thousands of developers, AI engineers, and data pros at NODES 2026, a free 24-hour conference diving deep into talks about the latest advances in engineering better intelligence. Learn directly from your fellow developers in technical sessions on real-world implementations, advanced tooling, and innovative models. The call for papers is open until June 15. To Know More : buff.ly/CdcNAK8 #AnalyticsandStatistics #MachineLearning #Node #graph #Applicationsoftware #KnowledgeGraphs #Architecture #AIEngineering #graphs #DataIntelligence

Most AI systems are blind to relationships. They retrieve. They predict. They hallucinate. They don't *reason*. Semantica gives AI a Context Graph — structured memory, causal chains, and full decision provenance. Watch the platform tour 👇 #KnowledgeGraphs #AI #OpenSource