Live walkthrough: Our carsharing enterprise model. See how processes connect to strategy, resources, customers, and constraints. Interactive exploration: "Ask the enterprise" about current processes. Key insight: The richer the context, the smarter the AI suggestions.

Real-time demonstration: Feed the knowledge graph into GenAI. Watch AI analyze process bottlenecks with full enterprise context. Interactive session: Audience can join the optimization process live.

How to identify processes ripe for AI-assisted redesign. Building your knowledge graph: Start small, think big. Integrating live data for continuous optimization.

Adam Amara, cofounder & CEO at Turing Biosystems, discusses network-based modelling and multiomics integration on metabolic networks, multilayer networks to integrate mutiomics and clinical data with knowledge graphs, and the use of TuringDB.ai to analyse large biomedical knowledge graphs and build digital twins.

Large Language Models (LLMs) are powerful but notoriously ungrounded as they generate fluent, plausible text that isn’t always factual, consistent, or explainable. One promising way to address these issues is by connecting LLMs with Knowledge Graphs, namely structured, explicit representations of knowledge that can provide context, constraints, and verifiable facts. The main paradigm for doing this is Graph-based Retrieval-Augmented Generation (GraphRAG), which integrates graph-based reasoning and retrieval into the generation process. In this talk, I’ll introduce the core ideas behind GraphRAG, describe common design patterns, and outline the steps and tools needed to implement such systems in practice.

Zaid Zaim from Neo4j will introduce Plug-and-Play AI Memory — a new approach to giving AI agents long-term, contextual memory through knowledge graphs.

Discusses how Asset Administration Shell (AAS, IEC 63278) and Knowledge Graphs enable interoperable, trusted data exchange; also touches on LLMs connecting unstructured and structured data and regulatory context such as the EU Digital Product Passport.

In this hands-on workshop, you will learn how Knowledge Graphs and Retrieval Augmented Generation (RAG) can help GenAI projects avoid hallucination and provide access to reliable data. Topics include LLMs and hallucination, integrating knowledge graphs, GraphRAG, vector indexes and embeddings, querying graphs with natural language, and using Python and OpenAI to create GraphRAG retrievers and GenAI applications.

Moderator: Larry Swanson. Panelists: Peter Haase (metaphacts), Harald Sack (FIZ Karlsruhe & KIT Karlsruhe), Jennifer Lechner (d-fine), André Teege (Piterion), Alexander Garcia (Siemens Energy). Topics include: Can LLMs actually “understand” symbols, or are they just statistically impressive? How does symbolic reasoning enhance comprehension and trust? Should neuro-symbolic AI be the gold standard for safety and regulation? Is interpretability more important than raw performance? Whose knowledge do symbolic systems represent—and what are the implications?

Exploration of RDF to LPG transformations and maintaining semantic meaning in knowledge graphs.

Applying RAG (Retrieval-Augmented Generation) to financial data using knowledge graphs.

Discussion on the role of knowledge graphs in mental health diagnosis and treatment.