GraphGeeks Podcast

Today's conversation with Claudia Natasia, CEO of Riley, takes us into the fascinating intersection of graph technology and customer behavior. As a data scientist turned product leader, Claudia discovered that the key to unlocking revenue growth was hidden in the complex web of customer data. That insight led her to found a company that's revolutionizing how businesses understand their customers using the power of graph technology. Join us as we explore her journey from data-driven problem solver to innovative tech founder, and learn how companies are uncovering elusive customer insights.

Listen to Amy Hodler interview Jesse Kallman, Founder & CEO at Danti, and Anthony Hylick, their Head of Machine Learning. Learn why Earth-Data is increasingly important today and how Danti uses graphs and AI to power its search engine. https://danti.ai/ Hear how this context-rich search goes beyond geospatial to enable users—from government agencies to private enterprises—to find the precise data they need from the vast, ever-growing datasets collected by satellites, drones, and other sources around the globe.

Listen to this GraphGeeks podcast to learn about Streaming Graphs for Cybersecurity. Our graph practitioners will appreciate hearing about graph event stream processing, and our cybersecurity listeners will learn how graphs are used to detect complex patterns and advanced persistent threats. Our guests include Paige Roberts, who’s had various roles in her 25 years in software and is currently the Director of Product Innovation for thatDot. Paige has also co-authored and contributed to several O’Reilly books, including “97 Things Every Data Engineer Should Know” and “Accelerate Machine Learning with a Unified Analytics Architecture.”We also have our cybersecurity expert, John Cloonan, who has 25 years of experience deploying security controls, combating network attacks, and bringing new cyber solutions to market. John is now the VP of Product at thatDot.Resources discussed on this podcast:Open source streaming graph quine.io/ The blog on scaling - www.thatdot.com/resource-post/scaling-quine-streaming-graph-to-process-1-million-events-second/The SANS Institute for Cybersecurity Training and Certification - www.sans.org/  

Listen to Amy Hodler interview Semih Salihoğlu, CEO of Kuzu and professor at the University of Waterloo, to learn about the fascinating history of graphs through the lens of database management systems. In this podcast, Semih walks us through the evolution of systems: from the first database system, IDS, to modern property graph databases, such as Neo4j and Kùzu. You’ll learn about the connections between the birth of the World Wide Web and document-based datasets and document stores, such as MongoDB. Amy and Semish also discuss the flexibility of RDF as a reasoning system and ties to the semantic web.In this quick history of graph databases, you’ll discover the roots of features that we see in modern graph database management systems and gain an appreciation for the collective innovations. Semih Salihoğlu Video Series https://www.youtube.com/@KuzuDBFurther Reading on the Early History https://tomandmaria.com/Tom/Writing/VeritableBucketOfFactsSIGMOD.pdf 2002 Interview with Charlie Bachman https://www.youtube.com/watch?v=iDVsNqFEkB0

In this podcast, we discuss current trends in knowledge graphs with François Scharffe, the CEO of The Data Chefs and co-founder of The Knowledge Graph Conference (KGC). First, François gives us insights into the evolution of KGC and the popularity of using knowledge graphs for RAG (retrieval-augmented generation). Then, we dive into the early indications that knowledge graphs may help bring back rule-/expert-based systems and the possibilities around personal knowledge graphs. https://www.thedatachefs.com/ https://www.knowledgegraph.tech/

Graphs are changing how we model, store, and query complex data. But when it comes to choosing the right type of graph model, the decision often boils down to two major contenders: Resource Description Framework (RDF) and Labelled Property Graphs (LPG). Each has its own unique strengths, use cases, and challenges. Join this GraphGeek talk with experts Jesús Barrasa and Dave Bechberger to better understand these approaches.

Sneak peek of Maya Natarajan's talk at KGC on graph market.

Discussion with Sanjeev Moham who has been in the data and analytic space for decades. Until recently, he was a Gartner research vice president and has recently returned from several conferences including Google Cloud Next. Sanjeev provides an overview of market trends including some surprise predictions for 2024. Find out more at SanjMo.com

Amy Hodler of GraphGeeks sits down with Weimo Liu, CEO of PuppyGraph, to discuss how they are changing the graph landscape. Unlike traditional databases, PuppyGraph is a graph engine that queries data directly where it lives—no data movement required. Key Highlights:Zero ETL: Query data lakes and warehouses (SQL, Delta Lake, etc.) as a graph without moving a single byte.Scalability: Designed for petabyte-scale analysis in industries like Cybersecurity, Anti-Fraud, and Healthcare.Simplify Graph-RAG by turning existing tables into a "knowledge brain" for chatbots.Fast Deployment: What used to take six months of data pipelining now takes just weeks via simple schema mapping.https://www.puppygraph.com/

For years, Enterprise Architects viewed graph databases with a mix of curiosity and dread. Between specialist silos, complex ETL pipelines, and infrastructure friction, many chose to stay in the safety of relational tables.Amy Hodler (Founder of GraphGeeks) chats with Max Latey (CEO of Pinboard Consulting) to discuss the shift in how organizations are adopting graph technology.Key Takeaways:Graph on Relational: How tools are allowing EAs to sprinkle graph capabilities over existing stacks without heavy ETL.GraphRAG & LLMs: Why the push for GenAI is making graph technology a must-have for context-rich AI.Data Modeling: Why understanding self-edges is the key to identifying a true network in your data.Lowering the Skill Ceiling: How SQL 2023 and GQL are making graph accessible to standard data teams.Pinboard Consulting specializes in high-impact graph solutions, entity resolution, and architectural strategy. https://www.pinboardconsulting.com/

Why is modern AI so "unruly"? According to information architect Jessica Talisman, it’s because we’ve over-indexed on data storage and ignored the art of description.In this Graph Chat, Bryce Merkel Sasaki sits down with Jessica (Founder of The Ontology Pipeline) to discuss the bridge between Labeled Property Graphs (LPG) and RDF, the rise of neuro-symbolic AI, and why every tech company needs the perspective of a "Chief Librarian."🔗 Resources:Substack: Intentional ArrangementFramework: The Ontology Pipeline

Join David Hughes (GraphGeeks community) for a Graph Chat with Chang She, CEO and Co-founder of LanceDB, filmed at the ODSC conference.Chang shares groundbreaking insights on how agentic retrieval systems are challenging traditional RAG approaches, requiring much higher throughput and iterative search. The conversation highlights the new Lance Format as the multimodal Lakehouse standard optimized for AI data operations.Most excitingly for the graph community, Chang provides a first introduction on the new open-source project, Lance Graph, which enables storing graph schemas and executing Cypher-like queries directly on Lance tables, integrating vector, tabular, and graph data into a unified format.Learn why data differentiation is the key to winning in the age of AI agents.https://lancedb.com/

Join Amy Hodler of GraphGeeks and Henry Gabb, Chair of the newly renamed Graph Data Council (GDC) (formerly the Linked Data Benchmark Council - LDBC), for a deep dive into the world of vendor-neutral graph benchmarks, standards, and innovation.Hear how the GDC is expanding its focus beyond traditional benchmarks like FinBench and Graphalytics to embrace microbenchmarks, synthetic data generation, and the exciting work being done on LEX schema to potentially unify property graphs and RDF. Learn why many members, including major vendors and researchers, value having a "seat at the table" to shape the future direction of the graph community.Explore the intersection of data performance, complexity, and the drive for standard graph query languages and schemas essential for emerging AI applications like text-to-graph query.https://ldbcouncil.org/

Amy Hodler and Dave Bechberger dive into the crucial role of memory in advanced AI systems, especially at the intersection of graphs, knowledge graphs, and generative AI.Dave Bechberger, currently focusing on MCP servers, agentic memory, and semantic data layers, explains that memory is fundamental because standard LLM calls are atomic and lack recollection of prior interactions. An agent without memory lacks continuity for complex user interactions.The discussion breaks down three key types of memory and how graphs apply:Episodic Memory: Transactional details are directly integrated into the context.Short-Term Memory: Session-based interactions that require compaction or summarization.Long-Term Memory: For extracting and storing patterns, trends, and preferences across multiple interactions.

Join Amy Hodler and Ricky Sun, CEO and founder of the high-performance graph platform Ultipa, as they explore the current state and future direction of graph technology. The discussion highlights the significance of the new ISO standard GQL (Graph Query Language), which Ricky believes will rapidly accelerate market adoption by providing a common language and preventing vendor lock-in. He also offers a practical view on Graph and AI, arguing that while AI is great for the "first and last mile", high-performance graph computing must handle the critical middle—providing real-time, white-box explainable reasoning for deep, trustworthy insights.GQL Book - https://www.packtpub.com/en-in/product/getting-started-with-the-graph-query-language-gql-9781836204008 Free GQL Playground https://www.ultipa.com/gql-playground

In this episode of the Graph Geeks in Discussion podcast, join host Amy Hodler and special guest Paco Nathan as they unpack the latest trends in AI and graph technology. They dive into insights from recent conferences, highlighting a shift toward practical, programmatic uses of generative AI within the software development lifecycle. Paco explains how companies are moving beyond simple code generation to focus on real-world applications like fault detection and root cause analysis. The conversation also explores the rise of hybrid AI—combining neural networks with symbolic systems like knowledge graphs—to create more efficient and explainable models. Whether you're a developer, data scientist, or just curious about the future of AI, this episode offers a deep dive into the innovations driving the industry forward, from the promise of neurosymbolic AI to the practical use cases of Graph RAG.

In this discussion with Dr. Denise Gosnell, an entrepreneur, business strategist, and author. Denise shares insights from her impressive career—from a college athlete to a PhD, to leading graph teams at AWS and Datastax—and discusses the inspiration behind her new book, Tech Confidential: An Insider's Playbook for Daring Entrepreneurs. She reveals how the book, structured like an onion with layers on ego, team dynamics, product-market fit, and exit strategies, provides a no-nonsense guide to navigating the tech industry. We also dive into why graph technology hasn't yet gone mainstream and discuss the importance of embracing chaos and having a coach, reminding listeners that you should never try to succeed alone. Playbook and resources: https://www.techconfidential.ai/

Join host Amy Hodler and guest Sumit Pal, a former Gartner research VP and current Strategic Technology Director at Graphwise, as they dive into the power of graph technology and its impact on AI. They discuss how graph-based data gives AI the crucial context it needs to deliver better results.In this podcast:How graphs help make data "AI-ready" by resolving quality issues and providing critical context.The difference between what a traditional AI model can do with flat data (what happened) versus what a graph-enhanced model can do (why it happened).Why the future of AI might be in smarter, more domain-specific Small Language Models (SLMs) rather than just massive LLMs.How Graph RAG can dramatically improve AI outputs.Follow up with Graphwise on https://graphwise.ai/.

Join us for an insightful discussion with Tomaz Bratanic, Graph ML and GenAI Research expert at Neo4j, as we dive deep into the world of GraphRAG and his newly released book "Essential GraphRAG – a practical guide to combining Knowledge Graphs with Retrieval-Augmented Generation (RAG)" (Manning Publications, co-authored with Oskar Hane).We explore how GraphRAG enhances LLM accuracy by combining the power of knowledge graphs with retrieval-augmented generation, covering everything from vector similarity search to agentic RAG systems. Tomaz also shares his unconventional journey from professional poker player to graph researcher.Key Topics Covered:The importance of incorporating more than just unstructured textAdvanced retrieval strategies and Text2Cypher generationBuilding knowledge graphs with LLMs and Microsoft's GraphRAG approachResources:📘 Free eBook from Neo4j: https://neo4j.com/essential-graphrag/

Join Amy Hodler, David Haglin (Rocketgraph), and David Hughes (Enterprise Knowledge) as they explore graph-wide scanning and its role in revolutionizing cybersecurity. Discover how graphs are eliminating blind spots, detecting advanced persistent threats, and transforming how analysts find crucial insights in massive datasets. Learn why traditional methods fall short and how AI integration is key to navigating the colossal scale of cyber data for unprecedented clarity and threat detection.Want to take Rocketgraph for a spin? https://rocketgraph.com/free-trial/