GraphGeeks Podcast

Setting the tone for GraphCon Seattle 2026, Brad Bebee (Director at AWS, Amazon Neptune) shares his perspective on the shifting landscape of graph technology. He explores why the rise of Generative AI and autonomous agents has transformed graphs from a "vitamin" (a nice-to-have clean data model) into a "painkiller" (an essential tool for AI accuracy, memory, and explainability).Key Topics:Why companies pay for graphs (and how Wiz leveraged graphs for explainability)The shift from "Vitamins" to "Painkillers" in enterprise adoptionWhy AI agents are driving a resurgence in ontologies and markdown graphsHow generative tools streamline knowledge graph creationQ&A: Source of truth vs. sidecar architectures

At ODSC, Amy Hodler (GraphGeeks) chats with Stamati Liapis, cofounder of Enlay, about using graph AI and network modeling to transform risk management in the construction industry. Stamati explains how he applied his PhD in computational neuroscience (studying brain networks) to solving complex risk networks in construction.Key Takeaways: Around 96% of construction data sits unused. Graph AI and LLMs help structure this messy data for accurate future predictions.We can combine graph modeling and LLMs to help contractors analyze financial, commercial, and contractual risk across a project’s entire lifecycle.Academic Founder Tip: Shift from perfectionism and ship an 80%-ready product to get real-world user feedback instead of optimizing in a silo.More Info about Enlayehttps://www.enlaye.com/

In this Graph Chat, Amy Hodler catches up with James Massaquoi at the Glasswing Ventures offices for a candid conversation on where knowledge graphs, AI agents, and enterprise data architectures are heading.Key Topics Covered:Context for Autonomous AI: Why reliable enterprise AI workflows depend on understanding historical context and connected data.Cutting Through Buzzwords: Why "context graphs" shouldn't be overhyped and where graph technology actually delivers value in the modern stack.Knowledge Graphs - Memory Stores: How the line between graph databases, auxiliary memory models, and agent architectures is blurring.Building for Enterprise Scale: What early-stage investors look for in AI and knowledge graph startups today.🔗 More on Glasswing Ventures: https://glasswing.vc/

In this interview live from the Open Data Science Conference (ODSC) in Boston, Amy Hodler (GraphGeeks) sits down with Dr. Janet Six, Senior Product Manager at Tom Sawyer Software, to discuss the evolving role of data visualization and graph technology in the age of AI. Dr. Six highlights why data visualization shouldn't just be an afterthought—like sticking a basic pie chart into a slideshow—and advocates for a systems engineering approach to craft interactive, meaningful visual tools. They explore how visualization is essential for monitoring and managing complex AI agent workflows, as well as providing the deep context that simple LLM text responses often miss.

Are you feeling anxious about the future of AI and your job? In this GraphGeeks chat, Amy Hodler catches up with Kathryn (Kat) Erickson, co-author of Tech Confidential, live from the Open Data Science Conference (ODSC).Kat shares how the tech industry shifted from excitement to fear, why bypassing failure with AI actually kills our creative fulfillment, and practical, "Zen" strategies to combat career anxiety through action and writing.Key TakeawaysMental Toughness in Tech: Tech Confidential tools for maintaining your confidence and identity at any stage of the tech journey. https://www.techconfidential.ai/ The Value of Failure: AI lets us skip the trial-and-error process, but we risk missing the unexpected breakthroughs and fulfillment that come from solving hard problems.Action Combats Fear: You can't control market shifts, but you can control your response. Reclaim the Explorer Mindset: AI has leveled the playing field. Instead of fearing the next 10 years, tech professionals have the power to actively build a better future.

Amy Hodler takes a moment with Paco Nathan (Senzing) at the Open Data Science Conference (ODSC) to chat about the shift happening in Graphs and AI.From packed tutorial rooms to hallway conversations, graphs are no longer just for academics—they are driving real-world business cases. Paco breaks down his ODSC workshop on entity resolution, and combining graph algorithms with vector stores.Key Takeaways:The Business Pivot: Why technical teams are shifting focus from just building knowledge graphs to solving immediate business problems.Graph + AI Integration: How entity resolution generates the clean data needed for advanced graph tech and downstream AI apps.Why ODSC is the Sweet Spot: A look at the thriving community, networking, and the future of growing graph focus.

In this Graph Chat, Amy Hodler catches up with graph expert and consultant Clair Sullivan at the Open Data Science Conference to talk about Entity Resolution, GraphRAG, and catching fraud. Learn how concepts that used to be highly niche—like ontologies, semantics, and context graphs—are now entering mainstream tech workflows. And hear why we need to stop "vibe coding" everything and use knowledge graphs to deliver high-fidelity results.More Info on Clair and what she does: https://github.com/cj2001

Listen to a quick hallway at the Open Data Science Conference (ODSC) with Amy Hodler and Daniell Stevens, Product Analytics at Adobe.In this impromptu conversation, Dan shares his takeaways from the conference, including a trick for using SQL to bridge the definition gap between data science and engineering teams. We also dive into his personal history with graph path languages, how graph technology is colliding with LLMs to solve messy data problems like entity resolution, and why getting out of your day-to-day silo at events like ODSC is so critical for data practitioners.

How do we move past the ultimate graph answer: "It depends"?Live from the Open Data Science Conference (ODSC), Amy Hodler sat down with Golven Leroy, graph researcher and data science lead at Graphable, to discuss groundbreaking core mathematics that could change how we calculate the compute cost, latency, and bounds of graphs and trees—independently of technology.We also dive into his top takeaways from ODSC, including tracking LLM experiments with MLflow, revolutionary chip/circuit design, and open-source frameworks like Agor for visualizing enterprise AI agents.Link to the referenced paper: https://msp.org/involve/2026/19-2/p05.xhtml

Is the future of AI fluid and semantic, or rigid and structured? In this episode of Graph Geeks in Discussion, host Amy Hodler sits down with Roie Schwaber-Cohen, Head of DevRel at Pinecone. Together, they explore a fascinating philosophical and operational debate: the intersection of vector geometry (semantic distance) and graph topology (explicit connectivity). Tune in to discover why solving the next generation of AI challenges, from hallucinations to agentic long-term memory, requires fusing both worlds, and why we all might just need to "embrace the fuzziness."