Podcast
Industrial AI Podcast
Hosted by Robert Weber / Peter Seeberg · EN
The Industrial AI Podcast reports weekly on the latest developments in AI and machine learning for the engineering, robotics, automotive, process and automation industries. The podcast features industrial users, scientists, vendors and startups in the field of Industrial AI and machine learning. The podcast is hosted by Peter Seeberg, Industrial AI consultant and Robert Weber, tech journalist.Their mission: Demystify Industrial AI and machine learning, inspire industrial users.
The hosts:
Peter Seeberg is an Industrial AI and machine learning expert for the manufacturing industry. He worked over 25 years in IT (Intel) and 10 years in Automation. He co-initiated the Industrial Data Intelligence Startup (Softing) where he was responsible for managing machine learning projects in industrial environments. Today he advises companies when it comes to Industrial AI and machine learning. Together with Robert Weber, journalist for industrial topics, he discusses AI and ML applications, standards, and education topics, make or buy decisions as well as regulation for AI in manufacturing.
31episodes
Episodes
Newest firstAll episodes
Autonomous Data Science!?
3d ago00:40:01Summary readyDiscover how agentic AI is reshaping time series forecasting and empowering business users. Dive into next-gen analytics with OctOpus. In this episode, we dive deep into the world of autonomous AI for data science with Doudou BA, CEO and founder of Octopus. I explore how Octopus is transforming raw data into actionable business decisions using advanced time series foundation models and agentic AI. We discuss the unique reasoning capabilities of Octopus, its intuitive approach for non-technical users, and how it stands apart from traditional AutoML solutions. Along the way, I share insights from VivaTech in Paris, including thought-provoking moments with industry leaders like Yann LeCun and Jeff Bezos. Join us as we reimagine the data science workflow and uncover what’s next for AI-powered business intelligence. More about NXAI (here) The Soofi X Discussion (here) Try OctOpus (here)
Summary
How a chemical engineer built an agentic manufacturing troubleshooting assistant
1w ago00:41:58Summary readyDiscover how domain expertise and AI merge to solve complex plant problems – no coding required. Can experience be replaced by intelligence? In this episode, I sit down with Scott Duncan, a chemical engineer who built an agentic manufacturing troubleshooting assistant – without any coding background. We dive into the real-world challenges of process manufacturing and how AI is transforming the way plant issues are solved. Scott shares his journey from hands-on troubleshooting to leveraging large language models, knowledge graphs, and real-time data for smarter, faster problem-solving. We also debate the future of domain expertise in an AI-driven world and what it means for education and workforce development. Join me as we explore the potential – and the limitations – of AI in reshaping the future of industrial operations. NXAI www.nx-ai.com Claude Code https://www.anthropic.com/news/claude-3-opus-sonnet-haiku MATLAB https://www.mathworks.com/products/matlab.html OPC Foundation https://opcfoundation.org/ OPC UA https://opcfoundation.org/about/opc-technologies/opc-ua/ PI System https://www.aveva.com/en/products/pi-system/ RAG (Retrieval-Augmented Generation) https://en.wikipedia.org/wiki/Retrieval-augmented_generation Knowledge Graph https://en.wikipedia.org/wiki/Knowledge_graph MCP Server https://docs.anthropic.com/claude/docs/mcp-server
Summary
AI-Engineering Workflows
2w ago01:34:56Summary readyFrom data silos to autonomous agents—discover how AI is reshaping engineering workflows. Insights, stories, and the tools driving the next wave. We just returned from three inspiring days at AI in the Alps, and in this episode, we dive into the most exciting breakthroughs and honest challenges facing industrial AI today. I share my firsthand impressions of revolutionary tools like TiRex-2, and we unpack what agentic AI really means for engineering, from breaking down data silos to transforming anomaly detection. Alongside Stefan Suwelack from Renumics, we discuss why skepticism has given way to optimism, how data infrastructure is finally catching up, and what the future holds for AI-driven organizations. The conversation is loaded with real-world examples, candid reflections, and a look at the evolving balance between sovereignty, open source, and big tech. Whether you’re an engineer, decision-maker, or just curious about the future of AI in industry, this episode offers practical insights and a glimpse into what’s next.
Summary
TiRex-2 - a multivariate time series foundation model
3w ago00:49:53Summary readyDiscover how TiRex-2 is revolutionizing time series AI for industry. Multivariate, streaming, and more—get the inside story. In this episode, I sit down with Levente Zolyomi, a leading PhD researcher at NXAI, to unpack the next evolution in time series AI: TiRex-2. We explore how TiRex-2 builds on its predecessor by handling complex multivariate data and streaming scenarios, opening new frontiers for industrial forecasting. Levente shares the story behind TiRex-2’s architecture, its breakthrough capabilities, and what sets it apart from transformer-based models like Kronos. I ask the questions you’re thinking—about zero-shot forecasting, synthetic data, and real-world benchmarks—so you can understand what matters most for your business. If you’re navigating industrial AI or just curious about the future of time series models, this conversation is packed with the insights you need.
Summary
From Sales to Spare Parts - Festo´s AI solutions
Jun 2400:52:52Summary readyHow AI is transforming every step of the industrial customer journey – from first inquiry to predictive maintenance. Discover the future with us. In this episode, we dive deep into how AI is revolutionizing the entire industrial customer journey. We explore how large language models and digital twins are reshaping everything from initial customer inquiries to spare parts management and predictive maintenance. I’m joined by Jan Seyler and Werner Reichelt from Festo, who share firsthand insights on integrating AI with engineering tools, orchestrating multi-agent systems, and bridging the gap between digital sales and real-world manufacturing. Together, we discuss the challenges of interoperability, the evolving role of sales engineers, and the opportunities presented by data-driven automation. If you’re curious about the practical impact of AI on industry, this conversation is packed with real examples and forward-looking ideas. Thanks to our PARTNER NXAI Festo https://www.festo.com/ Mistral AI https://mistral.ai/ DeepSeek https://deepseek.com/ NVIDIA https://www.nvidia.com/en-us/ Automate Show https://www.automateshow.com/ Claude (Anthropic) https://www.anthropic.com/claude Prometheus https://www.prometheus.com/ JKU Linz (Johannes Kepler University Linz) https://www.jku.at/en/ Digital Product Passport https://single-market-economy.ec.europa.eu/sectors/ecodesign/digital-product-passport_en Knowledge Graph https://en.wikipedia.org/wiki/Knowledge_Graph Retrieval-Augmented Generation (RAG) https://www.pinecone.io/learn/retrieval-augmented-generation/ Digital Twin https://en.wikipedia.org/wiki/Digital_twin Predictive Maintenance https://en.wikipedia.org/wiki/Predictive_maintenance
Summary
Industrial AI: From Pilot to Profit
Jun 1700:44:10Summary readyMeet Boris Scharinger and explore the real-world journey of AI in industry. Why expectations must meet reality for true transformation. Our guest is Boris Scharinger from Siemens. He wrote an interesting book "Industrial AI: From Pilot to Profit" and in this episode, we sit down with him. He is a leading voice in industrial AI and we uncover what it really takes to move from flashy AI pilots to solutions that deliver real value on the shop floor and in product engineering. We dig into the challenges of bridging proof-of-concept and production, the unique demands of industrial environments, and why so many initiatives stall before reaching profitability. Our conversation cuts through the hype, sharing candid examples from Siemens Energy and Tesla to illustrate where AI is truly changing the game and where it’s still hitting walls. We also tackle pressing topics like the impact of generative AI on management expectations, the evolving role of process mining, and the tough realities of deploying AI in brownfield versus greenfield environments. If you’re a startup, engineer, or decision-maker looking to understand the real mechanics—and pitfalls—of industrial AI, this episode is your inside track. Join us as we set the record straight on what it takes to turn AI ambition into sustainable success. Order the book here Siemens Energy https://www.siemens-energy.com/global/en.html Tesla Giga Press https://www.tesla.com/blog/gigapress Process Mining https://en.wikipedia.org/wiki/Process_mining Will van der Aalst https://www.vdaalst.com/ Google: Hidden Technical Debt in Machine Learning Systems https://papers.nips.cc/paper/2015/hash/86df7dcfd896fcaf2674f757a2463eba-Abstract.html
Summary
Agile Robots: Building VLAs and World Models
Jun 1000:48:39Tap to summarizeInside the push for adaptable, reasoning robots and the future of physical AI. Discover what’s driving real change in robotics. In this episode, I sit down at the Agile Robots headquarters in Munich with Laurenz von Czettritz to dive deep into the evolving world of robotics and AI. We explore why NVIDIA’s frameworks dominate the industry, what it really takes to build new physical AI solutions, and how foundation models are reshaping automation. Laurenz shares how his team is developing next-generation AI for robotics, from building their own models to tackling unique industrial data challenges. We discuss the obstacles, breakthroughs, and the strategic mindset required to stay ahead in this rapidly changing field. If you’re curious about the real-world journey to smarter, more adaptable robots, this conversation offers a candid look inside the industry’s most ambitious projects.
Transcribe →
AI for the Glass Industry
Jun 300:28:52Summary readyFrom manual chaos to smart automation—inside the future of glass industry workflows. Discover how AI is transforming custom orders. In this episode, I sit down with Georg Katzlinger to explore the surprising complexity of the flat glass industry and the unique challenges it faces. We dive into how AI solutions are revolutionizing the way custom glass orders are processed, from deciphering handwritten requests to integrating with legacy ERP systems. Georg shares his journey from engineering to AI entrepreneurship, revealing why deterministic, human-in-the-loop automation is essential for manufacturers. I ask the tough questions on accuracy, implementation, and industry-specific hurdles, giving you an insider’s perspective on what it takes to bring AI into traditional sectors. If you’re curious about the intersection of deep tech and real-world manufacturing, you won’t want to miss this conversation. #### NXAI Lumeso https://lumeso.com/ Flat Glass Industry https://en.wikipedia.org/wiki/Flat_glass ERP (Enterprise Resource Planning) Systems https://en.wikipedia.org/wiki/Enterpriseresourceplanning OCR (Optical Character Recognition) https://en.wikipedia.org/wiki/Opticalcharacterrecognition LLM (Large Language Models) https://en.wikipedia.org/wiki/Largelanguagemodel SAP https://www.sap.com/ Salesforce https://www.salesforce.com/
Summary
NVIDIA´s Safety Initiative / The unique Volkswagen-Siemens joint venture
May 2701:11:00Summary readyCan cutting-edge AI truly transform factories? We explore real-world challenges, success stories, and the future of intelligent automation. In this episode, we dive deep into the promise and pitfalls of industrial AI with hands-on experts from a unique Volkswagen-Siemens joint venture. We challenge the hype around humanoid robots, discuss the practical impact of AI on factory design and operations, and uncover what truly drives value on the shop floor. Our guests share candid insights on scaling AI solutions, the role of synthetic data, and why safety and trust remain at the core of industrial automation. Join us as we separate fact from fiction and chart the path forward for intelligent manufacturing. If you're curious about the real impact of AI beyond the buzzwords, this conversation is for you. NXAI https://nx-ai.com/ NVIDIA Safety Figure AI https://www.figure.ai/ BMW https://www.bmwgroup.com/ NVIDIA https://www.nvidia.com/en-us/industries/industrial/ SICK AG https://www.sick.com/ OpenAI https://openai.com/ Anthropic https://www.anthropic.com/ Google Gemini https://gemini.google.com/ Coursera https://www.coursera.org/ Andrew Ng https://www.andrewng.org/ Siemens https://new.siemens.com/global/en.html Volkswagen https://www.volkswagenag.com/ inpro https://www.inpro.de/en/ Katena-X https://catena-x.net/en/ Omniverse https://www.nvidia.com/en-us/omniverse/
Summary
Governed Autonomy: Why Edge AI Needs Guardrails
May 2000:53:27Summary readyDiscover how local policy enforcement is reshaping industrial AI safety. What happens when your smart machines lose their connection? In this episode, I sit down with Steven Yates, CTO and co-founder of Federant, to dive deep into the urgent need for runtime governance in edge AI. Drawing on decades of experience in embedded systems and PLC design, Steven reveals why the shift to the edge demands more than just powerful inference—it requires robust, local authority to keep operations safe when connectivity falters. We unpack real-world incidents where lack of governance led to costly mishaps, and explore how new open-source solutions are bridging the gap between cloud convenience and industrial reliability. If you think cloud SLAs are enough for industrial AI, this conversation will make you rethink the fundamentals. Join me as we explore the future of safe, autonomous operations—and why the old rules of industrial control are more relevant than ever. Federant https://federant.com/ EU AI Act https://artificialintelligenceact.eu/ GE Fanuc https://www.geautomation.com/ Intel https://www.intel.com/ Modicon 084 https://en.wikipedia.org/wiki/Programmablelogiccontroller#History Starlink https://www.starlink.com/ Deloitte 'Physical AI: The Moment of Acceleration' https://www2.deloitte.com/global/en/insights/industry/technology/physical-ai.html Edge AI Foundation https://www.edgeaicouncil.org/ Wevolver https://www.wevolver.com/ ADI Engineering https://www.linkedin.com/company/adi-engineering/ IEEE https://www.ieee.org/
Summary