Bridging IT and OT: Real-World Lessons with David & Willem, The IT/OT Insiders! 🚀 Moving beyond initial pilots to scale digital transformation in manufacturing and industrial environments is one of the toughest challenges in IoT today. In this episode of the IoT Show, I'm joined by David Ariëns and Willem van Lammeren to explore what it really takes to bridge the gap between Information Technology (IT) and Operational Technology (OT). Forget the buzzwords—we dive deep into practical frameworks, organizational culture, data architecture, and common cooperation patterns that help teams build solutions that actually last on the shop floor. 📖 Get the Book: David and Willem have distilled years of research and shop-floor experience into a practical guide to IT/OT convergence. Check out The IT/OT Handbook at 👉 https://itotbook.com 💬 We Want to Hear From You! What is the biggest roadblock your team faces when bringing IT and OT together? Is it culture, data silos, legacy infrastructure, or alignment on goals? Drop your thoughts, experiences, or questions in the comments below! 👇 📌 Timestamps: 00:00 - Introduction 01:30 - The Reality of IT/OT Convergence Beyond the Buzzwords 05:15 - The 3-Step Framework: Understand, Cooperate, Scale 10:45 - Navigating Culture & Shop Floor Dynamics 16:20 - Real-World Lessons from The IT/OT Handbook 21:50 - Wrap-up & How to Get Started 🔔 Enjoyed this episode? Don't forget to Like, Subscribe, and hit the notification bell so you never miss an episode of the IoT Show!

Two decades ago, Arduino revolutionized the technology landscape by lowering the barrier of entry for connected smart products. Today, they are aiming to do the exact same thing for the world of Artificial Intelligence. In this episode of the IoT Show, recorded live from IoT Stars at Embedded World 2026 in Nuremberg, Germany, we sit down with Marcello Majonchi from Arduino. Marcello opens up about how the pace of development has accelerated rapidly following Qualcomm's recent acquisition, shifting the company into hyper-drive to build out an end-to-end ecosystem for production-grade Edge AI. We deep-dive into Arduino's major announcement: the Arduino VENTUNO Q. Marcello breaks down how this new hardware seamlessly unifies traditional microcontrollers with powerful CPUs and Neural Processing Units (NPUs) designed to handle high-speed cameras and complex local computing. Despite the massive step up in scale, he explains why the core architectural primitive remains beautifully simple: gathering data from sensors, processing it with a high-performance brain, and executing an action back onto the physical world. Finally, we discuss the ultimate goal of the VENTUNO platform: the democratization of robotics. Discover how Arduino is breaking down the academic barriers that once required multiple PhDs, unlocking a future where everyday makers, developers, and professionals can bring Physical AI to life. Key Topics Covered: - The Shift from Users to Builders: Moving beyond cloud-based workflows (like ChatGPT and Gemini) to enable the creative community to build local AI applications. - The Qualcomm Acceleration: How the broader ecosystem is scaling rapidly to address the growing operational demands of the modern edge. - The Architecture of Arduino VENTUNO Q: Fusing advanced microcontrollers, multi-core CPUs, and specialized NPUs onto a single, cohesive platform. - The Naming Behind VENTUNO: Exploring the story behind the Italian word for "21" and marking Arduino's 21st year since its foundation. - Democratizing Robotics: Abstracting intense technical complexity so that advanced robotics and Physical AI become accessible realities for everyone. Chapters: 01:00:11 - Live from IoT Stars: Catching Up with Marcello from Arduino 01:00:28 - IoT, Edge AI, and the Fast-Moving Post-Qualcomm Acquisition Era 01:01:25 - The Next Frontier: Moving from AI Users to AI Builders 01:02:08 - Lowering the Barriers to Entry Just Like 20 Years Ago 01:02:54 - Introducing Arduino VENTUNO Q: Fusing MCUs and CPUs 01:03:26 - Sensors, Compute, and Action: The Unchanged Architecture Primitive 01:03:50 - Abstracting the Complexity of Modern NPUs and High-Speed Vision 01:04:24 - What’s in a Name? The Meaning Behind "VENTUNO" 01:04:54 - Marcello’s Biggest Passion: The Democratization of Complex Robotics 01:05:34 - Making Physical AI a Reality for Everyone 01:05:43 - Wrap-Up & Closing the Show #IoTShow #Arduino #VENTUNOQ #EdgeAI #EmbeddedWorld #PhysicalAI #Robotics #Qualcomm #Microcontrollers #TechDemocratization #IoTStars

While Edge AI has been heavily discussed for over half a decade, transitioning a concept into mass market deployment remains incredibly complex. In this episode of the IoT Show, recorded live from IoT Stars at Embedded World 2026 in Nuremberg, Germany, we catch up with Sergio Timpretti, VP of Marketing at EBV Elektronik. Sergio shares his front-line perspectives on how the European and global markets are moving past the experimentation phase to see a massive uptake in real-world Edge AI applications. We discuss the key drivers making on-device intelligence a necessity—including strict data privacy for camera sensors, zero-latency local decision-making, and critical low-power energy constraints. Sergio details how EBV Elektronik assists industrial and automotive clients who are experts in their own verticals (such as construction or motor control) but lack deep software development or AI experience. By supplying pre-built hardware, robust Board Support Packages (BSPs), and connecting developers with specialized third-party partners, they help companies overcome the traditional "make vs. buy" hurdle. Finally, we look ahead at what 2026 holds for the market, highlighting why this is the definitive year for industrial computer vision, predictive maintenance, and drone robotics to shift from low-volume prototypes into mass production. Key Topics Covered: - The Drivers of On-Device AI: Evaluating the strict requirements of data privacy, real-time latency, systemic resilience, and optimized power consumption. - Industrial Vision AI Use Cases: How Edge AI is transforming surface quality inspection, drone-based structure checking, and local access control. - The "Make vs. Buy" Dilemma: How organizations can accelerate development using pre-built MPUs and software infrastructure rather than starting from scratch. - Bridging the Expertise Gap: Why traditional industrial companies are partnering with distributors and third-party software experts to fuse complex sensor data. - The 2026 Edge AI Uptake: Why the market is finally mature enough to shift high-volume, production-ready AI applications directly to the streets and factory floors. Chapters: 01:00:12 - Live from Embedded World 2026: IoT Stars in Nuremberg 01:00:23 - Introducing Sergio Timpretti & EBV Elektronik 01:01:10 - Tracking the Surge in Vision AI and Industrial Object Recognition 01:01:53 - Guiding the Customer Journey: The "Make vs. Buy" Equation 01:02:56 - Privacy, Latency, and Power: Why AI is Migrating to the Deep Edge 01:04:22 - Navigating the Hardware Ecosystem and Industrial Complexity 01:05:08 - Real-World Applications: Drone Inspections and Predictive Maintenance 01:07:02 - Cloud vs. Edge: Who is Still Trying to Build it Alone? 01:07:26 - MPU Boards and BSP Infrastructure for Robotics 01:08:05 - What Excites EBV in 2026: Moving from Prototype to True Mass Volumes 01:09:02 - Wrap-Up & Closing Thoughts #IoTShow #EdgeAI #EBVElektronik #EmbeddedWorld #ComputerVision #PredictiveMaintenance #Robotics #IndustrialIoT #EmbeddedSystems #IoTStars

How do you take a brilliant Edge AI prototype and safely deploy it to a fleet of 100,000 devices without drowning in technical debt or failing security compliance? In this episode of the IoT Show, recorded live from IoT Stars at Embedded World, we sit down with George, founder of Foundries.com (now part of the Qualcomm ecosystem). George breaks down the monumental shift from traditional, deterministic embedded code to the variable, data-heavy reality of running Large Language Models (LLMs) and tinyML models directly on edge hardware. We explore the strict requirements of scaling IoT products today, including meeting the stringent regulations of the European Cyber Resilience Act. George explains how Foundries.com addresses these hurdles by separating applications from the core operating system using Docker containers, allowing developers to seamlessly push over-the-air (OTA) firmware, OS, and AI model updates on the fly. Finally, we discuss the intersection of IoT and Physical AI. From smart glasses running live translations to autonomous robotics in factories, discover how the hardware ecosystem is evolving to create secure, intelligent devices capable of safely interacting with the physical world. 🗒️ Key Topics Covered: - The Qualcomm Embedded Ecosystem: How the integrations of Foundries.com, Arduino, and Edge Impulse are creating an end-to-end journey from concept to mass production. - The Non-Deterministic Edge: Navigating the challenges of app size, code variability, and unpredictable behaviors when shifting AI to edge devices. - The Ultimate Latency Test: Why latency-critical applications like automotive safety and live-translation smart glasses simply cannot rely on the cloud for inference. - The App Store for Industrial IoT: Using Docker containers to orchestrate, secure, and update applications independently of the underlying operating system. - Guardrails for Physical AI: Balancing the massive opportunities of autonomous robotics with the need for safety regulations, public oversight, and strict operational rules. Chapters: 01:00:10 - Welcome Back to the IoT Show Live from IoT Stars 01:00:37 - Meet George: From Linaro to Founding Foundries.com 01:01:25 - The Qualcomm Acquisition & The Power of Open Source 01:01:43 - The Arduino & Edge Impulse Partnership: Shifting AI to Production 01:02:08 - Complying with the European Cyber Resilience Act 01:02:34 - Running Full LLMs on Higher-Performance IoT Edge Hardware 01:02:54 - The Core Challenge: Transitioning to Non-Deterministic Edge AI 01:03:12 - Ditching the Cloud: Managing Latency in Automotive & Smart Glasses 01:05:22 - Physical AI, Autonomous Agentic Loops, and Robotics 01:05:55 - Establishing Guardrails: Preventing Robots from "Going Crazy" in the Factory 01:08:16 - The Hardware Fragmentation Problem: IoT vs. Mobile Platforms 01:08:53 - Docker Containers: The "App Store" Model for Industrial Edge Software 01:09:44 - Pushing Continuous Over-the-Air (OTA) Model and Firmware Updates 01:10:08 - Wrap-Up & Setting Up the Final Guest #IoTShow #Qualcomm #EdgeAI #EmbeddedSystems #IoTStars #EmbeddedWorld #FoundriesDotCom #Arduino #EdgeImpulse #CyberResilienceAct #DockerContainers #OTAUpdates

How deep can you actually push intelligence into an edge device before running out of power and memory? In this episode of the IoT Show, recorded live from IoT Stars at Embedded World 2026, we sit down with Fabrizio from STMicroelectronics. Fabrizio shares technical insights into how the relationship between IoT data and AI has completely inverted over the last decade. Instead of simply streaming massive amounts of raw telemetry to feed big models in the cloud, the industry is shifting toward running tiny, ultra-power-efficient models directly on the physical hardware. We take a close look at how STMicroelectronics is enabling this shift through their ST IoT Graph tool—an end-to-end solution designed to program tiny AI models right inside MEMS sensors. Fabrizio explains the strict physics of energy consumption in edge architectures, proving why processing data directly at the sensor layer consumes vastly less power than waking up a microcontroller or transmitting over a radio link. Finally, we explore how distributed architectures are evolving to support Physical AI and Agentic Loops. Discover why the future of robotics and automation won't rely on a single massive "central brain," but rather a network of multiple "tiny brains" collaborating seamlessly across the device. 🗒️ Key Topics Covered: - 10 Years of IoT Evolution: How the conversation has moved from basic cloud connectivity to highly sophisticated Edge AI architectures. - The Power Consumption Pyramid: Why pushing inference to the deepest edge (MEMS sensors) is exponentially more energy-efficient than utilizing microcontrollers, NPUs, or the cloud. - ST IoT Graph: A breakdown of STMicroelectronics' end-to-end tool that enables developers to program tiny AI models directly inside sensors to output clean inferences rather than raw data streams. - Agentic AI Loops at the Edge: The rise of autonomous "observation-reflection-action" loops on embedded hardware and their impact on developer tooling. - The Architecture of Humanoid Robotics: Why modern physical AI relies on a hybrid model combining a central generative engine with distributed intelligence embedded in limbs and endpoints. Chapters: 0:00 - Live from IoT Stars at Embedded World 2026 0:12 - Catching Up: 10 Years of Evolution in IoT and Edge AI 0:51 - IoT is Powering Physical AI: Sensed and Interactive Environments 1:03 - STMicroelectronics Portfolio: Sensors, MCUs, and Connectivity 1:14 - Deep Edge AI: Programming Tiny AI Inside MEMS Sensors 1:47 - Balancing Power and Memory: The Deepest Edge is the Most Efficient 2:06 - Eliminating Data Waste: Why Cloud Providers Don't Want Raw Data 2:34 - Small Language Models (SLMs) and Generative AI at the Edge 2:54 - Agentic Loops: Automation, Device Configuration, and Embedded Logic 3:33 - Central vs. Distributed Intelligence: The "Tiny Brains" Robot Architecture 4:16 - Looking Ahead to 2026: Agentic Efficiencies & Physical AI Transformations 4:57 - Sending My AI Agent Next Year! Wrap-Up and Outro #IoTShow #STMicroelectronics #EdgeAI #TinyML #PhysicalAI #EmbeddedSystems #MEMS #AgenticAI #IoTStars #EmbeddedWorld2026

What does it take to move past the era of failed IoT projects and build something that scales? In this episode of the IoT Show, recorded live at IoT Stars during Embedded World 2026 in Nuremberg, Germany, we sit down with Brandon Satrom, SVP of Product and Experience at Blues. Brandon breaks down how the industry is shifting away from custom, ground-up builds toward modular solution composition using reliable, off-the-shelf components. We dive deep into Blues' mission to solve the "messy middle" of hardware connectivity—ensuring telemetry flows seamlessly from device to cloud without getting bogged down in complex radio layer configurations. Brandon also introduces their massive new product launch: a single module integrating Cellular, Wi-Fi, and NTN Satellite connectivity, allowing the hardware itself to intelligently handle network failover when running at the edge of the internet. Finally, we discuss the evolution of data strategy. Instead of dumping terabytes of unrefined data into cloud data lakes, discover how edge-powered sensors and LLMs are working together to marry raw telemetry with real-world context. 🗒️ Key Topics Covered: - Composing Solutions vs. Building from Scratch: Why modern businesses are succeeding by integrating proven, off-the-shelf hardware building blocks instead of over-engineering custom platforms. - Solving the Messy Middle: How Blues acts as a secure broker for device-to-cloud communication, allowing developers to focus entirely on their sensors, actuators, and core MCUs. - The 3-in-1 Connectivity Breakthrough: A closer look at Blues' newly launched module combining Cellular, Wi-Fi, and NTN Satellite, and why satellite serves as the ultimate failover for remote tracking. - Data Optimization & Edge AI: Why sending terabytes over cellular is a business dead-end, and how edge inference allows devices to send only the critical payloads required to update cloud models. - The Power of Context in 2026: Why LLMs fail without localized context (sensor placement, mounting, environment) and how the industry is bridging the gap between raw data and actionable insights. Chapters: 0:00 - Live from IoT Stars at Embedded World 2026 in Nuremberg 0:21 - Introducing Brandon Satrom and the Mission of Blues 0:54 - The Shift to Hardware Composition and Off-the-Shelf Tech 1:21 - Tackling the "Messy Middle" of Device Connectivity 2:16 - Why IoT Projects are Reaching Maturity and Succeeding in 2026 3:49 - Moving Beyond Dashboards: Making Sense of the Data Lake 5:04 - Optimizing Payloads and Trimming Cellular Data Costs 5:56 - Product Launch: Cellular, Wi-Fi, and NTN Satellite in One Module 6:50 - Smart Hardware: Letting the Module Decide the Best Connection 7:15 - What’s Driving Tech Forward in 2026? Marrying Telemetry with Context 8:18 - Wrap-Up and Thanks for Watching! #IoTShow #EmbeddedWorld2026 #BluesWireless #SatelliteIoT #CellularIoT #EdgeAI #IoTStars #EmbeddedSystems #TechInnovation

What happens when ultra-low-power connectivity converges with high-performance machine learning right on the device? In this episode of the IoT Show, recorded live at IoT Stars, we sit down with Alexis, Chief Product Officer at Edge Impulse. Alexis shares insights from his journey from cloud environments and ultra-low bandwidth systems to leading product strategy at Edge Impulse, particularly following their acquisition by Qualcomm. We discuss how Qualcomm’s developer-first strategy keeps Edge Impulse independent while granting unprecedented access to bleeding-edge chipsets and ecosystem collaborations with partners like Arduino. Alexis also addresses the critical "walls" facing the industry—highlighting security vulnerabilities and the absolute necessity of responsible AI as development accelerates. Finally, we look at the massive evolution from Visual Language Models (VLMs) to Vision Language Action Models (VLAs), charting the clear path forward for robotics, physical AI, and intelligent edge systems that sense, think, and act safely. 🗒️ Key Topics Covered: - Qualcomm & Edge Impulse Integration: How the corporate integration maintains Edge Impulse's core DNA while leveraging massive silicon and engineering resources. - The Major Risk in Rapid Edge AI Adoption: Moving past hype to avoid historical IoT pitfalls like early IP camera hacks by focusing heavily on responsible AI and developer guidance. - The Changing Developer Landscape: Bridging the gap between traditional embedded hardware developers and incoming data scientists/machine learning engineers. - The Evolution of Edge Models: How cascaded models allow low-power Arduino devices to combine vision and small language models for rich local context. - The Rise of Physical AI (VLAs): Why Vision Language Action Models are revolutionizing robotics and enabling safe, predictable, and highly tested machine execution. Chapters: 0:00 - Welcome back to the IoT Show Live from IoT Stars 0:13 - Introducing Alexis, Chief Product Officer at Edge Impulse 0:38 - Qualcomm’s Developer-First Strategy & Edge Impulse Integration 1:34 - Transitioning from Low-Bandwidth Connectivity to Edge AI 2:19 - What Can Go Wrong? Security Risks and Responsible AI 3:13 - The Evolving Developer Community: Embedded vs. Data Science 4:14 - Beyond LLMs: Visual Language Models (VLMs) on Constrained Hardware 4:56 - The Future of Robotics: Vision Language Action Models (VLAs) 5:30 - Outro & What’s Next on the IoT Show #EdgeAI #EdgeImpulse #Qualcomm #PhysicalAI #EmbeddedSystems #VLA #IoTShow #TinyML #Robotics

Are we finally past the "IoT Hype" cycle? Recorded live at **IoT Stars during Embedded World 2026**, this episode of the IoT Show dives into the current reality of the industry. We sit down with industry veteran Ken Yu to discuss why 2026 is seeing a massive uptick in massive-scale deployments and how the developer's role is evolving. We move beyond simple data collection to discuss the necessity of edge AI in transforming raw sensor data into meaningful industrial actions. If you are a developer struggling to demonstrate the value of your IoT solution, this conversation explores why "dashboards and numbers" are no longer enough. 🗒️ Key Topics Covered: - The 2026 Momentum: Why massive deployments (reaching millions of devices) are finally becoming a reality in sectors like livestock monitoring and emergency safety. - The Edge AI Value Add: How AI is being used to analyze data locally, providing the "insightful actions" that industries actually need. - Hardware vs. Software: Navigating the unique challenges of hardware validation and changing customer behavior in the field. - Build vs. Buy: When developers should build custom hardware and when to leverage third-party solutions to solve common use cases. 🎙️ Live from Nuremberg: This conversation was captured during the IoT Stars event, bringing you the latest energy and insights directly from one of the industry's premier gatherings for IoT innovators. Chapters: 0:00 - Live from Embedded World 2026 0:26 - Introduction: Ken Yu and the 2026 IoT Landscape 1:10 - Is IoT Finally Taking Off? Current Momentum and Scale 1:46 - The Hardware Challenge: Why it’s harder than software 2:06 - Why Data is Useless Without AI for Analysis 2:54 - Build vs. Aggregate: Strategies for Solution Builders 4:00 - The Future of Edge AI and Industry Trends 5:15 - Closing Thoughts from IoT Stars

Are developers getting caught up in the AI hype, or is there a real-world path to running intelligence on constrained, battery-powered devices? In this episode of the IoT Show, recorded live at **IoT Stars during Embedded World 2026**, we sit down with Wienke Giezeman, CEO and co-founder of The Things Industries. Wienke shares invaluable, unfiltered perspectives gained over 11 years in the developer ecosystem, moving past investor buzzwords to look at what enterprises actually need. We dive into the technical intersection of LoRaWAN and TinyML/Edge AI. While you can't push massive model updates over low-bandwidth networks, low-power silicon innovations are opening doors for local inference (like audio or basic image processing) directly at the ultra-edge—allowing battery-operated devices to last for years while sending smart, event-driven notifications. Finally, Wienke gives us a teaser of his brutally honest IoT Stars talk on the grit required to build a scaling SaaS company by ignoring vanity metrics and listening to the raw truth from your users. 🗒️ Key Topics Covered: - LoRaWAN vs. 5G/Cellular: Why enterprise IoT thrives on long-distance, low-power networks when concrete walls and total operation costs break cellular options. - Edge AI on Tiny Devices: The rise of low-power MCU AI chips (Inatera, Brainchip, Alif, Efficient Computer) capable of running local inference without draining batteries. - Bandwidth Realities: Navigating the technical boundaries—why over-the-air ML model updates are too heavy for LoRaWAN, and why a "mature enough" fixed model is often all you need. - The "Hype Spectrum": Balancing bleeding-edge technology with legacy enterprise clients who still need foundational logic before adopting AI. - Grit in the IoT Market: Lessons from a 10-year journey focused strictly on user utility rather than investor expectations. Chapters: 0:00 - Live from IoT Stars Nuremberg 2026 0:26 - Introduction: Wienke Giezeman and The Things Industries 1:20 - The Enterprise Reality: LoRaWAN vs. Ubiquitous 5G 2:43 - Low-Cost Scaling: Lowering the Barrier to Industrialized IoT 3:04 - Private Networks vs. Public Infrastructure 3:35 - Can Ultra-Low Power Devices Handle Edge AI? 4:07 - Meeting the Enterprise Where They Are (Moving Past the Hype) 4:56 - Smart Filtering: Audio and Image Recognition on the Battery Edge 5:40 - Teaser: "Don't Piss on Me and Tell Me It's Raining" (Lessons on Grit) 7:15 - Market Momentum: Steady Growth vs. Shiny Objects