Industry40.tv

Kudzai Manditereza
  • 5.0 (1)
  • TECHNOLOGY
  • UPDATED BIWEEKLY

Each episode of Industry40.tv Podcast will treat you to an in-depth interview with leading AI practitioners, exploring the Application of Artificial Intelligence in Manufacturing and offering practical guidance for successful implementation.

  1. 3D AGO

    Reducing Waste and Improving Efficiency with Multi-Agent Quality Control in Manufacturing: Wilhelm Klein - Co-Founder & CEO , Zetamotion

    # AI in Manufacturing Podcast — Show Notes   ## Episode: How to Reduce Waste and Improve Efficiency with AI-Powered Quality Control   **Podcast Name:** AI in Manufacturing Podcast (Industry 4.0 TV) **Episode Title:** How to Reduce Waste and Improve Efficiency with AI-Powered Quality Control **Guest:** Willem Klein, CEO & Co-Founder, Zetamotion **Host:** Kudzai Manditereza **Target Audience:** Manufacturing data leaders, IT/OT solution architects, quality control professionals, and digital transformation leaders implementing AI in industrial operations   ---   ## 1. Episode Summary This episode explores how AI-powered quality control can reduce waste and improve efficiency in manufacturing, featuring Willem Klein, CEO and co-founder of Zetamotion. Willem shares why over 90% of industrial AI pilots fail and explains that the real competitive advantage lies not in building bigger AI models, but in designing better end-to-end systems that integrate seamlessly into existing production environments. He introduces Zelia, Zetamotion's AI-powered inspection assistant that reduces model training from weeks of manual data labeling to under an hour using synthetic data and as few as five sample images. The conversation covers the tension between governance and grassroots innovation ("shadow AI"), why manufacturers overwhelmingly prefer edge deployment for quality control data, and why scaling AI across plants is far harder than leadership expects. Willem also shares his vision for fully autonomous inspection systems that configure both software and hardware. Listeners will gain practical insight into what separates successful AI quality control deployments from the 90% that fail.   ---   ## 2. Key Questions Answered in This Episode   - Why do over 90% of industrial AI pilots fail, and what do the successful ones have in common? - What is the difference between a model-centric and system-level approach to AI quality control? - How can manufacturers deploy AI-powered visual inspection without needing an in-house data science team? - What is synthetic data, and how does it reduce the time and cost of training machine vision models? - How should manufacturing leaders balance AI governance with grassroots innovation on the shop floor? - Why do manufacturers prefer edge deployment over cloud for AI-based quality control? - What makes scaling AI quality control across multiple plants and production lines so difficult?   ---   ## 3. Episode Highlights with Timestamps   - **[0:00]** — **Introduction** — Host Kudzai Manditereza introduces the topic of AI-powered quality control and guest Willem Klein of Zetamotion. - **[1:00]** — **Willem's unconventional background** — From Star Trek and the Chaos Computer Club to a PhD in philosophy of technology and technology ethics. - **[5:01]** — **Where Zetamotion fits in the AI landscape** — Willem traces AI history from Turing to the "GPT moment" and explains why most industrial AI pilots fail (90%+ failure rate per MIT study). - **[11:06]** — **The "dark number" of shadow AI projects** — Unsanctioned grassroots AI projects by savvy factory workers signal the importance of empowering domain experts. - **[14:48]** — **Governance vs. flexibility: A virtue ethics approach** — Willem argues for educating engineers and granting reasonable freedom rather than imposing rigid rules. - **[18:08]** — **System-level thinking over model obsession** — Why the best AI model is worthless if the surrounding system is clunky and unusable for operators. - **[21:44]** — **Introducing Zelia** — Zetamotion's AI inspection assistant that uses synthetic data to go from five sample images to a trained model in under an hour. - **[28:27]** — **The full vision for Zelia** — Autonomous end-to-end inspection solution building, including custom dashboards, API connectors, and deployment architecture. - **[33:13]** — **Human-in-the-loop and the "supercharged magnifying glass"** — Why human expertise remains essential for edge cases and continuous improvement. - **[33:46]** — **Time savings: From 100,000 labeled images to five samples** — A glass manufacturing example illustrating weeks or months of saved manpower. - **[35:51]** — **Edge vs. cloud deployment** — Why manufacturers treat QC data as highly sensitive and overwhelmingly prefer on-premise edge solutions. - **[38:10]** — **Scaling challenges across plants** — No two production lines are the same, even when running the same product, and why copy-paste deployment doesn't work. - **[42:44]** — **Future vision: From inspection to physical AI** — Expanding Zelia beyond defect detection toward fully autonomous systems that configure their own hardware.   ---   ## 4. Key Takeaways   - **System-level design beats model performance:** A highly accurate AI model that creates more work for operators than manual inspection will collect dust. Successful AI quality control requires optimizing the entire workflow — UI, integration, reporting, and operator experience — not just the model.   - **Synthetic data dramatically reduces deployment time:** Traditional machine vision projects require collecting and labeling tens of thousands of images over weeks or months. Zetamotion's approach with Zelia requires as few as five good samples and five defect examples per category, achieving alignment in under an hour.   - **Shadow AI signals opportunity, not just risk:** Unsanctioned AI projects by factory workers indicate high-caliber talent and real inefficiencies worth solving. Leaders should channel this energy with reasonable guidelines rather than suppress it with rigid prohibitions.   - **Edge deployment is non-negotiable for most manufacturers:** Quality control data reveals intimate details about product defects and production parameters. Most manufacturers consider this highly sensitive and strongly prefer on-premise edge solutions over cloud-connected systems.   - **Scaling across plants requires contextual adaptation:** No two production lines are identical, even when running the same product. Differences in equipment age, operating parameters, and environmental conditions mean AI models cannot simply be copied from one site to another without intelligent fine-tuning.   - **Democratization is the key unlock:** The biggest barrier to AI adoption in manufacturing isn't model capability — it's accessibility. Giving domain experts tools they can use without AI expertise (similar to how ChatGPT democratized LLMs) is where the real transformation happens.   - **Human-in-the-loop remains essential:** In quality control, novel defects and edge cases appear constantly. AI works best as a "supercharged magnifying glass" that directs human attention to where expertise is needed, with human feedback continuously improving the system.   ---   ## 5. Notable Quotes   > "Think of it not like a robot walking into your factory telling everyone to go home, but rather handing your best people a supercharged magnifying glass that draws their attention exactly where they need to apply their human expertise." — Willem Klein, CEO & Co-Founder, Zetamotion   > "What good is a model if you cannot situate it into the larger context where its performance can actually do very well?" — Willem Klein, CEO & Co-Founder, Zetamotion   > "The better your people, the higher your risk of shadow AI projects happening — because people see inefficiencies and they want to solve them." — Willem Klein, CEO & Co-Founder, Zetamotion   > "Nobody wants to have anyone have full scans of their products including all of the defects and QC parameters. It's like looking into someone's drawers — you see the skeletons in the closet." — Willem Klein, CEO & Co-Founder, Zetamotion   > "We're talking about weeks or months of manpower that can easily be saved by only having to show a couple of examples and defect images." — Willem Klein, CEO & Co-Founder, Zetamotion   ---   ## 6. Key Concepts Explained   **Synthetic Data (for Machine Vision)** Definition: Synthetic data is artificially generated training data created by AI systems to simulate real-world images, eliminating the need to manually collect and label thousands of physical samples. Why it matters: It removes the biggest bottleneck in deploying AI quality control — the months-long process of collecting, labeling, and curating training datasets. Episode context: Willem explained that Zelia uses synthetic data to go from five sample images to a fully trained inspection model in under an hour, compared to traditional approaches requiring 100,000+ hand-labeled images.   **Human-in-the-Loop (HITL)** Definition: A system design approach where AI handles routine tasks autonomously but routes edge cases, novel situations, and final decisions to human operators for judgment and feedback. Why it matters: In manufacturing quality control, new defect types and contamination scenarios appear constantly, making pure automation unreliable without human oversight. Episode context: Willem described Zetamotion's current deployment model as human-in-the-loop, where AI directs operator attention to areas requiring expertise, and human feedback continuously improves the system.

    49 min

  2. FEB 19

    A Guide to Implementing AI Agents in Factories: James Zhang - Co-Founder & CPO , OpsMate AI

    Episode Title:** Practical Guidance for Implementing Industrial AI Agents in Manufacturing Guest:** James Zheng, Co-Founder & Chief Product Officer, Optimate AI Host:** Kudzai Manditereza --- ## 1. Episode Summary This episode explores how agentic AI is creating a new category of digital skilled workers for manufacturing, addressing the industry's deepening productivity plateau and skilled labor crisis. James Zheng, Co-Founder and Chief Product Officer of Optimate AI, draws on over a decade of experience building and deploying manufacturing software — from SAP's cloud ERP to PTC's ThingWorx IoT platform — to explain why traditional digital transformation investments have failed to move the productivity needle. Zheng introduces the concept of a "decision intelligence and execution layer" that sits on top of existing systems of record (MES, ERP, CMMS, SCADA) to orchestrate AI agents that augment engineers, technicians, and frontline leaders. The conversation covers practical adoption patterns, the critical role of knowledge graphs and context graphs, why perfect data isn't a prerequisite for getting started, and real-world use cases in automotive and discrete manufacturing. Listeners will walk away with a clear framework for identifying, prioritizing, and scaling agentic AI use cases on the shop floor. --- ## 2. Key Questions Answered in This Episode - What is agentic AI and why should manufacturers care about it now? - What is the skilled labor crisis in manufacturing and how does agentic AI address it? - What is the difference between a knowledge graph and a context graph in industrial AI? - How should manufacturers approach data readiness for AI agent deployment — do you need perfect data? - What are the best first use cases for AI agents on the factory floor? - How does a decision intelligence layer differ from adding a copilot to existing manufacturing software? - How should manufacturing leaders balance top-down AI governance with bottom-up frontline innovation? --- ## 3. Episode Highlights with Timestamps **[0:54]** — **James Zheng's career journey** — From mechanical engineering to SAP, PTC ThingWorx, and founding Optimate AI, tracing the evolution of manufacturing software. **[3:53]** — **Why generative and agentic AI is different** — Zheng explains why this technology finally solves the problem he's spent his entire career pursuing. **[4:38]** — **The manufacturing productivity plateau** — US BLS data shows total factor productivity in manufacturing declined from 2008–2023 despite massive technology investment. **[8:50]** — **The skilled labor crisis defined** — Zheng explains how skilled workers (10% of cost but the most critical factor) are the true bottleneck, not capital or technology. **[11:46]** — **Two ways to apply agentic AI** — Adding copilots to existing tools vs. creating a new decision intelligence and execution layer that mimics how humans actually work. **[18:18]** — **Adoption patterns from other industries** — The progression from question-answering to task automation to autonomous workflows, applied to factory settings. **[24:07]** — **Data readiness: you don't need perfect data** — Why AI agents with reasoning capabilities can handle messy data, unlike legacy machine learning approaches. **[30:56]** — **Knowledge graphs vs. context graphs explained** — A detailed analogy breaking down the "what, where, who" (knowledge graph) from the "how and why" (context graph). **[37:41]** — **Optimate AI platform architecture** — Three layers: Factory Brain (knowledge graph), Agent Scaffolding (orchestration), and codified industry best practices. **[47:59]** — **Real-world customer use cases** — Automotive tier manufacturers reducing material loss and discrete manufacturers cutting cycle times by coaching frontline workers. **[53:28]** — **Advice for manufacturing leaders** — Embrace both top-down governance and bottom-up innovation by putting AI tools directly in frontline workers' hands. --- ## 4. Key Takeaways - **The productivity plateau is a people problem, not a technology problem:** Despite massive investments in IoT, machine learning, and automation from 2008–2023, US manufacturing productivity has stagnated or declined. The limiting factor is skilled labor — the engineers, technicians, and frontline leaders who represent only 10–20% of costs but determine quality, safety, and efficiency. - **Agentic AI creates a new abstraction layer, not a replacement for existing systems:** MES, ERP, CMMS, and SCADA systems remain as systems of record. AI agents sit on top as a "decision intelligence and execution layer" that uses these legacy systems as tools — just as a human worker would — rather than replacing them. - **Start with information access, then progress to task automation:** The most immediate value comes from giving frontline workers a single natural-language interface to find information across siloed systems, potentially saving one hour per person per shift. From there, automate non-value-added tasks like closing work orders before tackling complex autonomous workflows. - **Perfect data is not a prerequisite for AI agent deployment:** Unlike legacy machine learning that required clean, structured data, large language model-powered AI agents can reason through messy data. The real bottleneck is knowledge — specifically procedural and tribal knowledge — not data quality. - **Context graphs capture decision traces, not just static knowledge:** While knowledge graphs store the "what, where, and who," context graphs track the step-by-step reasoning and decision-making process. This decision trace becomes the foundation for self-learning AI systems that improve over time. - **Frontline workers must be the makers, not just users, of AI agents:** Because every factory, line, and shift presents unique problems, standardized playbooks from other domains don't transfer directly. The people doing the daily work need tools to build and customize their own AI agents. - **This technology wave has unprecedented bottom-up pull:** Unlike ERP or MES implementations that were top-down management systems, agentic AI delivers direct individual productivity gains, creating demand from frontline workers who already use ChatGPT in their personal lives. --- ## 5. Notable Quotes > "If you and I don't need perfect data to make a decision and take action, the AI agent does not need it either." — James Zheng, Co-Founder & CPO at Optimate AI > "Through my whole career, I have never seen a technology with this pull — not only from the top but also from the bottom of organizations." — James Zheng, Co-Founder & CPO at Optimate AI > "The bottleneck is not about data today. The bottleneck is more about knowledge." — James Zheng, Co-Founder & CPO at Optimate AI > "The existing software will be there forever. But the value is moving up to this next layer. The current layer will become just another tool — for the AI agent." — James Zheng, Co-Founder & CPO at Optimate AI > "Put the tools into the hands of your frontline team, let them explore. That's usually where magic will happen." — James Zheng, Co-Founder & CPO at Optimate AI --- ## 6. Key Concepts Explained **Skilled Labor Crisis** Definition: A term describing the critical shortage of experienced engineers, technicians, frontline leaders, and CI specialists in manufacturing — the knowledge workers who drive quality, safety, efficiency, and delivery decisions on the shop floor. Why it matters: This workforce segment represents only 10–20% of factory costs but is the primary limiting factor behind the manufacturing productivity plateau. Episode context: Zheng identifies this crisis (a term coined by Gene Farley, CEO of Pault) as the core problem agentic AI is uniquely positioned to solve. **Decision Intelligence and Execution Layer** Definition: A new software abstraction layer that sits on top of existing systems of record (MES, ERP, CMMS, SCADA) and systems of intelligence (IoT platforms, dashboards) to augment human decision-making and automate knowledge work through AI agents. Why it matters: It represents a paradigm shift from giving workers more dashboards to providing AI-powered digital teammates that reason, act, and learn. Episode context: Zheng positions this as the third generation of manufacturing software — after data collection (system of record) and data visualization (system of intelligence). **Context Graph** Definition: A data structure that captures the step-by-step decision trace of how and why decisions were made during problem-solving processes like troubleshooting, recording the reasoning path, hypothesis validation, and corrective actions taken. Why it matters: Context graphs enable AI agents to learn from past decisions and generate

    58 min

  3. FEB 3

    Building a Data Foundation for AI-Native Industrial Intelligence: Craig Scott - Founder & CEO , Fuuz

    1. EPISODE SUMMARY This episode explores why most manufacturing AI initiatives fail and what companies must do to build a foundation for AI-native industrial intelligence. Craig Scott, Founder and CEO of Fuuz, an industrial intelligence platform, shares insights from nearly a decade of bridging the gap between shop floor data and enterprise systems. The conversation reveals why the missing "shim" between operational technology and enterprise systems is the root cause of unreliable data in manufacturing, and why model-driven approaches are essential for scaling AI across industrial operations. Craig explains how organizations can achieve a single source of truth by implementing a persistent contextualization layer that governs data before AI ever touches it. Whether you're struggling with fragmented point solutions, evaluating industrial data platforms, or preparing your data infrastructure for AI, this episode provides a practical framework for building scalable industrial intelligence. 2. KEY QUESTIONS ANSWERED IN THIS EPISODE What is fundamentally broken with current manufacturing data infrastructure and how does it impact AI initiatives? Why do most AI pilots fail to scale in manufacturing environments? What is a model-driven approach to industrial data, and why is it superior to in-line data transformation? How do you balance enterprise governance with plant-level flexibility in industrial data architectures? Should manufacturers adopt industry-standard data models like ISA-95 or build custom models? What is the difference between a data lake and an operational intelligence platform? How can manufacturers prepare their data foundation before investing in AI technologies? 3. EPISODE HIGHLIGHTS WITH TIMESTAMPS [0:00] - Introduction — Craig Scott's background from hands-on manufacturing at age 15 to founding Fuuz, and why the company's purple branding represents the merger of "red" (OT) and "blue" (IT) data. [6:56] - What's Fundamentally Broken — Discussion of how critical manufacturing knowledge is leaving the business as the workforce ages, and why data-driven approaches are essential to capture and retain institutional knowledge. [8:09] - The Missing Shim Problem — Craig explains the gap between real-time shop floor data (SCADA/historians) and enterprise systems (ERP/PLM), and why neither system alone provides a single source of truth. [16:20] - MCP and I3x Integration — How Fuuz is implementing Model Context Protocol and aligning with the I3x initiative for standardized GraphQL APIs to enable AI connectivity. [18:52] - Model-Driven vs. In-Line Transformation — Why data transformation tools that reshape data in motion create scaling challenges, and how persistent data models solve enterprise-wide consistency. [24:06] - AI Governance and Hallucination Prevention — Why deterministic data models are essential for trustworthy AI—Claude can't "make up" OEE numbers when the data graph dictates values. [28:41] - Custom vs. Standard Data Models — Discussion of when to use ISA-95 accelerators versus custom models, using an automotive OEM wall-to-wall deployment as an example. [33:46] - Red and Blue Namespace Architecture — How Fuuz balances enterprise governance with plant-level flexibility through extensible tenant-based data models. [37:28] - What Category is Fuuz? — Craig explains how the platform spans MES, WMS, data ops, and application development—an operational intelligence layer, not a data lake. [47:13] - Technical Architecture Deep Dive — Overview of Kubernetes backend, Node.js framework, RabbitMQ messaging, MongoDB with custom ORM, and the hybrid gateway for edge connectivity. [51:16] - Real-World Deployments — Case studies including an automotive OEM running an entire car plant on Fuuz, Highbar Steel's solar-powered green steel mill, and PepsiCo co-packer integrations. [53:52] - Advice for Getting Started — Craig's recommendation to define the problem first, assemble cross-functional IT/OT teams, and start small with the understanding that small problems often expose bigger ones. 4. KEY TAKEAWAYS The "shim" between shop floor and enterprise is the missing piece: ERP and PLM systems are only accurate for the first 15 minutes after data entry. Without a real-time contextualization layer synchronizing shop floor and enterprise data, there is no true single source of truth. Model-driven persistence beats in-line transformation for scale: While edge tools that transform data in motion work for one or two sites, they require re-implementation across every site and system. A persistent data model is defined once and becomes the consistent interface for all enterprise systems. AI governance requires deterministic data models: LLMs cannot reliably do math and will hallucinate if given unstructured data. By forcing AI to read from governed data graphs, organizations can move toward semi-autonomous and eventually autonomous operations with trustworthy outputs. Extensible models balance governance and flexibility: Enterprise IT can define governed core models while individual plants extend them with additional metadata—they can add context but cannot change underlying structures, preserving data integrity while enabling local adaptation. Operational intelligence is not the same as a data lake: Data lakes are good for reporting and analytics but don't help run real-time operations. An operational intelligence platform provides both persistent contextualized state and real-time event streaming for actual operational execution. Start with the problem, not the technology: Many companies approach vendors saying they "need an MES" without understanding why. Defining value drivers first allows solutions to start small and expand as bigger problems reveal themselves. Build tools that enable AI, don't rely on AI as the platform: LLMs are evolving rapidly and may be replaced by new model architectures. Building platforms around deterministic data foundations protects against technical debt from betting on novel technologies. 5. NOTABLE QUOTES "There's a reason why our color is purple, because if you mix red and blue together, it makes purple. We are the part that's in between—the highly structured enterprise data like ERP and PLM and the really unstructured data that's happening on the plant floor." — Craig Scott, CEO at Fuuz "The ERP is a good source of truth for like the first 15 minutes that the data goes into the system, and then immediately, when you start generating real time data from the shop floor, it's out of date. Nothing is in sync anymore." — Craig Scott, CEO at Fuuz "When I connect Claude to Fuuz, Claude can't make anything up. It can't imagine an OEE for my line or my machine because it's being dictated by our data graph." — Craig Scott, CEO at Fuuz "I still look at AI as a tool, and I don't know that we're ready to acknowledge AI as the platform yet. We want to build tools and platforms that enable the technology, not rely on the new technology to be our platform." — Craig Scott, CEO at Fuuz "Data is money, and if we can turn that data into actionable insights, now we can make more money for your business." — Craig Scott, CEO at Fuuz 6. KEY CONCEPTS EXPLAINED Industrial Intelligence Platform Definition: A software layer that sits between operational technology (SCADA, historians, PLCs) and enterprise systems (ERP, PLM, CRM) to provide real-time data contextualization, persistence, and governance. Why it matters: Traditional architectures leave a gap between shop floor data and business systems, causing data inconsistency and preventing AI from accessing trustworthy operational information. Episode context: Craig describes Fuuz as the "shim" or "purple" layer that bridges red (OT) and blue (IT) data, enabling real-time synchronization and a true single source of truth. Model-Driven Architecture Definition: An approach where data models are defined first as persistent, governed structures, and all systems read from and write to this single canonical model rather than transforming data in-line during transit. Why it matters: In-line transformation tools work for small deployments but require re-implementation at every site. Model-driven persistence enables "once and done" enterprise-wide data consistency. Episode context: Craig contrasted this with edge tools that reshape data in motion, explaining that persistent models scale across global enterprises with multiple ERPs and systems. Unified Namespace (UNS) Definition: An architectural pattern that provides a single, hierarchical structure for all operational data, making it accessible to any system that needs it. Why it matters: UNS is gaining adoption as a way to democratize data access, but without persistent contextualized state, it only provides current values—not the historical context needed for operations and AI. Episode context: Craig acknowledged UNS as a great concept but emphasized that operational intelligence requires persistent state of contextualized data, not just real-time streaming. Model Context Protocol (MCP) Definition: A protocol that enables AI systems to connect to and understand data from external platforms through standardized interfaces. Why it matters: MCP allows AI tools like Claude to access governed industrial data without requiring custom integrations or exposing companies to AI hallucination risks. Episode context: Fuuz added MCP capability to expose their data graph to AI systems, ensuring AI outputs are governed by deterministic data rather than generating unreliable information. I3x Initiative Definition: An industry initiative working on standardized GraphQL APIs for industrial data exchange, enabling interoperability between industrial systems. Why it matters: Standardized APIs reduce integration complexity and allow best-of-breed systems to share data through common interfaces. Episode context: Craig mentioned Fuuz has be

    57 min

  4. JAN 22

    Driving Operational Excellence in Manufacturing with Practical AI: Mickey Shaposhnik - Founder & CEO , Next Plus

    Traditional MES platforms were built for a manufacturing world that no longer exists. They assume stable product lines. They assume you have time for lengthy implementations, tolerance for complexity, and operators who can navigate digital forms while running production.   But here's the challenge. Today's manufacturing reality is different: ⇨ Markets demand the flexibility to shift from 1.5-liter bottles to 1-liter bottles overnight ⇨ Low volume, high mix production is now the norm ⇨ Tribal knowledge is retiring faster than it's being captured ⇨ Workers stay 2-3 years, not 20, making traditional training models obsolete   The cost of this disconnect? ❌ Frontline workforce unable to contribute operational intelligence at scale ❌ ROI delayed by complexity, not capability ❌ Two-year deployment cycles for basic systems ❌ Digital initiatives stuck in pilot purgatory   That's why leading manufacturers are rethinking execution from the ground up, shifting from monolithic systems to AI-native, human-centric platforms built for today's workforce reality.   This new approach is effective because it’s built with an AI-native mindset, not a digitized version of paper-based processes   ✅ AI-generated SOPs from video, cutting engineering time by 80% ✅ Learning systems that surface troubleshooting guidance from historical fault data ✅ Human-centric design that captures operational intelligence without disrupting workflows ✅ AI-powered interfaces that enable natural interaction; think voice, not dropdowns ✅ Rapid deployment measured in weeks ✅ Scalable without complexity; connect thousands of machines without lengthy integrations   The companies winning today aren’t planning more; they’re executing faster and adapting continuously.   In this episode of the AI in Manufacturing podcast, I speak with Mickey Shaposhnik, Founder and CEO of Next Plus, about how practical, AI-powered frontline execution is redefining operational excellence.   Watch/Listen now

    44 min

  5. 10/22/2025

    Agentic AI Framework for Manufacturing Operations: Gilad Langer - Head of Digital Manufacturing Practice, Tulip Interfaces

    Agentic AI Framework for Manufacturing Operations AI in Manufacturing Podcast Show Notes Episode Guest: Gilad Langer, Head of Digital Transformation Practice at Tulip Interfaces Host: Kudzai Manditereza Publication Date: [Insert Date] Episode Summary Manufacturing systems are complex adaptive systems that require a fundamentally different approach to AI implementation than traditional monolithic architectures. In this episode, Gilad Langer draws on 30 years of manufacturing experience—including PhD research that laid the groundwork for Industry 4.0—to introduce a composable agentic framework specifically designed for frontline operations. He explains why adaptability has become a competitive necessity in today's disrupted markets and how multi-agent systems can transform innate factory equipment into intelligent, communicating entities. The conversation covers practical implementation strategies, the artifact model for structuring manufacturing data, and why cultural change remains the biggest obstacle to agentic AI adoption. Key Questions Answered in This Episode What is an agentic AI framework for manufacturing and why do factories need one? How do complex adaptive systems apply to manufacturing operations? What are the five pillars of composability in manufacturing? How should manufacturers structure their data for AI agents using the artifact model? What is the difference between staff agents, builder agents, and artifact agents? How do you implement agentic AI in a brownfield manufacturing facility? Why do traditional MES systems fail to deliver the adaptability modern manufacturing requires? Episode Highlights with Timestamps [0:00] — Introduction — Kudzai introduces Gilad Langer and previews the discussion on composable agentic frameworks for frontline operations. [1:19] — Gilad's Background — Gilad shares his 30-year manufacturing journey, including PhD research in the 1990s that anticipated Industry 4.0 concepts like IIoT and multi-agent systems. [6:58] — The Vision Realized — Discussion of how today's technology finally enables the adaptive manufacturing concepts envisioned decades ago. [7:49] — Why Adaptability is Now Essential — Gilad explains how tariffs, supply chain disruptions, and COVID have made manufacturing adaptability a competitive necessity, not just an aspiration. [14:10] — Complex Adaptive Systems Explained — Deep dive into how manufacturing systems share characteristics with traffic and weather patterns, including the concept of attractors and emergence. [15:38] — The Toyota System Connection — Gilad explains how Toyota understood complex adaptive systems and used lean methods to keep manufacturing in the "orderly space." [26:21] — The Danger of Uncontrolled Agents — Discussion of how agents without proper frameworks can cause catastrophic "butterfly effects" in manufacturing operations. [28:19] — Agent Taxonomy Introduction — Gilad walks through the four types of agents: staff helpers, builder agents, operational agents, and artifact agents. [35:06] — Agents as Digital Twins — Why each discrete item should have its own agent rather than one agent controlling multiple machines. [40:20] — The Artifact Model Explained — Comprehensive breakdown of how to structure manufacturing data using physical and operational artifacts. [51:07] — Implementation Strategy — Practical guidance on starting small with agentic AI, beginning with a single machine and growing from there. [57:15] — Tulip Platform Overview — How Tulip's no-code frontline operations platform enables composable agentic manufacturing. [1:00:46] — The Composability Test — How to determine if your implementation is truly composable: can you solve a problem within an hour? Key Takeaways Manufacturing systems are complex adaptive systems that require emergent, bottoms-up approaches. Traditional blueprint-based implementations lock organizations into rigid structures. Truly adaptive manufacturing systems mimic natural phenomena—like plants growing toward sunlight—by solving problems iteratively and adapting to obstacles without predetermined plans. The five pillars of composability provide a framework for evaluating any manufacturing technology. Ask whether a platform supports bottoms-up development, lean improvement, democratized access, human-centric design, and compliance requirements. If a technology fails any of these tests, it cannot deliver true composability. Agents can either help humans or bring innate objects to life. Staff agents assist workers with tasks like monitoring and scheduling. Artifact agents wrap physical equipment with intelligence, enabling machines, materials, and systems to communicate with each other and with humans. The artifact model simplifies manufacturing data into physical and operational categories. Physical artifacts include machines, tools, areas, and materials. Operational artifacts include orders, tasks, defects, and events. Most manufacturing plants have no more than ten distinct physical artifact types, making the data model inherently human-comprehensible. Per-artifact agents deliver true adaptability that hierarchical approaches cannot match. When one agent fails in a distributed system, the others adapt and continue operating. A single controlling agent creates a single point of failure that can bring down entire operations. Start small with agentic AI implementation. Pick one critical piece of equipment, add sensors, create a simple agent, and let operators interact with it. Scale gradually while building governance frameworks alongside the technology. Cultural change is the biggest obstacle to agentic manufacturing adoption. Engineers trained in monolithic thinking will naturally gravitate toward building rigid systems even when given composable tools. Organizations need change agents who maintain discipline around composable principles. Notable Quotes "It's not the most intelligent of the species that survives. It's the species that is most adaptable to change that survives—that thrives." — Gilad Langer, referencing Darwin's principle as applied to manufacturing "If you push the system, if you take out the slack, highly likely there's going to be a traffic jam. And it's the same thing in manufacturing." — Gilad Langer, on why pull-based systems outperform push-based systems "If it takes months or more to connect a machine and create an agent, you don't have a composable system. The answer should be hours." — Gilad Langer, on the composability test "We run manufacturing like that. As soon as an event we didn't expect happens, we just sit there and burn alive. Essentially, that's what we do." — Gilad Langer, on the limitations of blueprint-based manufacturing systems Key Concepts Explained Complex Adaptive Systems Definition: A class of systems composed of discrete entities that exhibit emergent behavior and patterns without centralized control—including traffic, weather, and manufacturing operations. Why it matters: Understanding manufacturing as a complex adaptive system reveals why traditional rigid architectures fail and why multi-agent approaches succeed. Episode context: Gilad uses examples of traffic patterns and weather prediction to illustrate how patterns emerge in chaotic systems and how Toyota's lean methods leverage these dynamics. Composability Definition: An architectural approach built on five pillars—bottoms-up development, lean thinking, democratization, human-centricity, and compliance—that enables systems to adapt continuously rather than requiring upfront blueprints. Why it matters: Composable systems can respond to market disruptions, supply chain changes, and unexpected events without costly re-engineering. Episode context: Gilad contrasts composable platforms with traditional MES implementations that "lock you in a prison" through rigid blueprints and design reviews. Artifact Model Definition: A simplified data structure that categorizes manufacturing elements into physical artifacts (machines, tools, materials, areas) and operational artifacts (orders, tasks, defects, events), typically resulting in no more than ten distinct artifact types per facility. Why it matters: The artifact model makes manufacturing data human-comprehensible and AI-ready by reflecting the actual reality of the shop floor rather than abstract database schemas. Episode context: Gilad explains how this model emerged from 1990s research and enables both knowledge graphs and agent-based systems to operate effectively. Emergence Definition: A phenomenon where complex system behaviors arise from simple rules followed by individual entities, without centralized planning or blueprints. Why it matters: Emergent systems achieve adaptability that hierarchical control structures cannot match. Episode context: Gilad uses the example of a plant growing toward sunlight—adapting around obstacles without any blueprint—to illustrate how manufacturing systems should evolve. Attractor (Chaos Theory) Definition: A state toward which a system naturally tends to evolve; attractors can lead to either stable operations or catastrophic failures. Why it matters: Agentic frameworks must include mechanisms to keep systems away from bad attractors that could cause plant shutdowns or quality disasters. Episode context: Gilad emphasizes that without proper governance, multi-agent systems can rapidly cascade toward destructive states—the "butterfly effect" in manufacturing. Resources & References Technologies & Platforms: Tulip Interfaces — No-code frontline operations platform Unified Namespace (UNS) — Real-time data communication architecture Multi-Agent Systems (MAS) — Distributed AI architecture Concepts & Frameworks: ISA-95 — Manufacturing operations standard Complex Adaptive Systems theory Chaos theory and attractors Toyota Production System / Lean Manufacturing Kaizen and G

    1h 2m

  6. 09/17/2025

    Building a Knowledge Graph Context Layer for Industrial A: Bob van de Kuilen - Director, Thred

    Context isn't static.   It's a living layer of knowledge built through problem-solving, conversation, and understanding the complex relationships on the factory floor.   This simple truth is often overlooked in industrial data strategies.    We’ve been conditioned to believe that context can be predefined; baked into standards, taxonomies, and hierarchies.   But in real-world manufacturing, things change, people think differently, and use cases evolve.   So how can we build this dynamic layer of understanding for industrial AI?   In our latest AI in Manufacturing episode, I spoke with Bob van de Kuilen, Director at Thred, about a more human-centric approach to industrial data contextualisation using Knowledge Graphs.   Thred is a tool that plugs into Ignition Platform, enabling users to visualize their factory assets in a knowledge graph, link related data points, embed domain expertise, and deliver structured, contextualized data to AI and analytics tools.   We discuss:  ✅ Why traditional approaches to data context often fail  ✅ Knowledge Graphs act as a mind map for data  ✅ The practical steps to building context  ✅ How this new context layer serves as the perfect foundation for AI agents.

    54 min

  7. 09/10/2025

    Standardizing Industrial Data Architecture with ISA-95: Jeroen Janssen - MES/MOM Consultant, Rhize

    SA-95 is a standard that’s often misunderstood, but incredibly powerful. While many think ISA-95 is rigid or overly complex, it actually enables flexibility by: ⇨ 𝐃𝐞𝐟𝐢𝐧𝐢𝐧𝐠 𝐚 𝐬𝐡𝐚𝐫𝐞𝐝 𝐯𝐨𝐜𝐚𝐛𝐮𝐥𝐚𝐫𝐲 for manufacturing concepts, creating a true ontology for your data. ⇨ 𝐂𝐫𝐞𝐚𝐭𝐢𝐧𝐠 𝐬𝐜𝐚𝐥𝐚𝐛𝐥𝐞 𝐩𝐥𝐚𝐜𝐞𝐡𝐨𝐥𝐝𝐞𝐫𝐬 for every type of data, so you can start small and add new use cases later without rebuilding everything. ⇨ 𝐏𝐫𝐨𝐯𝐢𝐝𝐢𝐧𝐠 𝐭𝐡𝐞 "𝐰𝐡𝐲" 𝐛𝐞𝐡𝐢𝐧𝐝 𝐞𝐯𝐞𝐧𝐭𝐬, not just the "what," giving crucial context to your analytics and AI models. But how do you move from theory to a practical, modern implementation? In our latest AI in Manufacturing podcast episode, we explore exactly that with ISA-95 expert Jeroen Janssen, who is an MES/MOM Consultant at Rhize Manufacturing Data Hub. In the episode, you’ll learn: ✅ How to overcome a data culture that creates so many silos. ✅ The "use case stacking" method for a phased, value-driven implementation. ✅ What a native ISA-95 data hub looks like and how a graph database can bring it to life. ✅ Why this standardized approach is the key to unlo

    54 min

  8. 09/03/2025

    Information Management and AI in Modern Manufacturing: Jeff Knepper - President, Flow Software

    Is the Timebase free historian getting an AI-Native DataOps component with Knowledge Graphs capability? You’ll hear it here first. In the latest episode of the AI in Manufacturing podcast, I sit down with Jeff Knepper, President at Flow Software Inc., to discuss the intersection of Information Management and AI in modern manufacturing, plus the exciting announcement of Timebase Atlas launch.   Here’s some of what we cover in this episode:   ✅ Why manufacturers struggle to make use of their data ✅ Building reliable pipelines for AI-driven use cases ✅ AI Agents in Manufacturing – Where they fit and what they need ✅ Unified Analytics Framework vs. Unified Namespace ✅ Historization Strategies – Best practices from edge to cloud ✅ Timebase Atlas Launch Announcement: Data Modeling, Pipelines, Knowledge Graphs, and AI interfaces ✅ MCP and Flow AI Gateway: Beyond APIs to Context-Aware Agent Interfaces

    1h 5m
See All (89)

About

Each episode of Industry40.tv Podcast will treat you to an in-depth interview with leading AI practitioners, exploring the Application of Artificial Intelligence in Manufacturing and offering practical guidance for successful implementation.

Information

  • Creator
    Kudzai Manditereza
  • Years Active
    2020 - 2026
  • Episodes
    89
  • Rating
    Clean
  • Copyright
    © Copyright 2020 All rights reserved.
  • Show Website
    Industry40.tv

You Might Also Like