Ep. 260 - Why Ignition Is Winning: Colby Clegg and Carl Gould on SCADA, Open Access, & Industrial AI

Ep. 260 - Why Ignition Is Winning: Colby Clegg and Carl Gould on SCADA, Open Access, & Industrial AI

Inductive Automation cofounders Colby Clegg and Carl Gould go deep on the origins of Ignition, the road to 8.3, and what AI means for industrial automation. Vlad and Dave host Colby Clegg, CEO, and Carl Gould, CTO, of Inductive Automation together for the first time to trace the full arc of the company. The story begins in 2003, when Sacramento systems integrator Steve Heckman brought Colby and Carl in to build the missing glue layer between OT data and modern IT tooling. What began as logging values into SQL databases became Factory PMI and eventually Ignition. A key thread is why Ignition broke through when larger automation vendors had superior distribution. Colby points to Clayton Christensen's Innovator's Dilemma. Incumbents could not match Inductive's unlimited per gateway pricing or partner with integrators because their own services groups competed with them. Carl adds the culture piece. Inductive refused to gate downloads, kept the module SDK open, made education free, and ran a public forum when competitors called it reckless, a posture they once called innovation without permission. Ignition 8.3 takes center stage, arriving after a deliberate five year gap from 8.1. Carl frames it as the completion of work that began with 8.0 in 2018. Gateway configuration is now stored in open, readable formats on disk, the gateway web interface was rewritten, and the platform supports orchestration, environmental separation, and infrastructure as code workflows Carl expects to become table stakes. The release also adds event streams, a revamped historian, and perspective drawing tools. For integrators still on 8.1, 8.3 is the version built for distributed deployments across many gateways. On AI, Carl is candid that the new MCP server module is intentionally a minimum viable product. It ships as a raw toolkit for integrators to author MCP primitives that expose Ignition data to agentic systems like Claude Code. First party MCP tools are coming, but Inductive wants to define the guardrails before shipping an API surface they will support for years. Carl frames AI as a new axis of software possibility, comparable to the shift from DOS to Windows. Colby ties it back to legacy SCADA conversion, framing the security and reliability gains as a national security issue. The episode closes with notes on the Inductive ecosystem, including a new collaboration with Tiger Data behind TimescaleDB, plus career advice on soft skills, context, and agentic coding tools. About Colby Clegg and Carl Gould Colby Clegg is the CEO and cofounder of Inductive Automation, the California based company behind Ignition, the cross platform SCADA, MES, and IIoT software used by manufacturers and integrators worldwide. Carl Gould is the CTO and cofounder, leading product and engineering direction across Ignition. Both joined founder Steve Heckman in 2003 and have shaped the platform's open, integrator first philosophy ever since. Inductive Automation: https://www.inductiveautomation.com [https://www.inductiveautomation.com] Timestamps 0:00 Introduction 1:00 Meet Colby Clegg and Carl Gould 2:00 The origins of Inductive Automation in 2003 8:00 Going to market and the Innovator's Dilemma 10:30 Innovation without permission as company culture 18:50 Ignition 8.0 and the leap to Perspective 26:00 The five year journey to 8.3 38:00 The MCP server module and AI in Ignition 45:30 AI in the control plane and guardrails 52:30 Tiger Data and the technology ecosystem 1:02:30 Career advice for the next generation 1:06:40 What is ripe for innovation References Ignition Community Conference: https://icc.inductiveautomation.com About Your Hosts Vladimir Romanov is a cohost of The Manufacturing Hub Podcast and the founder of Joltek, an independent manufacturing and industrial automation consulting firm specializing in modernization strategy, digital transformation, and workforce development. Joltek works with manufacturers and investors to reduce the risk of modernization and build the internal capability to sustain results. Connect with Vlad: https://www.linkedin.com/in/vladromanov/ Want to go deeper? Vlad and the team at Joltek have covered related topics here: Colby Clegg on Ignition 8.3 and Industrial Automation: https://www.joltek.com/blog/industrial-automation-colby-clegg-ignition-8-3 [https://www.joltek.com/blog/industrial-automation-colby-clegg-ignition-8-3] Connecting Allen Bradley PLCs to Ignition: https://www.joltek.com/blog/connecting-allen-bradley-plc-ignition [https://www.joltek.com/blog/connecting-allen-bradley-plc-ignition] Dave Griffith is a cohost of The Manufacturing Hub Podcast and founder of Capelin Solutions, an industrial automation firm helping manufacturers adopt smart manufacturing technology. He brings 15 years of experience in industrial automation and digital transformation. Connect with Dave: https://www.linkedin.com/in/davegriffith23/ Subscribe to Manufacturing Hub: https://www.manufacturinghub.live LinkedIn: https://www.linkedin.com/company/manufacturing-hub-network YouTube: https://www.youtube.com/@ManufacturingHub

Ep. 259 - Logan Terry of LSI on Change Management: The Soft Side of SCADA, MES, & ERP Projects

Change management decides whether your MES or digital transformation project lasts, or quietly gets shut off six months after go live. Vlad Romanov and Dave Griffith sit down with Logan Terry, who leads digital transformation at LSI, to dig into change management as the deciding factor in any automation or MES rollout. Logan defines change management as a methodical approach to moving an individual, team, or organization from a current state to a desired future state. The closer a system sits to where decisions are actually made, the more change management it requires, which is why MES is the single hardest place to land a project successfully. Much of the episode digs into why change management is rarely scoped properly. In competitive RFPs, the integrator who includes a robust change management line item often loses to the lowest bid, and end users frequently do not know how to evaluate that line item even when it is offered. Logan starts every client engagement with a direct question: what does your continuous improvement practice look like internally? If the client cannot sustain the change after handover, the project is on borrowed time no matter how clean the FAT and SAT looked. Logan walks through one of the most useful failure stories on the show this year. His team delivered a technically perfect OEE dashboard for a production line. Six to nine months later, every terminal was shut off. The postmortem surfaced two missed details. Maintenance was never folded into the design, and a single failed photo eye broke throughput calculations with no manual reconciliation path, which destroyed operator trust in the data. The second miss was behavioral. Showing a 30 percent OEE against a 90 percent ideal demotivates the floor, while reframing the same number as 80 percent of a realistic 36 percent target turned out to be a cleaner motivator. Looking forward, Logan sees vendors moving away from monolithic 14 function MES suites toward modular, use case specific deployments, which compresses change management scope from twenty five workflows to five or six. On AI, he argues that managing generative agents in production is closer to managing a team of people than managing software, with continuous validation replacing one time qualification. He cites the line that AI does not make bad data worse, it makes it more convincing. LSI now uses AI assisted coding agents and React based prototypes to shrink design cycles from three or four weeks of Figma work down to three or four days. About Logan Terry Logan Terry leads digital transformation at LSI, a multinational systems integrator with roughly 400 resources across 13 North American locations and offices in Asia Pacific. A mechanical engineer by training, Logan spent a decade in PLC, HMI, and SCADA development before moving into digital transformation consulting and joining LSI in late 2024. His work spans advanced SCADA, MES, analytics, and BI integrations. LSI: https://www.logicalsysinc.com/ [https://www.logicalsysinc.com/] Timestamps 0:00 Introduction 2:15 Logan's background and the LSI digital transformation practice 7:25 Defining change management 9:00 Why MES requires the most change management 13:00 How young engineers stumble into change management 24:30 Starting with decisions and workflows before technology 35:00 Internal CI capability as a project gating factor 43:30 OEE dashboard turned off six months after go live 46:30 Behavioral psychology of how operators read numbers 54:50 Modular MES replacing monolithic platforms 58:00 Generative AI and continuous validation 1:11:00 AI assisted prototyping shrinking design cycles About Your Hosts Vladimir Romanov is a co-host of The Manufacturing Hub Podcast and the founder of Joltek, an independent manufacturing and industrial automation consulting firm specializing in modernization strategy, digital transformation, and workforce development. Joltek works with manufacturers and investors to de-risk modernization and build the internal capability to sustain results. Connect with Vlad: https://www.linkedin.com/in/vladimirromanov/ Want to go deeper? Vlad and the team at Joltek have covered related topics here: Digital Transformation in Manufacturing: https://www.joltek.com/blog/digital-transformation-in-manufacturing [https://www.joltek.com/blog/digital-transformation-in-manufacturing] Manufacturing Execution Systems and Business Strategy: https://www.joltek.com/blog/manufacturing-execution-systems-business-strategy [https://www.joltek.com/blog/manufacturing-execution-systems-business-strategy] Dave Griffith is a co-host of The Manufacturing Hub Podcast and founder of Capelin Solutions, an industrial automation firm helping manufacturers adopt smart manufacturing technology. He brings 15 years of experience in industrial automation and digital transformation. Connect with Dave: https://www.linkedin.com/in/davegriffith23/ Subscribe to Manufacturing Hub: https://www.manufacturinghub.live LinkedIn: https://www.linkedin.com/company/manufacturing-hub-network YouTube: https://www.youtube.com/@ManufacturingHub

Ep. 258 - Hannover Messe Recap, the State of Industrial AI, and What Comes Next at Automate 2026

Industrial AI is moving past the chatbot phase. From the Hannover Messe show floor to system integration workflows, here's what end users actually want now. Vlad just returned from his first Hannover Messe, the largest industrial automation and manufacturing trade show in Europe. The takeaway that defined the week was a shift in how end users open conversations. A year ago, every booth visit started with the question, do you have AI? This year every vendor has some flavor of AI, so the question has flipped back to the one that actually matters. How does your product solve a specific problem in my plant? Vlad and Dave unpack what that shift means for vendors, integrators, and the end users buying these tools. On the end user side, the reality is mixed. Most knowledge workers in manufacturing have access to Microsoft Copilot and use it for better emails and meeting notes. Everything else is still mostly experimentation. While auditing PLC and SCADA logic on a recent project, Vlad expected the customer to insist on a hardened on premise model with a Dell IPC and dedicated GPUs. Instead, they shrugged and said put it in ChatGPT, the boilerplate logic has no real IP. Data governance on the carpeted side of the business is mature. On the OT side, it barely exists, and that gap matters as more plant floor data flows toward AI tools. For systems integrators, AI is compressing timelines on slow, repetitive work. Tag validation, electrical drawing automation, screenshot to bill of materials extraction, and functional spec to PLC starting points are all in active development. The tradeoff is that some of these tools save four weeks of manual auditing but require a couple of weeks to set up correctly, and a probabilistic LLM still demands human signoff on safety and control logic. Senior engineers benefit most because they already know what good output looks like. The bigger industry question is what happens to the junior to senior pipeline if entry level work disappears. Hardware tells a different story. Moore's Law, first proposed in 1965, held for about 60 years before chip density at three nanometers and heat budgets broke the cost curve. GPUs on the consumer side have been roughly stagnant since the Nvidia 30 series. On the industrial side, demand for radical hardware change has been low. PLCs, switches, IO modules, and field protocols look much like they did twenty years ago. IO Link, the protocol that should be a baseline for any Industry 4.0 deployment, was founded in 2006. Image recognition has unlocked pick and place applications that used to be too expensive to engineer the traditional way. The workforce thread runs underneath all of this. UPS recently negotiated voluntary buyouts of roughly one hundred and fifty thousand dollars per driver to remove tens of thousands of positions, while large technology firms continue to lay off staff and reinvest in data centers. Timestamps 0:00 Introduction 1:50 Hannover Messe scale, halls, and country delegations 7:20 Booth diversity from startups to hyperscalers and the German military 12:20 Why end users have stopped asking, do you have AI 19:00 The 1% on the bleeding edge versus the rest of industry 25:50 End users sending boilerplate PLC code through ChatGPT 29:20 Data governance on the OT side 32:50 AI inside systems integration workflows 39:50 Workforce shifts: UPS buyouts, FAANG layoffs, and reskilling 47:20 Hardware innovation, Moore's Law, and the industrial side 59:50 SCADA, MES, ERP, and AI generated dashboards 1:03:30 Upcoming shows: Automate 2026, ICC, and more References Hannover Messe: https://www.hannover-messe.de Automate 2026: https://www.automateshow.com Ignition Community Conference: https://icc.inductiveautomation.com Rockwell Automation Fair: https://www.rockwellautomation.com/automationfair About Your Hosts Vladimir Romanov is a co-host of The Manufacturing Hub Podcast and the founder of Joltek, an independent manufacturing and industrial automation consulting firm specializing in modernization strategy, digital transformation, and workforce development. Joltek works with manufacturers and investors to de-risk modernization and build the internal capability to sustain results. Connect with Vlad: https://www.linkedin.com/in/vladimirromanov/ Want to go deeper? Vlad and the team at Joltek have covered related topics here: Edge Computing, AI, and the Value of Manufacturing Data: https://www.joltek.com/blog/edge-computing-ai-value-manufacturing-data [https://www.joltek.com/blog/edge-computing-ai-value-manufacturing-data] Systems Integrators in Manufacturing: https://www.joltek.com/blog/system-integrators [https://www.joltek.com/blog/system-integrators] Dave Griffith is a co-host of The Manufacturing Hub Podcast and founder of Capelin Solutions, an industrial automation firm helping manufacturers adopt smart manufacturing technology. He brings 15 years of experience in industrial automation and digital transformation. Connect with Dave: https://www.linkedin.com/in/davegriffith23/

Ep. 256 - Why Machine Learning Still Outperforms LLMs for Manufacturing Process Control

Digital twins and machine learning are redefining batch optimization in manufacturing. Learn how centerlining models can catch quality issues in real time before they become irreversible. Concepts like digital twins, golden batch profiles, and statistical process control have long promised more than they delivered. Virag Vora of Twin Thread argues that layering machine learning on top of these ideas is what finally brings them to life. In this context, a digital twin is entirely data centric: a real time and historical representation of a process that serves as the foundation for AI models. The core use case is batch centerlining. The model compares current conditions against historically successful profiles, segmented by raw material source, product type, and seasonality. An orange juice manufacturer uses Twin Thread to determine whether incoming fruit should be sold fresh or routed to concentrate based on seasonal sugar content. The model identifies contributing variables in real time and alerts operators before a batch drifts beyond recovery. Twin Thread tackles the "not enough data" objection head on. With over 60 connectors, the platform works with the fragmented data reality of most manufacturing sites. Even low frequency data can train a useful model that quantifies what higher resolution instrumentation would unlock. Virag draws a clear line between ML and LLMs for process control. ML models trained on historical data produce deterministic outputs trusted for real time guidance on machine settings. LLMs excel at document retrieval and natural language interaction but are not suited for recommending set points on a live line. Twin Thread layers both: ML handles optimization, while Twin Thread Advisor lets users interrogate data and configure models through conversation. The standout proof point is Hills Pet Nutrition. After three years on Twin Thread, their models automatically feed recommendations into live production. That closed loop followed a deliberate path from human validation to A/B trials to automated execution with operator opt out. About Virag Vora Virag Vora is a solutions professional at Twin Thread, a platform that combines data centric digital twins with machine learning to optimize manufacturing processes. With a background in chemical engineering, Virag began his career deploying MES and DCS systems in biotech and pharma before joining Tulip and then Twin Thread. He helps manufacturers connect their existing data infrastructure to AI powered optimization across batch, continuous, and hybrid processes. Timestamps 0:00 Introduction 1:20 Virag's background in chemical engineering and industrial software 6:30 Moving up the ISA 95 stack from DCS to MES and applications 9:00 How AI reinvents digital twin, golden batch, and SPC concepts 12:20 What a data centric digital twin actually looks like 21:40 Where digital twins deliver the most value in manufacturing 27:00 Seasonality, segmentation, and model training strategies 36:00 Data prerequisites for deploying industrial AI 41:40 Flavors of AI in manufacturing: ML, LLMs, and agentic workflows 50:40 Closed loop AI control at Hills Pet Nutrition 53:10 Personal project: Family Graph using knowledge graphs 56:20 Prediction: operators as human digital twins References Twin Thread: https://twinthread.com This episode is sponsored by MaintainX is an AI powered maintenance and operations platform that helps technicians get the answers they need instantly so they can focus on getting assets back online. Learn more about how MaintainX supports frontline manufacturing teams. https://maintainx.com About Your Hosts Vladimir Romanov is a co-host of The Manufacturing Hub Podcast and the founder of Joltek, an independent manufacturing and industrial automation consulting firm specializing in modernization strategy, digital transformation, and workforce development. Joltek works with manufacturers and investors to de-risk modernization and build the internal capability to sustain results. Connect with Vlad: https://www.linkedin.com/in/vladimirromanov/ Want to go deeper? Vlad and the team at Joltek have covered related topics here: Edge Computing, AI, and the Value of Manufacturing Data: https://www.joltek.com/blog/edge-computing-ai-value-manufacturing-data [https://www.joltek.com/blog/edge-computing-ai-value-manufacturing-data] Digital Transformation in Manufacturing: https://www.joltek.com/blog/digital-transformation-in-manufacturing [https://www.joltek.com/blog/digital-transformation-in-manufacturing] Dave Griffith is a co-host of The Manufacturing Hub Podcast and founder of Capelin Solutions, an industrial automation firm helping manufacturers adopt smart manufacturing technology. He brings 15 years of experience in industrial automation and digital transformation. Connect with Dave: https://www.linkedin.com/in/davegriffith23/ Subscribe to Manufacturing Hub: https://www.manufacturinghub.live LinkedIn: https://www.linkedin.com/company/manufacturing-hub-network [https://www.linkedin.com/company/manufacturing-hub-network] YouTube: https://www.youtube.com/@ManufacturingHub [https://www.youtube.com/@ManufacturingHub]

Ep. 255 - From Virtual Design to Physical AI: Vention's Blueprint for Industrial Robotics

Physical AI is arriving on factory floors ahead of schedule, and Vention is already deploying it on applications four automation integrators failed to crack. François Giguère, CTO of Vention, draws a precise line between agentic AI and physical AI. Agentic systems process data and return data. Physical AI controls motion and actuation that produce real world consequences on a factory floor where a hundred percent uptime is the only acceptable standard. Giguère has spent a decade helping build Vention, a platform that lets manufacturers design robotic cells in 3D, program them through natural language, simulate them in a browser, and receive the physical machine shipped in modular components like an industrial kit. With a team of 95 engineers and three years as CTO, he brings a grounded perspective on where AI delivers real value in industrial automation and where it still falls short. The design, automate, simulate workflow at Vention represents one of the most complete implementations of AI-powered machine engineering currently in production. In the design phase, customers build systems from a modular component library. In the automate phase, an AI agent converts natural language prompts into Python control code for the entire cell including robot arms, conveyors, vision systems, and grippers. The program is validated in simulation before a single component ships. This is made possible by Vention's motion streaming architecture: instead of treating the robot as the master controller the way KUKA KRL does, Vention brings all motion planning, inverse kinematics, forward kinematics, blending, and trajectory optimization into its own software stack. The robot becomes a passive component consuming a motion stream, and the entire machine becomes programmable from a single unified codebase that AI tools excel at generating. Giguère notes that Vention's choice to use Python as the programming language for automation control gives their AI tools a measurable edge over environments built on structured text or ladder logic. Vention's two physical AI products are GRIP (Generalized Robotics Intelligence Pipeline) and Rapid AI Operator, a modular bin picking application built on top of GRIP. The technology relies on transformer-based foundation models. About François Giguère François Giguère is the CTO of Vention, an industrial automation platform where manufacturers design, program, simulate, and deploy robotic systems entirely online. Employee number four at the company, he has contributed to Vention's growth for over 10 years and leads a team of 95 engineers. He holds a background in electrical engineering and real-time embedded software development. Learn more: https://vention.io Timestamps 0:00 Introduction and welcome 1:00 François Giguère's background and Vention overview 2:20 How AI spans Vention's internal tools and customer products 4:00 Why embedded and robotics code is harder for AI to generate 7:00 Design, automate, simulate: Vention's three-stage AI workflow 13:50 Motion streaming: one unified controller for all robot brands 18:20 Defining physical AI versus agentic AI 20:10 GRIP pipeline and Rapid AI Operator 22:40 Case study: MacAlpine Plumbing bin picking with foundation models 39:40 Nvidia GTC impressions: agentic AI eclipsing physical AI 46:20 Edge versus cloud: why real-time inference stays on-prem 56:10 Predictions: physical AI roadmap and the VLA timeline This episode is sponsored by: MaintainX helps maintenance and operations teams work smarter by putting critical information directly in the hands of technicians. According to MaintainX, technicians spend up to 40 percent of their time searching for answers and responding to radio calls rather than fixing assets. https://www.maintainx.com [https://www.maintainx.com] About Your Hosts Vladimir Romanov is a co-host of The Manufacturing Hub Podcast and the founder of Joltek, an independent manufacturing and industrial automation consulting firm specializing in modernization strategy, digital transformation, and workforce development. Connect with Vlad: https://www.linkedin.com/in/vladromanov/ [https://www.linkedin.com/in/vladromanov/] Want to go deeper? Vlad and the team at Joltek have covered related topics here: Industrial Robotics: https://www.joltek.com/blog/industrial-robotics [https://www.joltek.com/blog/industrial-robotics] Edge Computing and AI Value in Manufacturing Data: https://www.joltek.com/blog/edge-computing-ai-value-manufacturing-data [https://www.joltek.com/blog/edge-computing-ai-value-manufacturing-data] Dave Griffith is a co-host of The Manufacturing Hub Podcast and founder of Capelin Solutions, an industrial automation firm helping manufacturers adopt smart manufacturing technology. He brings 15 years of experience in industrial automation and digital transformation. Connect with Dave: https://www.linkedin.com/in/davegriffith23/ [https://www.linkedin.com/in/davegriffith23/] Subscribe to Manufacturing Hub: https://www.manufacturinghub.live [https://www.manufacturinghub.live] LinkedIn: https://www.linkedin.com/company/manufacturing-hub-network [https://www.linkedin.com/company/manufacturing-hub-network] YouTube: https://www.youtube.com/@ManufacturingHub [https://www.youtube.com/@ManufacturingHub]