Manufacturing Hub

Nick Haase, co-founder of MaintainX and host of The Wrench Factor, builds mobile-first tools for frontline technicians. He talks about designing AI for plant-floor workers, voice-note capture to preserve retiring expertise, practical AI that reduces support calls, and shifting maintenance from a cost center to a growth engine. Short, hands-on tech that meets workers in the flow of work is the focus.

Konstantin Paradizov, founder at Eukodyne with decades in pharma and food & beverage and a Six Sigma background. He discusses turning plant data and process knowledge into practical AI workflows. Conversations cover on‑prem transcription and privacy, hybrid cloud vs local stacks, iterative human validation, and pragmatic hardware and model choices for real manufacturing impact.

Manufacturing Hub is back with Episode 252, where co hosts Vlad Romanov and Dave Griffith break down what an AI survival guide should actually look like for manufacturing and industrial automation professionals. This is not a hype conversation about replacing people with magic software. It is a grounded discussion about what AI tools can do today, where they fail, why context and data quality matter so much, and how industrial teams should think about experimentation without losing sight of real operating constraints.In this episode, Vlad and Dave unpack the evolution many engineers and technical leaders have already felt in real time, from early prompt engineering, to agent based workflows, to MCP servers, skills, context management, and the growing cost of tokens and infrastructure. The conversation moves beyond generic AI commentary and into the reality of plant floor environments, where success depends on process knowledge, data architecture, OT constraints, cybersecurity, governance, and clear business value. One of the strongest themes throughout the episode is that manufacturers cannot skip the hard work of structuring data, understanding workflows, and defining use cases simply because AI tools are moving quickly.Vlad brings a very practical industrial lens to the discussion. Drawing on years of hands on experience across controls, manufacturing systems, plant modernization, and digital transformation, he explains why industrial AI has to start with operational context. A maintenance team, an engineering team, and a quality team do not need the same data, do not ask the same questions, and should not be handed the same AI workflows. That distinction matters. This conversation also highlights why the best industrial AI implementations will likely come from teams that combine domain expertise with strong technical execution, rather than generic AI shops trying to force a solution into environments they do not fully understand.Dave adds an important systems and adoption perspective, especially around cost, scaling, management expectations, and the danger of trying to prompt your way past foundational architecture work. Together, Vlad and Dave explore why manufacturers are interested in AI, why many are afraid of being left behind, and why so many projects still stall once they hit the realities of obsolete equipment, weak data models, fragmented systems, and unclear ownership of information. They also discuss deterministic logic versus LLM behavior, reporting workflows, industrial dashboards, PLC code generation concerns, and the practical question every manufacturer should ask before investing: what problem are we solving, for whom, and what is the measurable return?For those new to Vlad, he is an electrical engineer and manufacturing leader with deep experience across industrial automation, controls, data systems, OT architecture, modernization strategy, and plant operations. Through Joltek, Vlad works with manufacturers on digital transformation, IT OT architecture and integration, modernization planning, operational improvement, and technical workforce enablement. Learn more here:Joltek: https://www.joltek.com IT OT Architecture and Integration: https://www.joltek.com/services/service-details-it-ot-architecture-integrationIf you are a plant leader, controls engineer, systems integrator, OT architect, SCADA or MES practitioner, or simply someone trying to separate useful AI workflows from noise, this episode will give you a much more realistic framework for thinking about industrial AI adoption.Timestamps00:00 Welcome back and why this episode matters01:00 Setting up the industrial AI theme for the coming weeks03:10 From prompt engineering to structured AI workflows05:30 AI agents, parallel workflows, tokens, and context windows09:00 MCP tools, Playwright, and what new integrations unlock16:20 How Vlad researches AI and where useful information actually lives22:00 Real manufacturing problems versus AI in search of a problem29:40 Why industrial data architecture is harder than most people think37:00 OT expertise, workforce enablement, and who should build solutions45:40 Practical advice for manufacturers starting the AI journey50:30 Data governance, hallucinations, infrastructure, and cybersecurity57:20 What looks promising today in reporting, dashboards, and industrial applications

In this episode of Manufacturing Hub, Vlad and Dave sit down with Travis Cox and Kevin McCluskey from Inductive Automation to unpack what was actually proven at ProveIt and why it matters for teams trying to modernize plants without building a fragile mess of point to point integrations. If you have ever looked at a shiny demo and wondered what the real architecture looks like, how it scales beyond a single line, and what it takes to roll out across multiple sites without turning every change into a high risk event, this conversation is for you.Travis and Kevin walk through their ProveIt Enterprise B build and the thinking behind it. The core idea is simple but powerful: treat the factory like a system that needs a shared digital infrastructure, built on open standards, where data is contextualized and reusable. They break down how they used Ignition Edge close to PLCs for resiliency, local HMIs, and disciplined data modeling, then moved data through MQTT into a Unified Namespace so multiple applications can consume the same trusted signals and context. This is the difference between “we can connect to anything” and “we can scale without rewriting everything every time the business changes.” Open standards show up repeatedly in the conversation because ProveIt is specifically designed to force interoperability and practical implementation tradeoffs. Inductive Automation has also written about ProveIt as a place where MQTT, OPC UA, and SQL show up as real foundations rather than slogans.From there, the episode gets into the part that should make both OT and IT teams pay attention: modern deployment practices applied to industrial applications. Kevin outlines a clear maturity path from a single designer workflow to version control, then to containerized deployments, and finally to full GitOps style promotion across dev, staging, and production using tools like Argo CD, Helm, Kubernetes, and release promotion concepts that look like what the software world has used for years. Argo CD is explicitly built around Git repositories as the source of truth for desired state, which is exactly why it fits this style of deployment. The live portion of the conversation demonstrates how fast this can get when the infrastructure is treated as code: they spin up a brand new “site four” by submitting a form, generating a pull request, merging it, and letting the pipeline do the rest.Timestamps00:00 Welcome back and why this ProveIt recap matters01:35 Meet Travis Cox and Kevin McCluskey from Inductive Automation03:10 What ProveIt is and the key vendor questions it forces05:20 Enterprise B architecture overview from PLC to Edge to site to enterprise07:30 HMI walkthrough across liquid processing, filling, packaging, palletizing09:05 Why deploy Ignition Edge instead of only a centralized site gateway12:05 Design once, reuse everywhere and what that means for scaling quickly14:35 On prem realities versus cloud infrastructure in the ProveIt environment17:10 MCP, n8n workflows, and bringing live operational context into AI20:40 i3X style API access to models, history, and alarms for interoperability23:15 GitHub, Docker Compose, Helm, Kubernetes, Argo CD, Cargo and GitOps promotion36:55 Spinning up a new site live and what it changes for multi site rolloutsAbout the hostsVlad Romanov is an electrical engineer and MBA who has spent over a decade building and modernizing manufacturing systems across industrial automation, controls, and plant operations. Through Joltek, Vlad works with manufacturers to assess current state OT foundations, reduce modernization risk, improve reliability, and build internal capability through practical training and standards that stick.Dave Griffith co hosts Manufacturing Hub and brings a practitioner lens focused on what works on the plant floor, how architectures survive real constraints, and how industrial teams can modernize without breaking production.About the guestsTravis Cox is Chief Technology Evangelist at Inductive Automation and has spent over two decades helping customers and partners design scalable architectures, apply best practices, and deliver real solutions with Ignition.Kevin McCluskey is Chief Technology Architect at Inductive Automation and works with organizations on architecture decisions, platform direction, and enabling the next generation of industrial applications.Learn more about Joltekhttps://www.joltek.com/serviceshttps://www.joltek.com/book-a-modernization-consultation

This episode wraps up our Technology Modernization theme with a Siemens perspective that feels very grounded in what factories are actually dealing with right now. Brian Albrecht and Louis Hughes from the Siemens XD team walk through what they are seeing in the field across brownfield and greenfield conversations, why executives keep asking for industrial AI before the foundations are ready, and what it really takes to turn messy plant data into something you can trust for analytics, operations, and eventually AI enabled workflows.A big thread in this conversation is that modern manufacturing is not blocked by ambition, it is blocked by readiness. Everyone wants faster decisions, fewer surprises, and higher uptime, but the path there usually starts with boring work that is not optional. Data transparency across machine, plant, MES, and cloud layers. A clear definition of what real time actually needs to mean for a given use case. And a plan to contextualize and orchestrate data so that AI does not get fed junk inputs. Brian and Louis explain how they approach those early customer conversations, how workshops turn vision into prioritized use cases, and why trust, pilots, and repeatability matter more than flashy demos when you are working in regulated or high consequence environments.If you have been hearing nonstop AI buzz but you are still wrestling with legacy controls, inconsistent tags, documentation that no one can find, and seven layers of security constraints, this episode is for you. We get into practical use cases like AI vision and anomaly detection, LLMs for tribal knowledge and troubleshooting workflows, and the idea of fast versus slow AI, meaning AI that must act during production versus AI that can analyze after the fact.Timestamps00:00 Welcome and why this episode closes the modernization theme02:10 Meet Brian Albrecht and Louis Hughes from the Siemens XD team05:25 Vertical differences across oil and gas, discrete, and process manufacturing07:50 What executives ask for right now beyond AI, factory of the future and data transparency10:50 Brownfield reality and why most modernization work starts with legacy systems12:30 The AI conversation when foundations are missing, meeting customers where they are15:10 Current AI use cases in manufacturing, downtime, throughput, LLMs, and vision18:10 What it means to be AI ready, data silos, contextualization, and orchestration23:50 Fast versus slow AI and why production time decisions are different from analytics25:30 Edge versus cloud architecture, latency, and where the data should live33:40 Cybersecurity, trust, and why perception can lag behind the technology36:50 Hallucinations, guardrails, and why recommendations usually come before automation51:10 Book recommendations, career advice, and future predictions for industrial AIAbout the hostsVlad Romanov is an electrical engineer with an MBA from McGill University and over a decade of experience in manufacturing and industrial automation. He has worked across large scale environments including Procter and Gamble, Kraft Heinz, and Post Holdings, and he now leads Joltek, helping manufacturers modernize systems, improve reliability, strengthen IT and OT architecture, and upskill technical teams through practical training and on site enablement.Dave Griffith is the cohost of Manufacturing Hub and an industrial automation practitioner who focuses on how modern technologies translate into real factory outcomes, from controls and data foundations to scalable implementation strategies.About the guestsBrian Albrecht started in electrical engineering and spent about a decade in systems integration in Oklahoma City focused on oil and gas, building SCADA, networking, and automation solutions and leading teams delivering real world projects. He now works with Siemens customers on building relationships and delivering solutions that create measurable value.Louis Hughes has roughly 20 years of manufacturing experience, starting in software development for manufacturing and engineering applications, then moving into solution architecture, services delivery, and experience center leadership. He now leads a smart manufacturing team, bringing a software and systems view into automation conversations focused on solving customer problems, not just deploying tools.Joltek Services - https://www.joltek.com/servicesContact Joltek - https://www.joltek.com/contactReferenced in the episodeProveIt Conference - https://www.proveitconference.com/Siemens - https://www.siemens.com/Crossing the Chasm by Geoffrey A Moorehttps://en.wikipedia.org/wiki/Crossing_the_ChasmExtreme Ownership by Jocko Willink and Leif Babinhttps://en.wikipedia.org/wiki/Extreme_Ownership

Amy Williams, a life sciences automation and digital transformation practitioner at Skellig Automation, describes a virtual factory that mirrors real regulated batch pharma. She walks through a fed-batch fermentation flow, UNS and MQTT data publishing, and why raw tags plus paper records matter. Short takes cover data contextualization, schema reuse, and practical vendor demo expectations.

A practical dive into turning plant-floor signals into usable information. They explore where to start with visibility, why simple dashboards beat spreadsheets, and how workshops align KPIs like OEE. The conversation covers Unified Namespace tradeoffs, adoption as change management, realistic industrial AI use, and career skills for data-driven manufacturing.

Benson Hougland, a long-time Opto 22 product strategist for industrial controllers and edge devices, shares hands-on manufacturing wisdom. He contrasts siloed brownfield realities with modern, data-ready plants. He discusses practical upgrades, layered edge approaches for legacy equipment, why sanctified data matters for industrial AI, and how to win small to scale modernization.

Technology modernization in manufacturing is not a list of shiny tools. It is a sequencing problem. In this episode of Manufacturing Hub, Vlad Romanov and Dave Griffith break down why the executive vision for AI often collides with the reality of the plant floor, and what a practical path forward actually looks like when you account for data quality, legacy controls, networking, and the true cost of integration.A core theme in this conversation is imperfect information. Leaders often believe the data already exists because reports exist. But a stack of paper, a few spreadsheets, or a single counter value is not the same as contextualized, trustworthy history that can drive decisions or support advanced analytics. Vlad and Dave walk through why foundational work matters, what teams usually miss during modernization, and how quickly the bill grows when you discover your architecture is outdated, undocumented, or full of dependencies you cannot see until you open panels and start tracing signals.You will also hear a grounded debate on how to think about SCADA, MES, historians, dashboards, and what it would actually mean to “feed data into AI” in a manufacturing context. The takeaway is simple. If you want better outcomes, you need a better understanding of your current state, a clear business case, and a roadmap that prioritizes what matters operationally. Modernization is not one big upgrade. It is a series of decisions that either reduce friction or create it.About the hostsVlad Romanov is an industrial automation and manufacturing expert focused on plant assessments, controls and data architecture, IT and OT integration, and workforce upskilling. Vlad has over 10 years of experience across large manufacturers and complex multi site environments, working from PLC and HMI layers up through SCADA, MES, and ERP integration programs. He is the founder of Joltek, where the mission is to help manufacturers modernize safely, build internal capability, and deliver results that actually survive handoff to operations.Learn more about Joltekhttps://www.joltek.comhttps://www.joltek.com/servicesDave Griffith is an industrial automation practitioner and consultant who works closely with manufacturers to modernize legacy environments, improve reliability, and build practical systems that operators and maintenance teams can support. Dave brings a strong perspective on what is feasible in real plants, where uptime, risk, budget, and organizational readiness drive every decision.Timestamps00:00:00 Welcome and why this month is about technology modernization00:02:10 The real problem with “just add AI” in manufacturing00:04:15 Quick background on Vlad and Dave and the work they do00:05:25 The disconnect between the perfect factory vision and the plant floor00:06:25 Vlad on business cases, integration reality, and infrastructure gaps00:09:05 Dave on imperfect information and why reports are not data00:14:35 What executives actually want from AI and why it is often about people constraints00:20:25 How to get there, hardware first, data normalization, and context00:22:05 Vlad on assessments, legacy hardware, and why upgrades get complicated fast00:39:00 New facility planning mistakes and why early decisions lock you in00:45:10 You have the data, now what, OEE baselines, bottlenecks, and root causes00:58:10 Final takeaways, inventory your architecture and treat data like an assetReferences and links mentionedManufacturing Hub Podcasthttps://www.manufacturinghub.liveProveIt Conferencehttps://www.proveitconference.comAutomate Showhttps://www.automateshow.comIgnition Community Conferencehttps://icc.inductiveautomation.comIf you are watching on YouTube, subscribe so you do not miss the rest of this month’s deep dives on hardware, data teams, and practical applications that actually work on real plant floors.

Amos Purdy, an MBA and electrical engineering expert with over 15 years in industrial automation, shares his journey through MES and SCADA systems across diverse industries, including EV battery manufacturing. He discusses the challenges of translating theoretical solutions into practical applications on production lines. The conversation explores the importance of real-world projects over credentials, the balance of hiring web developers versus plant veterans, and modernizing legacy plants by enhancing data transparency and mitigating risk. Amos also highlights the evolving role of AI in manufacturing and the criticality of hobbyist energy in driving innovation.