Limits: Context, Hallucinations, and Data Quality

In this episode of Manufacturing Hub, Vlad Romanov and Dave Griffith sit down with David for a practical, operator grounded conversation about industrial data, modernization, and what it actually takes to turn plant floor signals into business decisions. David has spent more than two decades in manufacturing across automotive, solar, and electric vehicles, and his story is a familiar one for a lot of us. He walked into a plant thinking he was there for a project, discovered PLCs in real time, and never left the factory world. From early days wiring up a SQL Server to pull line data instead of sending people out with stopwatches, to leading data and analytics and shaping MES and reporting strategy, this conversation stays focused on the messy middle where most factories live.

A big theme here is that collecting data is not the same thing as creating information. As tooling has improved, connectivity, historians, SCADA, cloud storage, MQTT, and the modern ecosystem have made it easier to get signals out of machines. The hard part is deciding what matters, aligning stakeholders, and creating context that survives across teams and projects. David breaks down how real progress often starts with simple visibility, what is ruining your day, what is the biggest safety risk, what is the recurring quality miss, what is the downtime story you do not trust, then builds from there using workshops and iterative delivery instead of giant multi year “boil the ocean” programs.

We also get into Unified Namespace, why it resonates with people who have been burned by tightly coupled ISA style integrations, and why change management is the hidden cost. If you are exploring UNS, this episode highlights the difference between drawing the box on a whiteboard and getting a whole organization to actually adopt consistent naming, context, and ownership. Then we finish with a grounded take on industrial AI. No hype, no doom. Just a realistic view of where AI helps today, where it breaks, and why context windows, documentation quality, and domain expertise still decide whether results are useful or dangerous.

Timestamps
00:00:00 Welcome and the month theme on technology modernization
00:02:10 David’s background from automotive and the Tesla Fremont NUMMI era to data leadership
00:05:10 The moment data became “real” and why proactive visibility drives safety and outcomes
00:07:10 How Kaizen and Toyota Production System style problem solving creates demand for data
00:11:50 Why modern tooling makes collection easier and why budget and commitment still decide success
00:16:10 Starting points that work in the real world and the simplest visibility model that scales
00:18:20 Unified Namespace explained through decoupling, context, and why the first attempt often fails
00:23:50 Who really uses the data, operators, quality, engineering, and the “next factory” teams
00:29:10 Defining KPIs when nobody has answers and using workshops to force prioritization
00:34:20 What rollouts actually take, machine states, data structures, controls changes, and iteration
00:40:10 Industrial AI reality check, where it helps today and why it is not running your factory
00:51:10 Predicting the next few years, consolidation, pricing, and better integration with agents

About the hosts
Vlad Romanov is an industrial automation and manufacturing leader with over a decade of plant floor experience across major manufacturers. He is the founder of Joltek, where he helps teams modernize operations through IT and OT architecture, integration, reliability focused execution, and practical upskilling that actually sticks. Joltek works with manufacturers who need real outcomes, not buzzwords, and the work spans controls, data, networking, and operational performance.

Dave Griffith is the co host of Manufacturing Hub and works at the intersection of manufacturing operations, technology modernization, and practical delivery. He focuses on helping teams bridge the gap between “we want data” and “we can run this plant better next quarter.”

About the guest
David has 25 plus years of manufacturing experience spanning automotive, solar manufacturing, and EVs. He started in plant floor automation and conveyance projects, then moved deeper into industrial data, MES, and analytics leadership. His recent work includes leading data and analytics, defining KPI strategy, and building the layers required to turn raw plant signals into usable business information.

Links from Joltek

• https://www.joltek.com/blog/mastering-unified-namespace-uns-a-guide-to-data-driven-manufacturing-transformation
• https://www.joltek.com/blog/ultimate-guide-mqtt-manufacturing

Subscribe for more conversations on manufacturing modernization, industrial data architecture, MES realities, and what works on the plant floor when the budget, people, and legacy systems are all real.