- Workshop
How AI Is Changing Manufacturing from the Ground Up
Jonathan Smalley
CEO, SmaK Plastics and RotoEdge Pro
A 30-Day Production Case Study Using RotoEdge Pro
What if you could hand the complexity of day-to-day production management to AI — and trust it?
That’s the question at the center of this live case study. This session presents a structured 30-day production study designed to determine how far artificial intelligence can go in guiding, or even leading, manufacturing decisions on the shop floor. The premise is straightforward: Focus your team on making good parts. AI will do the rest for you.
The Foundation
Before AI can guide decisions, it needs data. RotoEdge Pro, a real-time manufacturing data platform, captures hundreds of variables during every logging operation across all key production activities. Its newly integrated AI module uses that continuous data stream to analyze conditions, forecast outcomes, and generate production-level instructions in real time. This study puts that capability to the test under live, changing production conditions.
The Study
Over 30 days, AI takes an active role in production guidance. The study tracks three parallel data threads. This three-thread design isolates the specific value AI guidance adds, rather than crediting AI for improvement that would have happened on its own:
- A baseline forecast — what AI predicts will happen if nothing changes, built from the prior month’s KPI data
- AI-guided actuals — real results as shift supervisors and production leads implement AI’s recommended changes
- An updated AI forecast — AI’s revised predictions as changes are adopted, shift by shift and day by day
What’s Being Measured
Five core KPIs are tracked throughout: Machine Productivity, Machine Scrap Rate, Operator Performance, Number of Parts Molded, and Sales Value of Parts. Together, these cover throughput, quality, labor, and commercial output. The objective is to analyze the full scope of whether AI guidance “moves the production and productivity needle” where it counts.
What Attendees Will Take Away
This session moves beyond AI theory. Attendees will see actual production data, AI recommendations, and management decisions from a 30-day plant study. They will see when managers followed the guidance, when they chose a different course, and how those decisions affected performance.
The presentation will show:
- What real-time data AI needs to produce useful recommendations.
- How AI converts labor, machine, material, scrap, inventory, and order data into shift- and day-level production guidance.
- Where the AI baseline differed from actual results—and what changed when managers applied its recommendations.
- The effect of AI-guided decisions on productivity, labor performance, scrap, inventory, revenue, and customer-order fulfillment.
- Where manufacturers can begin, how to evaluate AI readiness, and which results to measure.
The session offers more than a view of what AI can do. It provides a practical framework for using it, explains the data AI needs, and shows where it can improve speed, visibility, and decision-making. It also clarifies where management judgment still matters most.
The case study took place in a rotational molding plant. But the pressures it measured extend across labor-intensive manufacturing. Labor changes. Machines fall behind. Materials run short. Scrap disrupts the schedule. Customer priorities shift. Each change affects output, cost, delivery, and revenue.
AI can help manufacturers respond faster. But useful results require more than software. They require accurate real-time data, clear performance goals, disciplined measurement, and managers who know when to act.
Attendees will leave with a clearer understanding of where AI can improve production today, what it takes to use it effectively, and how to turn its guidance into measurable operational and revenue gains.
