A global pharmaceutical manufacturer needed to scale API production far beyond its MES design point while avoiding instability, downtime risk, and a costly platform replacement.
Case Study
5x output versus the original production target
80% of issues were driven by work processes, system integrations, and data flows rather than the MES itself
17 min critical historian maintenance job, reduced from roughly 20 hours
An unsustainable digital model
A global pharmaceutical manufacturer focused on chronic diseases needed to scale production at a plant dedicated to manufacturing the API for one of its high-demand therapies. The site’s MES had originally been implemented to support an initial annual production target. As demand increased, the plant scaled output well beyond that original design point, producing 4x more API the next year and 5x the following year, with a longer-term requirement to support growth up to 10x over five years.
The operation was highly automated, with the automation system controlling the production process while triggering MES operator workflows with limited human interaction. As production increased, the system was processing tens of thousands of MES workflows each month, creating heavy strain on the stability of the digital environment.
The system had not been built for the required level of throughput or future scale. As pressure increased, the site experienced instability, alerts, workarounds, and frequent risks of downtime. The internal team knew the system, but they were working reactively to keep production moving rather than identifying root causes or preparing the operation for additional scale.
Challenge
- As demand increased, the plant scaled output well beyond that original design point
- As pressure increased, the site experienced instability, alerts, workarounds, and frequent risks of downtime
Looking beyond the obvious answer
The customer initially asked for support resources to help manage the backlog and stabilize day-to-day operations. Stellix recommended a different approach.
Rather than simply adding people to the existing reactive approach, Stellix assessed the broader manufacturing operations to understand where the system was stressed, and why. The team looked beyond the MES itself, evaluating workflows, integrations, batch reporting, data collection points, and concurrent processes.
This analysis changed the conversation. Problems became visible in the MES, but Stellix found that roughly 80% of the issues weren’t caused by the MES system itself, but instead were driven by work processes, system integrations, and data flows that hadn’t scaled up with production.
Stellix translated those findings into a structured remediation program across three priority areas: MES-ERP simplification, concurrent workflow optimization, and batch reporting enhancement. The team then organized the findings into 15 work packages, allowing related improvements to be addressed together rather than through a lengthy series of disconnected changes.
In one case, Stellix identified a dashboard that was creating significant system load even though manufacturing teams weren’t using it. Removing the unused function reduced workflow-step executions by approximately 7,250 per day, a 6.7% reduction, while also reducing execution errors and avoidable support effort.
Stellix also deployed a two-track model. Managed services provided day-to-day support, system-specific assessments, and proactive maintenance to keep operations running. In parallel, Stellix executed project work to address larger work process and technology issues that were stressing the system.
The engagement also addressed the human side of system performance. Stellix met daily with operations teams to review what was happening in the system and why. The team also supported weekly leadership updates, helping the customer explain system performance, root causes, and corrective actions with more confidence. Adoption visits were implemented to upskill the customer’s team so they could better understand, manage, and improve the system over time.
Stellix Role
- Identified that roughly 80% of issues were driven by work processes, system integrations, and data flows rather than the MES itself
- Reduced workflow-step executions by approximately 7,250 per day by removing an unused dashboard
From stabilization to performance at scale
Stellix helped the customer move from firefighting to a more stable, structured model for digital operations. The work improved confidence in the existing MES by showing that the system could perform reliably when the surrounding human processes, human workflows, integrations, and support model were strengthened.
That shift changed a major technology decision. Before Stellix became involved, the customer was considering replacing the existing MES with another MES platform due to dissatisfaction with system performance. After Stellix demonstrated that the existing platform could be stabilized, the customer instead chose to continue investing in it, including making a major software upgrade.
As the relationship matured, the focus expanded from stabilization to sustainable performance at scale. Stellix helped improve visibility into system health, reduce disruption risk, support batch-release reliability, and standardize the practices needed to maintain performance as throughput continued to grow.
Outcome
- Helped the customer invest $8M+ in targeted improvements instead of conducting a rip-and-replace estimated at $50M
- Established a managed services model to support continued scale and system performance
Sustainable production growth and 8-digit savings
The plant is now producing significantly more than the original production target and is on a path toward a 5x increase this year, with the digital operations roadmap designed to support longer-term scale requirements of up to 30 tons.
Specific improvements are already reducing operational friction, including reducing a critical historian maintenance job from roughly 20 hours to 17 minutes, lowering the risk that interface issues would delay batch-report generation and release activities.
The customer has invested more than $8 million in improvements rather than pursuing a full rip-and-replace approach estimated to cost around $50 million. More importantly, the customer now has greater trust in its MES/PCS environment, a clearer understanding of what affects system performance, and an ongoing managed services model designed to support continued scale.
Results
- Reduced a critical historian maintenance job from roughly 20 hours to 17 minutes
- Supported production growth from the original target to 5x output
Bridging Vision and Reality
The future belongs to adaptive organizations
Let’s have a conversation about improving performance, strengthening operations, and updating systems to adapt as fast as your environment changes.