A Composable Agentic Framework for Frontline Operations

Over the last year, “agentic AI” has shifted from emerging concept to practical conversation. Everyone is now talking about agents, and with today’s tools, building one has become every person’s business. But that raises a much bigger question: what agents should we build, and how do we organize them into something meaningful?

This is a topic that is not new and I have reflected on it through a number of lenses, e.g. Why IIoT is Transformative - its not the technology! and The Genius of the Toyota Production System Explained. This post however offers my first reflections on what a Composable Agentic Framework could look like for operations in general and manufacturing specifically. It’s an attempt to give industry an initial perspective, a concept and maybe some guidance for applying agentic AI to frontline operations in ways that improve both productivity and adaptability. Notice I say "initial", there is clearly much more to this topic that needs to be explored, discussed and debated - in addition the technology is nascent and we can expect much more sophistication and depth as it evolves.

Why Agents? Why Now?

For decades my peers and I, as manufacturing thinkers, have dreamed of holonic systems and fractal factories—production environments that adapt in real time, scale seamlessly, and continuously self-optimize. But until recently, that vision stayed in the realm of theory. The technology just wasn’t ready.

Now it is. Today’s digital platforms, IIoT connectivity, cloud infrastructure, and AI capabilities make it possible to realize this vision in practice. Instead of rigid, monolithic systems, we can now compose operations out of, and with, autonomous, collaborative agents that interact dynamically.

And this matters because composability is built on the idea that continuous, incremental improvements add up to transformation. What’s new is that agentic AI can accelerate these improvements beyond what we can imagine. Large language models and agentic frameworks have already proven their ability to supercharge productivity in domains like software development, research, and customer interaction. The challenge—and opportunity—before us now is to understand and define how to bring that same acceleration into composability and frontline operations.

Agents make this possible. Each agent is discrete, goal-oriented, and autonomous, yet designed to collaborate with other agents. When composed together, they create systems that flex, adapt, and continuously optimize.

In earlier posts, I’ve argued that digital transformation is not about IT and OT learning to coexist, but about creating a new whole where the distinction ceases to matter. That’s the essence of composability. Agents are the next step: a way to make that vision practical, modular, and scalable.

An Agent Framework for Composable Digital Solutions

The starting point is simple: in new digital operations platforms like Tulip, apps already behave like agents.

• They have a clear goal (guide an operator, track a unit, log a machine event).
• They operate autonomously within their context.
• They collaborate with other apps and systems through shared data, triggers, and transitions.

Add AI into the mix, and these apps become agentic apps—supercharged digital teammates. And when multiple apps are composed together, they form a multi-agent system that mirrors the complexity of real operations, in other words they become digital twins in the true sense of the concept.

But in order for this "mirroring" to become a digital twin we need to define some rules and this is where the framework comes in. To move from scattered apps and automations to composable digital solutions, we need a structured way to think about agents.

Add AI into the mix, and apps evolve into agentic apps—supercharged digital teammates. Composed together, they form multi-agent systems that can mirror the complexity of real operations—becoming digital twins in the truest sense. But achieving that requires more than simply building agents; it requires structure and guidance. Without it, the risk is a proliferation of scattered apps and agents with no cohesive purpose—at best delivering little value, and at worst creating more complexity, reduced productivity, and even unsafe outcomes. The goal of this suggest framework is to provide the rules and design principles that ensure agents align toward a shared purpose. This reflects the essence of holonic structures: their power comes not just from autonomy, but from working together toward a common goal. That shared purpose is what makes them optimal, and what turns a collection of agents into a true composable digital solution that delivers measurable benefits.

In my earlier blog post “To Data Model or Not to Data Model”, I described the Artefact Model as a key element in composability: a scalable, flexible, interpretable representation of the operational system. The Artefact Model gives us the common context in which agents can interact—products, orders, machines, deviations, and operators all represented digitally and consistently.

A Perspective on Agent Types

Before diving into the types themselves, it’s important to recognize that agents serve two distinct scenarios in manufacturing:

Authoring / Building – Here, agents augment the creation process. They help engineers, developers, and even citizen builders design solutions faster and smarter. Think of them as co-pilots that propose app templates, generate artefact structures, suggest best practices, and automate repetitive setup tasks. These agents accelerate innovation and democratize solution-building.

Operations – Once deployed, agents act within day-to-day execution. They monitor machines, guide operators, coordinate workflows, manage deviations, and connect enterprise systems. These operational agents are the ones “living” in production, continuously working toward defined goals while collaborating with other agents and humans.

The framework presented here is focused specifically on the operations scenario. That being said there are commonalities and some agent types apply to both scenarios, but the context differs: in building, agents amplify human creativity and speed; in operations, agents amplify execution and adaptability. 

Agentic AI in operations enables a powerful ecosystem where "teams of experts" (agents) work together, demonstrating "collective intelligence". Crucially, operational agents, empowered by AI, transform what were once innate objects like machines and materials into active, intelligent members of the dynamic work environment. We are giving them the ability to be agents—autonomous and collaborative participants within the dynamic manufacturing operation network.

With that lets take a look at a shared taxonomy for the different types of agents in a composable agent framework:

Physical Agents: These agents are defined by their direct representation of physical manufacturing objects within the digital twin. They continuously mirror the real-world status, attributes, and behaviors of their tangible counterparts, enabling real-time monitoring, analysis, and control. Here are some examples:

• Product Agent: Represents a specific product or unit throughout its manufacturing journey. Its goal is to track the product's individual status, quality parameters, and genealogy, providing a comprehensive digital record for each item produced.
• Machine Agent: Serves as the digital twin of a specific piece of equipment or machinery on the shop floor. Its purpose is to monitor machine health, performance metrics (e.g., OEE, availability, performance, quality ), and predict potential failures, enabling proactive maintenance and optimized utilization.
• Tote Agent: Represents a tote or device that carries and conveys product or material on the shop floor. This agent's role is to track the movement of the material or products it carrier in the operations and facilitates traceability and location with ease.

Operational Agents: These agents are defined by their focus on tangible operational entities and processes used in manufacturing management. They manage the flow of work, information, and events, ensuring that manufacturing processes adhere to plans and respond effectively to deviations. Here are some examples:

• Order Agent: Represents a specific production or work order. Its goal is to oversee the end-to-end execution of that order, tracking progress against the schedule, managing material consumption, and ensuring all required steps are completed.
• Deviation Agent: Activated when a process or quality deviation occurs. Its purpose is to identify, classify, and manage the deviation, potentially initiating corrective actions, alerts, or escalation workflows to relevant personnel or systems.
• Schedule Agent: Responsible for dynamically managing and optimizing production schedules. This agent works to ensure resources are efficiently allocated and production targets are met, adapting to real-time changes in machine status, material availability, or order priorities.

System Agents: These agents are defined by their role in facilitating integration and intelligent interaction with broader enterprise-level systems and data repositories. They ensure data consistency, enable seamless workflow orchestration across different platforms, and provide access to critical business context. Here are some examples:

• ERP Agent: Manages the flow of information between Tulip and the Enterprise Resource Planning system. Its function includes receiving work orders, reporting production updates, and managing material consumption and inventory levels in the ERP.
• UNS Agent: Represents the integration with a Unified Namespace. This agent enables seamless, real-time data exchange across the entire operational landscape, ensuring that all systems have access to consistent and up-to-date information.
• Data Lake Agent: Responsible for managing the ingestion of operational data from Tulip into a central data lake and enabling access to this data for advanced analytics and further AI model training. It ensures that the rich data captured by Tulip's composable applications is leveraged for broader insights.
• Device Agent: Corresponds to a specific connected device, such as a scale, barcode scanner, or sensor. This agent's role is to facilitate seamless data exchange between the physical device and the Tulip platform, ensuring accurate data collection and enabling device-triggered actions.

Staff or Companion Agents. These are a general type of agent that augment the human's ability to find information, research topics, suggest improvements, and perform tasks. They are used in a variety of scenarios and serve as utilities in both the operational environment as well as the engineering or builder environments. Here are some examples:

• Quality Research Agent: Quickly finds documentation, suggests troubleshooting steps to an operator, or summarizes a quality history for a supervisor.
• App Builder Agent: Generates app templates, proposes table structures in the Artefact Model, or scaffolds connectors based on device specs—accelerating citizen developers and engineers.

What unites these agent types in this framework is the three core properties: it has a goal, it operates autonomously within a bounded scope, and it is collaborative—able to exchange data, signals, and intent with other agents and humans.

Crucially, these agent types do more than align with the Artefact Model — they enhance it. By consistent real time representation of artefacts (products, resources, orders, deviations), agents enrich the shared digital twin with actionable state, decisions, and provenance. That enriched Artefact Model becomes the lingua franca that lets agents interoperate reliably, enables composition, and prevents the classic failure mode: a landscape of scattered apps and ad-hoc bots with no unifying purpose.

In short: agents must be designed to work as an integral part of  the Artefact Model so that autonomy and collaboration add up to a cohesive, safe, and value-driving digital twin.

Beyond Incrementalism: The Future of Multi-Agent Collaboration Frameworks

Much of what we know about manufacturing improvements has historically been driven by incrementalism—step-by-step gains in efficiency, quality, or throughput. This mindset is not wrong; in fact, it is the foundation of continuous improvement and the heart of lean thinking. But incrementalism alone can only take us so far. To thrive in today’s volatile and complex operating environments, we need systems that don’t just get gradually better but can adapt dynamically to new conditions.

This is where multi-agent collaboration becomes transformative. Agents, by design, are autonomous but collaborative, and when they interact at scale, they exhibit something greater than the sum of their parts: collective intelligence.

The result is emergence and self-organization: a system-level intelligence and adaptability that was not explicitly programmed into any single agent. Emergent behavior is what allows multi-agent systems to flex and reconfigure in response to disruptions, market changes, or unexpected events. This is not just automation—it’s a new layer of operational intelligence applied directly to the frontline.

But to realize this potential, we must also reconsider the frameworks that structure our digital manufacturing systems. Such a composable, agentic world—where apps act as agents and operations are orchestrated by multi-agent systems—doesn’t fit neatly into traditional manufacturing systems standards and hierarchies definitions (see my earlier post, OK, Let’s Talk ISA-95).

That doesn’t mean throwing standards away, but it does mean rethinking or adapting them to this new reality. If emergence is the key to adaptability, then our models and standards need to evolve to describe systems that are dynamic, distributed, and composable rather than hierarchical and rigid.

In short: incrementalism is still essential, but it is no longer sufficient. Collective intelligence, powered by agents and guided by frameworks like the Artefact Model, is what will enable manufacturing to achieve adaptability at scale—and truly fulfill the promise of digital transformation.

Final Reflections

Building, authoring, creating agents is within everyone’s reach. But without structure and guidance, we risk ending up with a fragmented landscape of apps and bots—scattered efforts that deliver little value, or worse, add complexity, reduce productivity, and even create unsafe outcomes.

My hope is that this initial framework presented here provides that needed guidance. It should help us define what kinds of agents to build, how to compose them into systems, and how to ensure they align with a unifying purpose. It grounds agentic design in Composability and its Artefact Model, ensuring that agents not only adhere to but actively enhance the shared digital twin. This alignment is what keeps autonomy and collaboration from drifting apart and turns them into something greater: collective intelligence with emergent adaptability.

This is why composability and agent frameworks matter. They give us the structure to channel autonomy toward common goals. They offer to guide us on the path to increased productivity with adaptability. And they point to the need for new thinking in our standards and models—beyond the rigid boundaries of monolithic approaches, toward a more dynamic and composable reality.

In the end, the promise of agentic AI in operations is a the newest step in the digital transformation journey: Continuous Transformation - reinvention at scale of manufacturing operations.

And this is just the beginning. There is so much more to explore, define, and refine. I invite you—industry peers, practitioners, and thinkers—to engage in this discussion and debate. Let’s shape together what a composable agentic framework should look like in practice. After all, it takes a village... 

Don't Be the Last Dinosaur: Your Plant's Digital Evolution Starts Now!

Plant Managers, manufacturing leaders - look around you. The manufacturing world is not just changing; it's undergoing a seismic shift. While you're grappling with daily firefighting, your competitors – the agile, the digitally native, and those strategically investing – are busy building tomorrow's factories. They are not compromising; they are not settling for just automation, they are digitizing every process, they have rich digital data, they are ready to deploy intelligent, agentic systems that learn, adapt, and optimize production with unprecedented speed and accuracy.

The choice before you is stark: Innovate and adopt, or become obsolete.

If you continue to manage your plants with fragmented data, manual processes, and reactive decision-making, you are literally leaving money on the table. You're bleeding efficiency, compromising quality, and surrendering market share. The 'traditional' way of manufacturing is becoming a relic.

Here are the critical decisions and actions you must undertake RIGHT NOW to avoid being left in the dust:

1. Stop analyzing and planning- Start digitizing today: Your operations are awash in data, but is it usable? Is it real-time? Is it connected? The foundation of every advanced manufacturing system—from IIoT to agentic AI—is clean, contextualized data. 

ACTION: Invest immediately in robust digital data infrastructure. This means connecting your machines, sensors, and systems (OT and IT convergence is non-negotiable). If your data is trapped in silos, you are blind, and your plant will suffocate under its own inefficiency. This is simply critical - not having digital data is a waste, like other wastes in manufacturing!

2. Embrace the Power of Composability: Shift your thinking beyond overarching automation or top-down systems to digitize plant processes. The "lights-out factory" is not only outdated, it never truly materialized. Digital transformation isn't about replacing humans but augmenting their capabilities. Composability focuses on empowering your workforce, leading to significant productivity gains. Deploy pilot projects where AI agents can take over mundane, repetitive, or complex analytical tasks. Think predictive maintenance that schedules itself, quality control that detects micro-deviations before they become defects or failures, and production dispatching that dynamically adjusts to supply chain disruptions. 

ACTION: Identify one critical bottleneck in your plant that could be addressed by a digital solution - yes “Kaizen”, start bottom up and iterate. Adopt technology, find a partner and just start. There are some impactful digital technology platforms (I recommend starting with Tulip of course) and launch a focused pilot. Show your team and leadership the tangible benefits.

3. Future-Proof Your Workforce – Invest in Upskilling, Not Just Training: Your people are your greatest asset. They need to evolve from procedure followers to orchestrators, data interpreters, and system managers. This isn't just about technical skills; it's about fostering a culture of continuous learning and adaptability. And with democratization that digital technologies offer this quickly can create a ground swell, a movement within your organization. 

ACTION: Develop a strategic plan for workforce transformation. Enhance your operational excellence with augmented lean principles and identify critical future roles and necessary skill sets. Empower your team to embrace these new technologies and strike down any skepticism or technology fears.

4. Demand Agility from Your Systems – Ditch the Rigidity: The era of monolithic, inflexible manufacturing systems is over. Your plant needs to be agile, able to pivot production lines, incorporate new products, and respond to market shifts with unprecedented speed. This means moving towards composable, interoperable platforms that can readily empower your operations with the new digital capabilities including critically AI. 

ACTION: When evaluating new solutions (like MES, LIMS, CMMS or other systems), prioritize open composable architectures with cloud-native capabilities, IIoT platforms and and in herent AI capabilities that are not an afterthought or “bolt on”. Demand systems that are built for change, not for static operations. These systems have to enable you to transform, they have to provide you a way to implement according to the 5 pillars of composability. Make agile, emergent control a reality with agentic AI.

5. For Regulated Industries: Make GxP a Competitive Advantage, Not a Burden: If you're in Pharma, Biotech, or Med Device, the GxP implications of these technologies are paramount. But don't let compliance be an excuse for stagnation. Modern digital validation approaches and Pharma 4.0 guidances mean you can innovate with compliance. Transformative digital platforms have inherent built in compliance through detailed digital data, audit trails, and transparency to control mechanisms. Democratization means technology is simpler to understand with that comes transparency and self documentation.

ACTION: Engage with experts who understand both cutting-edge digital transformation and the nuances of GxP. Be proactive in defining your digital validation strategies for IIoT and AI, leveraging initiatives like Validation 4.0. This ensures your innovation is robust, secure, and compliant.

The clock is ticking. The question isn't if your plant will undergo this digital transformation, but when and who will lead it. If you hesitate, you risk becoming a case study in industrial obsolescence. Seize this moment, or watch your competition leave you in their digital dust. This is the mindset you need to adopt to thrive in this new era. What's your immediate next step?

How Holonic Dreams are Becoming Manufacturing Realities

Let me tell you, there are few things more thrilling than seeing a concept you poured your heart into decades ago slowly coming to life in ways you barely dared to dream. For me, that feeling hits hard with the incredible capabilities of AI in general, and specifically, Generative AI . These aren't just buzzwords; they're fundamentally reshaping how we think about digital manufacturing (or whatever the latest term is). While Generative AI is phenomenal for creating content, designing new products, or even simulating complex processes, its true power in manufacturing often lies in its ability to empower something even more profound - Multi-Agent systems. This is the realization of Holonic concepts in a composable manner to enable agile manufacturing with Agentic AI .

When I see these advancements I am just mesmerized and my mind goes back to the 1990s. That’s when my journey into this future really began, deeply immersed in the world of Holonic Manufacturing Systems (HMS) and the emerging field of multi-agent systems.

Back then, I was a young researcher PhD working a methodology and architecture for Holonic manufacturing systems in collaboration with other like minded researchers as part of global consortium. It wasn’t just an academic exercise; it was a burning ambition to make manufacturing truly agile and resilient. I envisioned a factory floor that wasn't a rigid, top-down hierarchy, but a vibrant, decentralized network of intelligent, collaborative entities – what we called "holons."

The Holonic Vision: A Glimpse into the Future I Believed In

Imagine a shop floor where every machine, every production cell, every product, wasn't just a passive component but an intelligent "holon" – a self-contained, self-regulating unit. They would have their own smarts, making decisions, talking to each other, and collectively adapting to whatever curveball the market threw at them. Koestler's concept of a "holon" – simultaneously a whole and a part – perfectly captured this idea of distributed intelligence.

The benefits? Oh, they were clear and seemed a world away but yet an eerily anticipatory need of the current political and economic circumstances.

• Agility beyond belief : Reconfiguring production lines in a flash, launching new products on a dime, responding to customer demands with unprecedented speed.
• Built-in resilience : If one holon stumbled, the others would dynamically pick up the slack, re-routing operations to keep things flowing. Downtime issue would be a distant memory.
• Seamless scalability : Adding new machines or processes would be like plugging in a new module, effortlessly integrating into the intelligent network.
• Optimization from within : Local decisions by these smart holons would ripple up to optimize the entire system, far surpassing anything a central, rigid control system could ever hope to achieve.

This wasn't just theory; it was a blueprint for a manufacturing revolution.

We are Still Waiting for a Digital Manufacturing's Breakthrough

The holonic concept was the perfect architectural dream, but the engine to power it, multi-agent systems, was still in its infancy. My research in the 90's focused on how to design these agent systems, how to give them that holonic spirit, but the reality was that our ambition ran ahead of the available technology. We were hitting walls. The computational power needed to run complex agent logic on shop-floor controllers was simply astronomical for the time. Getting a multitude of agents to communicate reliably and securely across a factory? That was a networking nightmare. And then the AI capabilities were nascent, a whisper of potential, compared to the what we wield in our hands today."

Those were exhilarating times for pure research, pushing the theoretical limits of what manufacturing could be. But bringing it to large-scale industrial reality? That was a bridge too far. Until now ...

Today's Reality: AI and Digital Infrastructure can Unleashing the Holonic Dream

Fast forward to today, and the technological landscape has dramatically evolved. The convergence of several critical advancements has not only rendered the holonic vision achievable but has propelled it into operational realms previously unimaginable:

1. Advanced AI and Machine Learning Capabilities : Modern Artificial Intelligence and Machine Learning algorithms now provide the sophisticated analytical and cognitive capabilities for individual software agents. These algorithms enable agents to learn from large-scale industrial datasets, execute robust predictive analytics with high precision, and achieve adaptive process optimization in real-time. This represents a fundamental shift from deterministic, rule-based systems to dynamic, self-optimizing intelligence.
2. The Industrial Internet of Things (IIoT) as the Network of Agents, Powered by Agentic AI : This is where the core holonic vision finds its full realization. The Industrial Internet of Things (IIoT) is not merely a collection of connected devices; it forms the very network of agents. The IIoT nodes themselves are designed as autonomous, intelligent agents . Each smart device, each sensor, each piece of equipment can be made to act as a data acquisition point and, crucially, as a decentralized intelligent entity. The emergence of Agentic AI imbues these IIoT nodes with advanced capabilities for complex task decomposition, strategic planning, execution, and critical self-reflection. This synergy of IIoT as the foundational agent network and Agentic AI providing the cognitive layer directly mirrors the autonomous and cooperative principles fundamental to our original holonic concepts, enabling seamless interoperable collaboration across the manufacturing ecosystem. 

Futuristic Use Cases Becoming Reality: Empowering the Digital Twin for Tomorrow's Factory

For all these visions to truly become reality, we needed more than just powerful tech; we needed a concept that can effectively by applied to the realities of a physical operation. Here we can use a Digital Twin approach to represent the reality of the operation and build a foundational model with a set of constructs that aligned perfectly with the holonic principles I’d spent years researching.

This is also where Agentic AI enters the stage, becoming the intelligence that breathes life into this digital replica. My research from the 90s proposed a consistent model for these foundational constructs, embodying them as intelligent Product, Order, and Resource agents (or holons). This was the blueprint for how the real-world manufacturing elements could become autonomous, cooperative entities within the digital twin.

Let's step into this future for a moment, and I’ll paint a picture of what a manufacturing operation truly looks like when its digital twin is powered by these agentic principles, or in other words a next generation paradigm shifting composable manufacturing system . In this world, a work order isn't just data on a screen; it instantly awakens an intelligent Order Agent within the digital twin - or plainly the manufacturing system. This agent immediately gets to work, dynamically negotiating with Resource Agents —the digital representations of machines, tooling, even the specific human expertise required—to secure optimal production slots and materials in the virtual space, which then collaboratively drives actions in the physical factory assisting operators in orchestrating the operation.

As raw materials enter the facility, each component, or even the nascent product itself, manifests as a Product Agent within this digital twin. This agent carries its own unique digital identity and manufacturing instructions, literally guiding operators to route its counterpart through the physical production line. It's constantly communicating its status and needs within the digital twin, ensuring it receives the precise processing at each stage in the real world. If a specific machine (a Resource Agent ) suddenly reports a slight anomaly – say, a bearing starting to warm up – its built-in intelligence within the digital twin instantly flags it. Instead of waiting for a catastrophic failure, the line's collective intelligence, orchestrated by operators using the various software agents operating within this digital twin environment, might subtly re-route the physical Product Agent to an alternative, readily available machine. Or, better yet, the affected Resource Agent might even initiate a precise, self-healing routine or schedule a just-in-time, predictive maintenance intervention, ensuring that the issue is resolved before it impacts production, all while the Order Agent helps ensure deadlines are still met.

Quality control isn't a post-production check; it's baked into every micro-decision. Product Agents and Resource Agents , leveraging their digital twin data, are continuously monitoring parameters, spotting the tiniest deviation, and triggering immediate corrective actions to ensure "right first time". This seamless, autonomous orchestration – where products find their way, orders fulfill themselves, and machines manage their own well-being, all empowered through the precise, real-time fidelity of their digital twins – transforms the factory into a living, breathing, self-optimizing organism. It’s a level of agility, efficiency, and resilience that felt like pure science fiction in the 90s, but is now can become our tangible reality.

This leads us to an operational reality where the use cases that may seem futuristic are in fact possible , for example:

• Self-Optimizing Production Lines : Imagine entire lines monitoring themselves, sniffing out bottlenecks, predicting breakdowns, and then autonomously re-routing production or tweaking parameters to keep output optimal. Empowering human operators with currently unimaginable support in orchestrating operations.
• Dynamic Resource Allocation : Agents negotiating for machines, tools, and materials in real-time, ensuring every asset is utilized perfectly, eliminating idle time. Elevating scheduling and dispatching to unheard of levels of effectiveness and accuracy. 
• Predictive Maintenance and Self-Healing Systems : No more waiting for a breakdown. Agents predict failures with incredible accuracy and can even kick off self-repair routines or proactive maintenance, slashing downtime and costs.
• Enhanced Quality Control : Agents tirelessly monitoring processes and product quality, spotting deviations instantly and triggering immediate corrective actions. This is "right first time" manufacturing, every time.
• Boosted Compliance : Automated data collection, precise procedure execution, immutable digital records – agentic systems dramatically reduce human error and guarantee adherence to the toughest regulations.
• Unparalleled Traceability : Every single action, every decision by an agent, meticulously recorded. Audit trails become pristine, investigations swift and clear.
• Driving "Right First Time" : By minimizing variability and providing real-time feedback, these systems help ensure products meet quality specs from the outset, slashing costly rework.
• Accelerated Innovation : With more efficient, reliable processes, companies can pour more resources into R&D, bringing life-saving drugs or mission-critical components to market faster.

The journey from the elegant theories of holonic manufacturing systems to the practical, jaw-dropping capabilities of Agentic AI has been long, but intensely rewarding. What started as pure academic curiosity, exploring the power of decentralized, intelligent control, has now become the very bedrock of digital transformation in manufacturing. We’re no longer just imagining; we are actively building factories that learn, adapt, and optimize themselves , powered by the incredible, collaborative intelligence of software agents, physical machines, and empowered humans. It's a testament to the enduring power of fundamental research, a strategic commitment to true digital transformation, and the relentless, accelerating pace of technological innovation.

But hold on, not so fast. Here’s where my passion often turns to frustration. We have the technology today, and more is coming fast – innovation is accelerating at an exponential rate! Yet, a fundamental problem persists in manufacturing: so many companies still don't grasp that adopting digital technology demands a profound transformation , not just a simple upgrade.

The Agility Forum , a 1990 initiative to transform manufacturing, proclaimed that we need to thrive in an environment where change is the only constant. In today's volatile business landscape – marked by unprecedented geopolitical shifts, rapid market fluctuations, and increasingly fragile global supply chains – this is not longer a theory; it's the raw truth of survival. While our research in the 90s certainly anticipated a future of greater dynamism and the critical need for manufacturing systems to adapt , even we couldn't have fully foreseen the sheer velocity and breadth of the disruptions we face now.

This intense, continuous flux means leveraging that change, embracing agility itself, as your ultimate competitive advantage. The sheer ability to adapt, to pivot swiftly, and to continuously evolve your operations is precisely what will differentiate leaders from those left behind. In this dynamic landscape, digital transformation is not a static one time event, nor is it a project with a defined end; it is a continuous process of adaptation to changing business and technological environments - hence we need to start talking about Continuous Transformation .

The core issue isn’t the lack of innovative tools; it’s the mental, organizational, and cultural shift required to truly embrace them - yes its still really about people . Real digital manufacturing means rethinking everything – your processes, your workflows, even how you do business. It’s a complete reimagining, and that's precisely why the original holonic concepts, now enabled by modern tech, offer the inspiration for a breakthrough path. Embrace this paradigm shift, or risk being outmaneuvered by those who do. The future of manufacturing is intelligent, interconnected, and increasingly autonomous, built directly on the visionary concepts laid down decades ago.

Experiencing The Realities of Disruptive Technology

I still remember my first encounter with CAD software in the early 1990s. I had just learned to draft using  drafting table, T-squares, and mechanical pencils. And then here comes CAD, I was excited—and admittedly a little naive—about the possibilities. 

During my university years, I was required to take a compulsory drafting course, even though CAD had already become an industry standard. I spent time drafting by hand, carefully measuring every line and angle, despite knowing that digital tools had long since taken over professional workflows. After the learning how to draft my expectation of CAD was that it would be a tool that would instantly produce my designs for me, yes I had inflated expectations of a magical tool that would do all the work for me. I would think of an idea and like magic, the computer would take care of everything.

Of course, reality quickly set in. Instead of effortlessly generating perfect blueprints, I had to learn an entirely new way of thinking. CAD didn’t replace the design process; it transformed it. I still needed to have the ideas, understand the engineering principles, and apply them. Drawing the first line, starting with defining points then connecting them, was not a trivial task. CAD was a powerful tool, but it required skill, experience, and thoughtful direction to produce anything meaningful. It didn’t do the work for me—I had to learn how to use it effectively.

Fast forward to today, and I see a strikingly similar pattern emerging with the rise of AI—especially Generative AI (GenAI). There are a similar confused and inflated expectation that GenAI will simply generate perfect content, solve complex problems, and even replace human creativity. But just like CAD in the ‘90s, GenAI is not a magic wand. It’s a tool—one that still relies on human intelligence to be effective.

The misconception that AI will replace human ingenuity overlooks a crucial reality: AI doesn’t think, ideate, or problem-solve on its own. It relies on human direction. Just as I had to learn how to structure my designs for CAD, today’s professionals must learn how to craft effective prompts, refine outputs, and iterate toward meaningful results. Prompt engineering isn’t just about asking the right questions; it’s about framing problems, guiding AI to useful insights, and applying critical thinking to refine its output.

Take this blog post as an example. You can’t simply tell a GPT AI tool to “write a perfect blog post this specific comparison” and expect a meaningful result. I had to define the scope, structure the request, and continuously iterate to get content that aligns with what I, emphasis on "I", wanted to convey. These are my ideas and my experiences - I had to include these in the prompt. AI amplifies human creativity—it doesn’t replace it. The key here is that ChatGPT did make me more productive, I wrote this post in minutes versus a few hours, including the graphic.

Just as CAD revolutionized drafting and engineering without eliminating the need for skilled designers, GenAI is reshaping many industries making content creation, coding, and problem-solving—but it still requires expertise and direction. The future isn’t about replacing human intelligence but augmenting it—"humans in the loop." Those who understand how to harness AI and its applications will be the ones who truly unlock its potential, especially in manufacturing operations where precision, problem-solving, and adaptability are crucial. Technology evolves, but one thing remains constant: the value of human ingenuity. Whether it’s designing with CAD or leveraging GenAI, success comes not from the tool itself, but from how we apply it with expertise and intent.

About Accountants and Production Managers: ERP vs. MES

This is a rewrite of a whitepaper that I published in 2004 based on a long and frustrating MES selection process where the "can I use my ERP as MES" misunderstanding went rampant. I find that the discussion is still very relevant today and the topic gets even more confusing with some of the emerging digital technologies in this space. So this is an attempt to bring more clarity...

About ERP and MES

With today’s increasingly accelerating manufacturing technology innovation, digital transformation is critical for staying competitive. Among the key systems that have traditionally driven manufacturing operations are Manufacturing Execution Systems (MES) and Enterprise Resource Planning (ERP) systems. The myriad of opinions and discussion on these concept in the context of digital transformation and therefore understanding the differences between these two systems is crucial. In addition, as digital technologies continue to advance, the lines between MES and ERP are increasingly blurring, especially with the advent of No-Code democratization and Frontline Operations Platforms. I have found that and effective ways to conceptualize this is through the analogy of a production manager and a company accountant.

The Accountant: ERP’s Role in Manufacturing

In the last decade ERP systems have seen massive proliferation into many businesses, including manufacturing businesses. These businesses have invested heavily in ERP systems and today struggle to realize payback from these investments. In the case of manufacturing businesses, realizing ROI is logically focused on the production floor, an area in which ERPs are traditionally considered weak.

As the ERP market becomes increasingly saturated, vendors are looking for ways to increase revenue and expand their footprint. ERP vendors have turned their attention to shop floor management and manufacturing execution systems (MES). By adding MES functionality, they can increase license revenue. 

Consider the role of an accountant in a manufacturing company. The accountant manages financial records, oversees budgets, handles payroll, and ensures that all financial transactions comply with regulations. Their work involves high-level data analysis, financial forecasting, and strategic decision-making that influences the entire organization. This is akin to the role of an ERP system.

At their core, ERP systems are advanced accounting information management systems, they are enterprise-wide management tools designed to integrate various functions across a business. In manufacturing, ERP systems handle tasks such as procurement, inventory management, finance, human resources, and supply chain operations. They provide planning tools like Material Requirements Planning (MRP) and Manufacturing Resource Planning (MRP II), which help companies predict future resource needs based on historical data and forecasts.

However, despite their comprehensive nature, ERP systems are not designed to manage the real-time, dynamic environment of the production floor. They excel at providing a broad, strategic view but lack the granular control needed to manage the intricacies of manufacturing processes. Just as an accountant isn’t equipped to manage the day-to-day operations on the production floor, an ERP system isn’t designed to handle the real-time demands of production management.

The Production Manager: MES’s Role on the Shop Floor

MESs have evolved to address the inherently complex production management functions. An MES is a specialized system focused on the shop floor, where it manages real-time production activities. It coordinates equipment, workers, materials, and processes to ensure that production is carried out according to plan. Unlike ERP systems, MES operates in real-time, responding instantly to changes and ensuring that production goals are met. It tracks production data minute by minute, making it possible to identify and correct issues as they arise.

Imagine the role of a production manager. This person is in the thick of things, ensuring that production runs smoothly and efficiently. They manage workers, monitor machines, and make real-time decisions to keep everything on track. The production manager is intimately familiar with the production process, knows when to adjust schedules, and reacts quickly to any disruptions. This role exemplifies what an MES does in a manufacturing environment.

While ERP provides a high-level overview of production schedules and resources, MES is concerned with execution ensuring that production is executed as planned. MES is deeply integrated with the physical aspects of manufacturing, enabling it to manage the nuances of the production process that ERP systems cannot.

Differences Between MES and ERP

Aspect	ERP  (Enterprise Resource Planning)	MES  (Manufacturing Execution System)
Scope and Focus	Covers a wide range of business functions across the entire enterprise. Designed for strategic planning and resource management across departments.	Specifically focused on the production floor, with deeper engagement in executing production processes, equipment monitoring, and labor management.
Data and Time Frame	Deals with high-level, aggregated data, often historical or forecast-based and financially biased. Works on a broader timeframe for long-term planning and decision-making.	Operates in real-time, handling detailed, granular data from the shop floor, responding immediately to production needs.
Integration and Flexibility	Integrates various business functions but often lacks the flexibility needed for real-time adjustments on the production floor.	Highly flexible and adaptable to the dynamic environment of manufacturing. Integrates with machinery, sensors, and other shop floor systems.
Decision-Making	Supports strategic, long-term decision-making at the corporate level, focusing on overall financial business performance and resource allocation.	Highly flexible and adaptable to the dynamic environment of manufacturing. Integrates with machinery, sensors, and other shop floor systems.

Blurring the Lines: How Digital Technologies Are Redefining MES and ERP

As digital transformation continues to reshape manufacturing, the era of traditional monolithic MES may be coming to an end. New technologies and platforms are presenting a different way to solve the shop floor management coordination challenge. Based on the foundations of MES these new solution incorporate advanced digital technologies such as No-Code, IIoT (Industrial Internet of Things), machine learning, AI-driven analytics, Generative AI and enhanced user interfaces. They offer a more holistic view of manufacturing operations, providing real-time insights that empower workers on the shop floor to make data-driven decisions.

Unlike traditional monolithic MES, which focused solely on production execution, the new breed of technologies leading with the Frontline Operations Platforms encompass a broader range of activities, including quality control, maintenance, lab operations, inventory management, and workforce training. This transformation is a direct response to the growing need for systems that not only manage production but also integrate seamlessly with other digital tools and platforms to enhance overall operational efficiency. It also aligns with the broader digital paradigm, where the goal is not just to automate existing processes but to create a more connected, intelligent, and responsive manufacturing environment. The integration capabilities of Frontline Operations Platforms enable a seamless flow of information between the shop floor and the enterprise level, blurring the traditional lines between MES and ERP.

Several key trends are driving this convergence:

1. IIoT and Real-Time Data Integration:

The proliferation of IIoT devices on the shop floor allows for the real-time collection and analysis of data. This data can be fed into both MES and ERP systems, enabling more informed decision-making across all levels of the organization. For instance, real-time production data captured by IIoT sensors can be used by the ERP system to adjust supply chain logistics or by the MES to optimize production schedules on the fly.

2. Advanced Analytics and AI:

Machine learning and AI are increasingly being used to analyze the vast amounts of data generated by manufacturing processes. These technologies enable predictive maintenance, demand forecasting, and process optimization, functions that traditionally belonged to either MES or ERP. The use of advanced analytics allows these systems to overlap, as both can now contribute to strategic and operational decision-making.

3. Human Centric Platforms:

The new no-code platforms take a human centric approach that break down the traditional process centric solution. They allow to build solution that can be used across manufacturing modalities and also allow to combine MES and ERP functionalities blurring the lines between the two. The new solutions provide a democratized platform for managing all operational process. Workers on the shop floor, managers, and executives can all access the same platform, though with different levels of detail and control, depending on their role.

4. Cloud Computing and Edge Computing:

The shift towards cloud-based solutions and edge computing is enabling greater integration and scalability of MES and ERP systems. Cloud computing allows for centralized data management, making it easier to integrate MES and ERP data. Edge computing, on the other hand, brings computational power closer to the production site, enabling real-time data processing and decision-making that benefits both MES and ERP functions.

5. Interoperability and Open Standards:

Increasingly, manufacturers are adopting interoperable systems that can communicate with each other through open standards. This trend is making it easier to integrate MES and ERP systems, allowing for a more seamless exchange of data and better collaboration between different departments.

The Future: A Converged System for Manufacturing Excellence

The convergence of MES and ERP functionalities into more integrated platforms represents the future of manufacturing. As these systems continue to evolve, they will offer manufacturers the ability to manage both high-level strategic planning and detailed operational execution through a single, cohesive platform. This convergence will enable a more agile and responsive manufacturing process, better equipped to meet the demands of the modern market. The systems are working together more closely than ever, driven by advancements in digital technology that empower manufacturers to achieve new levels of efficiency, flexibility, and innovation.

In Summary...

In the rapidly changing landscape of manufacturing, understanding the distinct yet increasingly interconnected roles of ERP and MES systems is crucial. As digital technologies continue to advance, these systems are evolving and converging, offering manufacturers a powerful toolset for driving operational excellence. The transformation of MES into Frontline Operations Platforms exemplifies this convergence, blurring the lines between strategic planning and operational execution. By embracing these integrated platforms, manufacturers can unlock new opportunities for efficiency, agility, and competitiveness, setting the stage for a new era of manufacturing excellence in the digital age.

Yet, it is naive and risky to assume that one of these systems can be extended to effectively do the other’s job. Similarly, one would not assign an accountant to be a production manager, or vice versa. Each might be an expert in his own field, yet it takes a completely different set of skills, expertise and knowledge to effectively tackle each task.