Qlector

Even a Perfect Production Plan Is Useless Without the Workforce That Can Execute It

Nenad Miric — Wed, 15 Apr 2026 14:39:57 +0000

How Leading Manufacturers Use People-First Production Planning to Build Realistic Production Plans Around Their Actual Workforce Capacity

In modern manufacturing, machines define theoretical capacity – but people ultimately determine what is actually possible on the shop floor. People-first production planning introduces a new perspective: planning production around real workforce capacity rather than forcing people to fit predefined plans.

Our newly developed module, Advanced Workforce Scheduling and Worker Exchange, brings this concept into practice. By integrating data from HR and ERP systems and tracking competencies and attendance, the module provides planners with a clear overview of workforce availability. It enables transparent worker exchange between departments in cases of workforce surplus or shortages, helping manufacturers respond faster to absences and reduce operational friction.

Workforce as the Real Constraint

In many manufacturing environments, production planning still follows a traditional logic: production plans are defined first, and available workers are then allocated to match them.

In practice, this approach often breaks down due to staff shortages, skill gaps, or high absence rates. Production lines that appear feasible on paper may simply lack the necessary competencies on the shop floor.

As a result, planners and supervisors spend significant time coordinating adjustments, searching for suitable replacements, or negotiating workforce availability across departments.

The issue is rarely a lack of data. Most companies already track competencies, attendance, and workstation requirements. The real challenge is turning this information into practical support for daily workforce scheduling decisions.

Introducing People-First Production Planning

While developing advanced worker exchange functionality for a large global manufacturing company in Germany, we introduced the term People-first production planning.

The concept reverses the traditional planning logic.

Instead of defining production plans first and then trying to fit workers into them, companies begin by allocating available workers to production lines, assessing which lines are realistically covered, and then building production plans around actual human capacity.

This shift is becoming increasingly relevant in manufacturing environments where skilled labour is limited, and workforce disruptions are common.

People-first production planning does not replace production planning systems. Rather, it complements them by ensuring that real workforce capacity becomes a central planning parameter.

A System Built on Real Data

The foundation of the system is a unified data layer integrating workforce-related information from existing IT systems.

Through a REST API, the module receives data such as:

employee master data
working-time constraints
confirmed competencies
attendance and absences
production lines and workstations
workstation requirements, including required competencies and the number of workers

Typically, the customer’s IT team or a third-party integration layer ensures that this data is automatically retrieved from ERP and HR systems.

With these inputs consolidated, planners gain a clear and up-to-date overview of workforce availability across shifts and departments.

Workforce Scheduling with a Pool Approach

At its core, the module supports shift-based workforce scheduling using a “pool” approach. Workers available in a shift are considered part of a shared pool from which planners can assign the right competencies to production lines and workstations.

Attendance and absence data are automatically imported from the HR system, giving planners immediate visibility into which workers are available in each shift.

Workers can then be scheduled to production lines based on competencies, availability, and operational constraints. The system supports real-world production scenarios such as:

production lines requiring multiple roles in a team, for example, operator, mechanic, and electrician
specialists who support several production lines, such as one mechanic responsible for multiple lines

Scheduling can be performed in multiple stages, combining manual planning with automated scheduling suggestions. Planners can apply filters, evaluate different parameters, and adjust assignments step by step.

This enables simplified communication and coordination on the shop floor, giving planners visibility and the ability to respond quickly when absences are reported.

Warm, known or new?

Manufacturing environments rarely operate with static assignments. Workers rotate between tasks, build experience on different workstations, and operate under various operational constraints.

The system therefore supports:

tracking “warm-up” and “cool-down” periods
advanced rotation schemes, for example, staying at one workstation for several working days and then rotating
rotation between “warm,” “known,” or “new” workstations, depending on worker experience
the ability to “pin” a worker, allowing supervisors to manually prevent rotations when necessary

At the same time, the system supports worker constraints, such as pre-retirement status or reduced working hours. It also supports organizational and location constraints, determining what each supervisor can see and which production lines belong to the same operational location.

Finally, planners and supervisors can add comments on workers, production lines, and shifts, improving coordination and communication across teams.

An Internal Workforce Marketplace

One of the most distinctive capabilities of the module is the worker exchange mechanism, designed as an internal exchange pool for workforce capacity.

In many factories, one department may temporarily have surplus workers while another department faces higher workloads or unexpected absences.

The system enables a structured exchange process:

Department A creates its workforce schedule and identifies surplus workers.
These workers are added to the exchange pool, including shift and role information.
Department B creates its schedule and identifies a shortage of workers.
Supervisors search the exchange pool for suitable available workers.
A reassignment request is submitted.
Department A confirms the reassignment.
The worker is scheduled to the open workstation.
If necessary, the reassignment can also be canceled.

From Absence to Suggested Worker Exchange

Because the system tracks workforce schedules and historical changes, it can also detect patterns over time.

For example, when a worker reports sick leave, the system immediately identifies the resulting gap in the workforce schedule. Based on available competencies and historical exchange patterns, it can suggest possible replacements.

This opens the door for further automation: absence → scheduling gap → suggested worker exchange. Instead of manually searching through workforce lists, planners receive targeted suggestions that accelerate decision-making.

Benefits for Planners and Shop-Floor Teams

For operational teams, the system improves visibility, communication, and the traceability of scheduling decisions. For management, the benefits extend further. Workforce capacity can be balanced more effectively across departments, improving utilization and enabling more flexible production operations.

Reduced coordination effort, fewer operational bottlenecks, and more realistic production plans ultimately translate into higher productivity and less stress for both planners and shop-floor teams.

Get Your Free People-First Planning Consultation

What would your production plans look like if they were built around the workforce you actually have? Get in touch to discover how Qlector LEAP enables People-first production planning on the shop floor.

The post Even a Perfect Production Plan Is Useless Without the Workforce That Can Execute It appeared first on Qlector.

LEAP Feature Updates for Smarter Production Planning

Nenad Miric — Thu, 12 Mar 2026 09:33:59 +0000

In today’s complex manufacturing environments, production planners must coordinate machines, materials, people, and delivery deadlines while dealing with constant changes on the shop floor.

To support more realistic and reliable production planning, we have introduced several new capabilities in Qlector LEAP. These updates improve how production plans are created, how delivery deadlines are met, and how inventory is managed.

Below is a quick overview of the latest improvements.

Financial inventory forecasts

Inventory planning is often expressed only in quantities, such as pieces, kilograms, or liters.

However, decision makers also need to understand the financial value of inventory.

With the latest update, LEAP can now convert inventory forecasts into financial values using pricing and contract data from ERP systems.

This enables manufacturers to see how much material they have, and how much capital is tied up in inventory, but also brings benefits such as:

faster detection of excess inventory
earlier identification of critical materials
improved purchasing decisions
optimization of warehouse and intermediate inventory levels.

Sequential planning for more realistic production plans

Since production processes consist of multiple dependent steps, one operation often cannot start until another one has been completed. Many planning tools still treat operations as independent tasks, which can lead to unrealistic schedules in which production steps are planned without properly considering their dependencies.

The latest LEAP update introduces sequential planning, an upgrade of the existing planning algorithm that adds sequential verification of production phases.

In practice, this means the system automatically checks:

dependencies between operations within a production order
the completion status of individual phases
dependencies between related production orders
the availability of required input materials.

By verifying all relevant phases and dependencies, LEAP can better estimate whether a production plan is feasible and how long it will realistically take.

This results in more accurate production timelines, faster conflict detection within the production plan, and improved optimization of production scheduling. For production planners, this means plans that better reflect the real constraints of the shop floor.

Backward scheduling for better delivery reliability

Meeting delivery deadlines is one of the biggest challenges in production planning.

Traditional planning often starts from the current date and schedules production forward. However, this approach can sometimes reveal too late that a delivery deadline cannot be met.

With the new backward scheduling capability in LEAP, planning starts from the desired delivery date instead.

The required delivery date is fixed in the system, and LEAP calculates when production must start so the order can be completed on time.

To do this, the system considers multiple real production constraints, including:

available production capacity
shift limitations
work center calendars
operation durations
technological processes and bill of materials
availability of dependent input materials.

Based on this information, LEAP calculates the earliest feasible start date for the production order, making this approach particularly useful in environments where customers provide fixed delivery schedules for the coming weeks.

A more flexible and intuitive planning board

Production planners work with large amounts of operational data every day. To make planning faster and more intuitive, the LEAP planning board now offers a more flexible and customizable layout.

Users can adjust the interface to their needs, resize menus and planning areas, and access additional information or input fields directly within the planning board. This reduces the need to switch between multiple views or tabs during daily planning.

Two additional navigation features further improve usability. The lock function allows planners to freeze a specific view of the planning board when reviewing or comparing parts of the production plan. The target function highlights selected production orders and their related tasks, making dependencies easier to identify.

To Wrap Up

With the latest capabilities in Qlector LEAP, manufacturers can create more realistic production plans, improve delivery reliability, and gain better visibility into the financial impact of inventory.

And better planning not only improves operations, but also directly impacts profitability by reducing hidden inefficiencies across the production process.

On the button below, you can try our simple Hidden Cost Calculator to estimate how much of these hidden inefficiencies could be costing your factory every year.

The post LEAP Feature Updates for Smarter Production Planning appeared first on Qlector.

Workforce Scheduling in 2026: Four Trends Reshaping How People and Production Connect

Nenad Miric — Thu, 26 Feb 2026 08:54:09 +0000

Last time, we shared the five trends we see shaping the shop floor in 2026, and why planning is moving to the centre of competitiveness. This time, we’re zooming in on one specific area that’s quietly becoming a major differentiator: workforce scheduling.

On paper, schedules often look fine. But when the clock strikes 6:00 AM, reality tells a different story. Production plans break down because the right skills aren’t available on the right shift, absences appear at the last minute, overtime spikes, and people are expected to cover too much, too often.

And it’s happening in a tight labour market. In the U.S. alone, Deloitte* estimates that manufacturing may need around 3.8 million new workers between 2024 and 2033, with nearly half of those roles potentially going unfilled, largely due to skill gaps and the difficulty of finding qualified production talent.

In this article, we share four workforce scheduling trends we see shaping the shop floor in 2026, in response to today’s market reality.

Matching Real Demand with Real Skills

For a long time, workforce scheduling was mostly reactive. When someone was absent, a shift became understaffed, and the schedule was adjusted only after the problem had already occurred. These fixes were often made under pressure, typically resulting in overtime for employees, and were implemented too late to avoid disruption.

In 2026, we see a clear shift away from this approach. Instead of constantly reacting, planners are focusing on building schedules that are realistic from the start and flexible enough to absorb change.

It’s no longer just “Who is available?” but “Do we really have the right skills, capacity, and buffers to execute this plan?”

Availability without the right skills often creates hidden problems. Output slows down, scrap and rework risk increase, more supervision is needed, and pressure on the team grows.

That’s why workforce scheduling starts to function as a decision system that connects production demand with real human capabilities and constraints, such as skills, certifications, experience, availability, and real-life limitations. For example, senior workers who avoid night shifts, parents with childcare responsibilities, or employees with health and legal constraints that affect shift eligibility.

When schedules are built around skills and real demand, plans become more realistic. And when plans are realistic, shifts run smoother, surprises are fewer, and firefighting becomes the exception rather than the rule.

This is exactly the gap intelligent workforce scheduling is designed to close. By connecting production demand with real skills, availability, and constraints, modern tools help planners build schedules that are realistic from the start and easier to adjust when reality changes.

Here is an example of such a tool that helps build realistic, skills-based schedules that actually work on the shop floor.

Why Integrated Systems are the New Foundation

In practice, workforce scheduling is not a standalone task.

It feeds, and is fed by production plans, time tracking, labor costs, and compliance data. When tools are disconnected, and spreadsheets do the heavy lifting, the outcome is familiar: manual work, duplicated data, errors, and slow reactions when something changes.

In 2026, we increasingly see manufacturers move toward integrated workforce systems. By connecting scheduling with production data, HR information, and time tracking, planners gain better visibility and fewer manual steps.

That integration enables faster and more confident decisions, and ultimately reduces administrative load, making workforce scheduling smarter, not more complicated.

How Employee Self-Service Saves the Schedule

People swap shifts, get sick, have personal commitments. When every small change requires phone calls, emails, and approvals across multiple layers, scheduling quickly turns chaotic.

Modern workforce systems are addressing this with structured flexibility. Employees can request shift swaps, claim open shifts, and manage changes through mobile-friendly workflows, while still making sure the right skills are in place and rules are followed.

This doesn’t reduce control, but removes unnecessary manual work and delays. And with fewer obstacles, schedules become far more resilient to everyday reality on the shop floor.

Hardcoding Safety and Fairness into Every Shift

Factories can’t afford burnout, and they can’t afford unsafe fatigue patterns either.

This matters operationally because chronic fatigue shows up as more mistakes, more quality issues, and more incidents.

In 2026, workforce scheduling becomes more deliberate about how work is shared over time, limiting long night-shift sequences, avoiding constant overtime for the same people, protecting rest periods, applying clear rotation rules, and distributing demanding shifts more fairly.

A schedule that looks efficient but breaks people isn’t efficient at all. It’s simply a delayed cost.

To Wrap Up

This year, it has become clear that workforce scheduling is evolving beyond simply covering shifts. It is increasingly about connecting people, skills, and capacity with real demand on the shop floor.

That’s the approach behind Qlector’s Intelligent Workforce Scheduling solution, which has been recognised with a Silver Award for Best Innovation and is already used by one of the largest manufacturing companies in Europe to plan and optimise shifts for over 800 production workers at a single plant.

As shop floors become more complex and less forgiving, workforce scheduling will increasingly define how well plans survive contact with reality.

Curious how your workforce scheduling compares? Discuss it with one of our experts to see what’s working, what isn’t, and where there’s room to improve.

Source
*Deloitte Insights: Supporting U.S. Manufacturing Growth Amid Workforce Challenges. Available: here.

The post Workforce Scheduling in 2026: Four Trends Reshaping How People and Production Connect appeared first on Qlector.

Why Production Plans Still Fail and What 2026 Is Teaching Us About It

Nenad Miric — Thu, 25 Dec 2025 08:01:25 +0000

If you walk into a modern factory today, you’ll see smart machines, sensors everywhere, and a flood of data. And yet, production plans still break.

This shouldn’t come as a surprise. According to a recent industry survey*, 70% of manufacturers still collect data manually, creating a bottleneck that slows decision-making and exposes the limits of traditional planning in today’s fast-changing production environments.

Here are five trends we see shaping the shop floor in 2026, and why planning has moved to the centre of competitiveness:

Static Plans Go to History

Once upon a time, production plans were built weekly or monthly and then protected like a sacred object. In reality: machine hiccup, material delay, priority change.

And suddenly, the plan is obsolete.

In 2026, we’re seeing a clear shift toward continuous planning, where plans adapt as reality evolves to stay relevant. That means:

Plans update instead of being defended
Replanning is normal, not a failure
Decisions are based on what’s happening now, not what was expected yesterday

Of course, continuously updating a production plan sounds simple in theory. In practice, it only becomes possible when planning is supported by systems that can handle complexity faster than humans can.

And that leads us to the second important trend…

AI Becomes a Planning Partner

The reason continuous planning is finally becoming realistic is simple: AI can now do in seconds what used to take planners hours.

For a long time, AI in manufacturing focused mainly on historical analysis: what went wrong, where time was lost, and which patterns appeared. But the real shop-floor question for 2026 is different: “What should we do now?”

This year, we’re seeing AI move away from reporting and toward becoming a decision partner:

suggesting updated plans
automatically generating re-optimised schedules
balancing trade-offs between delivery dates, work-in-process, and overtime

But there’s a next step emerging: AI agents. We’ve written about this in more detail here.

Instead of only recommending changes, AI agents can act within predefined rules, monitoring events, detecting deviations, and even initiating corrective planning actions autonomously. They see problems and act on them when speed matters.

This doesn’t replace planners, but rather removes the chaos between problem and decision, and increasingly, between decision and action.

Digital Twins Evolve into Decision Engines

Their popularity continues to grow this year as well. Although digital twins used to be mostly about nicely rendered visuals and dashboards that looked great in presentations, the problem was that visuals alone couldn’t make decisions.

In 2026, we’re seeing digital twins evolve into decision tools. Instead of guessing, “If this machine stops, what happens?”, teams simulate the scenario and test the impact before committing to action.

When integrated with AI, digital twins can analyse complex datasets and adapt decision-making on the fly, leading to better efficiency and less downtime.

Planning for Uncertainty Becomes the Norm

We’ve all seen supply chains get disrupted, often without warning. Modern factories are responding by building resilience and agility into planning, not just execution.

That means:

Planning with uncertainty in mind
Quickly pivoting between suppliers and routes
Rebalancing priorities when external conditions change

In practice, resilient planning means seeing risk and being able to act on it, because a plan that can’t adapt to supply variation is just a fragile strategy.

People, Not Just Machines, Define Performance

Machines and automation get a lot of attention. But people still run production.

In 2026, one of the biggest differentiators we see is workforce effectiveness, rather than some new sensor or algorithm.

That means:

Matching the right people to the right tasks
Creating schedules that account for skills, availability, and shift changes
Making sure plans are executable with real human capacity

Tools that support workforce scheduling are not here to only fill shifts, but also to connect human reality with production reality. When planners can trust that workforce constraints are built into the plan, everything becomes smoother, resulting in fewer firefights, higher productivity, and more realistic expectations.

Final Thought

In 2026, manufacturing competitiveness doesn’t depend only on machines, automation, or data dashboards, but also on how good your planning is in an uncertain, fast-changing world like the one we live in today.

AI-driven planning, decision-ready digital twins, supply-chain resilience, and human-aware workforce scheduling are no longer “nice to have.” They are becoming operational standards.

And planning, the quiet backbone of execution, is finally stepping into the spotlight it deserves.

Interested in improving your production planning and reducing operational costs? See how much better planning could save you in practice with our Hidden Costs Calculator:

Sources
*Manufacturing Leadership Council – Seventy Percent of Manufacturers Still Enter Data Manually. Available: here.

The post Why Production Plans Still Fail and What 2026 Is Teaching Us About It appeared first on Qlector.

Four Steps to Implementing AI in Production Planning and Scheduling

Qlector LEAP — Sat, 08 Nov 2025 08:22:51 +0000

Qlector Research (Jun–Sep 2025)
Qlector interviewed several of Slovenia’s largest, high-performing manufacturing companies between June and September this year. We wanted to understand their day-to-day approach to production planning, what the real challenges are, how they are solved, and what they intend to invest in next. The results are relevant to plant and operations leaders responsible for OTD, WIP, and cost control.

ERP Everywhere, MES Common, MRP Universal

How quickly you can introduce artificial intelligence (AI) into production planning depends on the company’s digital maturity and data culture. In our experience, the entire process involves four main steps: an organized factory calendar, a correct plan, accurate simulations, and finally, the holy grail of any manufacturing company – automated production planning and scheduling.

Based on our rich experience in CEE and the DACH region with the implementation of operational AI and digital twins, we should emphasize that their introduction is not a piece of cake. It requires a certain level of digital maturity and a corresponding data culture in the company, as well as changes in organizational processes if they are not designed to ensure optimal workflow.

The last 10% remains for people

To provide guidance and assistance in this process, we have compiled a list of all the necessary steps that will lead you to automated production planning. Practice shows that even when implementing AI solutions, the last 10% will probably always be left to humans. They know the dynamics of the company’s current needs and decisions and bring a business context to planning that is not captured and visible in IT systems.

Small victories for motivation

The implementation process is designed to gradually build users’ digital competencies, increase trust in AI, and motivate users with small victories in the process. This is in contrast to the traditional implementation process, which focuses on the small tasks without the big picture in mind.

Step #1 - Factory calendar

The factory calendar represents the basic framework of a factory on which we build a digital twin and is the foundation for predictions based on data from MES and ERP systems. So the first necessary step is to have an orderly factory calendar in the ERP system that includes all shifts, machines, and people capacities. If for some reason the company does not have this, it can start managing the factory calendar in the Qlector LEAP solution.

Step #2 - Correct plan

The second step refers to the correct plan, which includes all planned work orders and stock. The work orders must be organized to reflect the actual situation on the shop floor. Similar to the factory calendar, companies can use the Qlector LEAP solution instead of ERP for this step. With our manual planning board feature, planners can simply edit the plan by dragging & drop work and planned orders and write changes back to ERP. A prepared plan is automatically passed to a shift leader to organize people and dispatch shifts on the shop floor.

Step #3 - Accurate simulation

Once the plan is prepared, we can begin production simulations and predictions. It is important that the predictions are realistic and that we can verify them together with the users – whether what we predicted actually happened. We guide users through the process of building trust in AI and predictions. We empower them with a systematic comparison of predictions and realization.

Automatic maintenance of master data by digital twin

In this step, the AI is already building a digital twin of the entire factory. If we compare the old way with the new way, we can see that a lot of time and energy is now saved because AI takes care of the master data. Namely, the digital twin learns what is the realistic time for tool change/cleaning, the real-time work order start, and end, what the real downtime or scrap is, etc.

Before the implementation of AI, master data maintenance was a repetitive and manual task that took a lot of resources and was not done often enough. At the same time, all production processes depend on them, so their quality and availability are important success factors.

Step #4 - Automatic planning

Now that we made sure that production times are correct, we have actually validated the digital twin of the factory. And so we came to the final step, automatic planning. Our experience shows that the winning combination is made of 90% artificial intelligence and the last 10% is still in the hands of humans, who can take into account current business needs and decisions and simply drag & drop a specific work order.

OEE that is at least 5% higher!

If we follow the described steps of digital maturity and the gradual introduction of AI into production planning and scheduling, we can ultimately reduce the number of planners by half, achieve an OEE that is at least 5% higher, and significantly reduce stock levels.

From end product to raw material

In doing so, we follow the “pull” principle – from end product to raw material. For any manufacturing company, it is crucial to achieving a delivery accuracy of at least 95%. So the end product we have to deliver to the customer is the best starting point.

Are you interested in what kind of value an operational use of AI can bring to your company?
Book your FREE 15-Minute consultation!

The post Four Steps to Implementing AI in Production Planning and Scheduling appeared first on Qlector.

How Leading Manufacturers Plan Production: 50% Still Depend on Excel and Paper

Nenad Miric — Wed, 29 Oct 2025 08:28:38 +0000

ERP Everywhere, MES Common, MRP Universal

Every company in the sample runs an ERP backbone. Solutions range from HTS Solution and in-house platforms to programs to roll out SAP S/4HANA at multiple sites. Three out of four also operate an MES layer, sometimes standalone with PLC connectivity on the lines, sometimes as part of the ERP estate, at least partially. MRP is universal across the board. None of that will surprise plant managers, but it matters: decisions about planning tools do not start from a greenfield site.

Planning Gap: 50% Still Depend on Excel and Paper

Every company surveyed plans in ERP; about half explicitly reference SAP APO. At the same time, 50% of companies still use manual methods such as Excel spreadsheets or paper-based planning as additional support to their ERP system. In most cases, Excel is used for shift-level micro-scheduling or annual plans.

Inefficient Planning Generates Substantial Costs

This hybrid approach continues to characterize planning processes in many factories, even though manual planning tools lack real-time visibility, rely on individual expertise, are prone to errors, and cannot quickly adapt to real-time changes.

While such methods may appear adequate in some cases, inefficient planning processes often generate substantial hidden costs, estimated in many manufacturing companies at 5–10% of annual revenue.

Efficiency Is Crucial, but Mostly Rated as Average

Here is the paradox: planning is rated as very important or critical by all respondents, yet only 25% consider their planning processes very efficient. The remaining 75% describe them as average. For executives, this gap represents a clear opportunity: planning is central to business performance, but most teams acknowledge that it could operate much more effectively.

Pain Points: Volatility, Micro-Scheduling, and Machine Sequencing

When asked where the main challenges lie, respondents cited a broad range of planning issues:

Demand volatility and its impact on finished-goods inventory.
Micro-scheduling in Excel that disrupts flow, complicates split orders, and slows operations.
Machine sequencing that must account for highly specific production constraints without reducing throughput (for example, chemical-free paper changeovers).

KPIs: OTD Leads, WIP Follows, and the Role of In-House Metrics

The most frequently cited KPIs are OTD (measured or being introduced by approximately 50% of respondents) and WIP (around 25%). In addition, plants track a range of in-house KPIs such as plan vs. actual, worker efficiency, first-pass yield, OEE, plan accuracy, scrap, and inventory health (including sales trends vs. forecasts).

This combination of KPIs underscores a simple truth: any planning tool that cannot address both the corporate language (OTD, WIP) and the local dialect (plan adherence on Line 3, changeover losses on Press 6) is unlikely to succeed.

Investments Clustered Around Three Themes

Over the last year, investments concentrated on three areas (each mentioned by about 50% of companies): new lines to increase capacity, automation and warehousing, and QA camera systems to strengthen quality control.

Digital Planning Investments Largely Undefined

When asked whether they plan to invest in the digitalization of production planning within the next 12 months, the vast majority of companies reported that they do not have defined plans in this area.

Half of the respondents answered “don’t know.” The reasons vary: some are bound by group-level IT strategies that avoid local solutions, while others express interest in digitalization but do not yet have a concrete plan in place. A quarter of respondents answered “no,” yet emphasized that they should invest in this area.

Pilots with limited integration therefore represent a pragmatic entry point.

Repetitive Work Is Real and Quantified

When we asked planners to estimate the share of repeatable, structured steps in their daily process, answers clustered at 30–50%. Most reported daily performance tracking and morning briefings for the current or next day’s plan. For leaders focused on productivity, this represents a valuable opportunity: anything done the same way every day is a candidate for streamlining or AI assistance.

Document Load

Half of the respondents reported heavy document handling, such as emails, purchase orders, and small-order administration, especially in order management. A quarter said it is minimal because information is cleaned and structured daily. This contrast mirrors the maturity curve: plants with disciplined data hygiene spend less time shuffling PDFs and more time executing.

Where AI Would Help First

Asked for one domain where modern digital tools such as AI would help most, manufacturers converged on three fronts:

Inventory and SKU management: daily stock monitoring and forecasting stock-out risk.
Supply chain and quality: supplier reliability scoring, forecast vs. actual monitoring, and correlating final product quality with incoming component quality.
Operational planning: delivery date calculation, workforce scheduling, and machine load optimization.

The Bottom Line

The current state of production planning in Slovenia’s largest, high-performing manufacturing companies is clear: ERP systems are widespread, MES solutions are common, and MRP has become standard. Yet planners still bridge critical tasks with spreadsheets, and most organizations rate planning performance as average despite its recognized importance.

The practical path forward is also clear: reinforce micro-scheduling, align metrics from plant to line, validate the gains of AI through focused pilots, and apply AI where work is repetitive and rules are known.

The outcome is disciplined, repeatable improvement in OTD and WIP without immediate capital investment.

Identify the Hidden Losses in Your Production Planning

If you would like to find out how much money your factory may be losing due to inefficient production planning and identify potential savings, we invite you to schedule a short, free consultation with our experts:

The post How Leading Manufacturers Plan Production: 50% Still Depend on Excel and Paper appeared first on Qlector.

Why Manufacturers Lose Millions Every Year: The Illusion of ERP Normatives in Production Planning

Nenad Miric — Mon, 29 Sep 2025 12:56:36 +0000

While manufacturing companies lose millions due to static, outdated ERP normatives, Qlector LEAP brings together actual, historical, and normative data in real time to deliver realistic production time predictions and reliable production plans.

When we meet potential users at events or sales presentations, we almost always get the same question: What makes Qlector LEAP truly unique in the sea of AI solutions and buzzwords that often leave companies confused and stuck in FOMO, worried about missing out on opportunities?

This blog aims to explain why Qlector LEAP is a unique solution that continuously compares ERP master data normatives with actual shop floor performance from MES, using these insights to generate realistic production plans for the future.

From Work Orders to Realistic Production Plans

Qlector LEAP tracks execution across work orders and identifies whether production is running at, below, or above the ERP normatives. It considers both historical company data and ERP normatives, then uses advanced machine learning models to capture deviations between planned and actual performance. These deviations are directly incorporated into future production plans, making them more reliable and realistic.

In theory, companies should track actual production times and quantities and compare them against ERP normative data – for example, on a quarterly or semi-annual basis. In practice, this rarely happens, often due to conflicting interests and strategic negotiation dynamics.

Sales Conflicts

The first conflict typically arises with the sales department. Sales performance is closely tied to ERP normatives, which define expected time and material consumption and form the basis for cost calculations and sales prices. If the normatives are unrealistic, then the cost calculations are wrong, which distorts margin reporting and sales performance metrics. For that reason, sales teams are rarely willing to accept changes to ERP normative data unless top management is involved – a negotiation process that is typically slow and complex.

Union Conflicts

The second conflict often comes with labor unions. ERP master data normatives serve as a benchmark for expected worker productivity, defining how many units should be produced in a given time. They form the basis of wage systems, bonuses, and performance evaluations. If normatives are unrealistic, they fuel employee dissatisfaction, union disputes, and undermine fair compensation frameworks.

Why Realistic Plans Matter

With realistic production plans in place, companies can forecast material consumption, plan tool changes more accurately, and rely on actual cycle times and finished volumes. This is critical to maintaining high on-time delivery rates and keeping customers satisfied.

Automated Comparisons for Future Plans

The advantage of Qlector LEAP is that it automatically compares actual performance with ERP normatives and historical data—on a weekly or even daily basis. If production is consistently running above or below normatives, the model recognizes this and incorporates it into future plans, ensuring they are far more realistic.

The Key Differentiator

This is the key differentiator compared to other solutions. We call it the process digital twin of the factory. It is the heart of our solution – a powerful and sophisticated combination of data, machine learning methods, and algorithms. The crucial point is that this self-learning digital twin delivers actionable insights and realistic predictions for planners, instead of lagging deviation analyses that arrive too late to improve current plans and schedules.

Transparency and Visibility

Beyond predictions, Qlector LEAP also addresses the challenge of limited visibility in production planning. By creating a unified view of orders, resources, and constraints, it provides planners and managers with full transparency into what is really happening in production. This eliminates blind spots that cause inefficiencies, miscommunication, and misalignment across teams.

Optimized Work Order Sequencing

In addition, Qlector LEAP ensures that production runs are executed in the most efficient order. Its AI-driven optimization of work order sequences minimizes downtime, reduces unnecessary changeovers, and streamlines workflows. This transforms sequencing from a manual, error-prone task into an automated, intelligent process that significantly boosts on-time delivery and overall equipment effectiveness (OEE).

From Hidden Costs to Millions in Savings

It is difficult to understand why companies continue to rely on the illusion of ERP normatives in production planning—especially when it is clear that realistic predictions, full production transparency, and optimized sequencing provide far greater flexibility and proactive responsiveness to market changes and uncertainties.

At the same time, research and benchmark studies show that manufacturers lose 5–10% of annual revenue due to inefficient planning. Even modest improvements – and the benefits unlocked by Qlector LEAP – can generate millions in savings.

Seamless and Strategic

Since production planners cannot directly change ERP normative data themselves, our solution eliminates the need for exhausting negotiations between management, sales, and unions – seamlessly providing a strategically acceptable solution for all stakeholders.

Calculate Your Hidden Costs

By implementing Qlector LEAP, manufacturers gain an automated, technologically advanced, and strategically sound solution to a problem that has long burdened production planners. To help companies clearly see the financial impact of inefficient planning, we also provide an easy-to-use Hidden Costs Calculator that quantifies hidden losses and highlights the potential savings achievable with Qlector LEAP.

Book Your Free Consultation

If you’d like to find out exactly what hidden costs inefficient planning may be causing in your factory – or if you simply want to explore the opportunities that intelligent production planning can unlock for you – book your free introductory call here.

The post Why Manufacturers Lose Millions Every Year: The Illusion of ERP Normatives in Production Planning appeared first on Qlector.

How AI Is Quietly Revolutionizing Downtime Management in Manufacturing

Qlector LEAP — Sat, 26 Jul 2025 09:06:32 +0000

Downtime is one of the most expensive and stubborn challenges in modern manufacturing. But unlike traditional methods for production planning and scheduling, new industrial AI-based solutions are not fighting it with guesswork.

By leveraging Machine Learning and Digital Twin technologies through advanced planning and scheduling (APS) systems, manufacturers are now able to simulate thousands of scenarios, anticipate disruptions, and act faster than ever before. Solutions like Qlector Leap are bringing this transformation to life, offering tools built for today’s production complexity and uncertainty.

Why Downtime Is Everyone’s Problem

The scale of the issue is staggering. In automotive manufacturing, the cost of one hour of unplanned downtime has doubled since 2019 and now exceeds $2.3 million. Energy price spikes, labor shortages, and volatile supply chains only add to the pressure. Globally, the world’s 500 largest companies lose nearly $1.4 trillion annually due to unplanned downtime – that’s 11% of their total revenue.

Industrial AI has emerged as a powerful counterforce. Half of manufacturers now use at least one AI-driven solution, up from just 25% in 2019. Clearly, companies are no longer waiting for systems to fail before they act.

What Causes Downtime?

On the surface, downtime often looks like bad luck. But under the hood, it’s frequently caused by predictable shop floor dynamics:

• Inventory imbalances and delayed material supply
• Labor issues such as unexpected absences or skill mismatches
• Tool preparation and machine availability problems

This is where AI-based APS tools, such as Qlector Leap, make a real difference. They pull in ERP and MES data to deliver a continuously updated picture of operations. By comparing ERP norms to real-time production metrics, these systems flag anomalies, learn from ongoing outcomes, and refine planning logic on the fly.

In workforce scheduling, for example, AI can construct a digital twin of every worker, taking into account their availability, limitations, skills, experience level, and productivity. This ensures optimal staffing and shift planning, dramatically reducing human-induced downtime.

Unlike traditional APS solutions that depend on static ERP norms, Qlector Leap uses historical and real-time data to uncover the early signs of issues – whether it’s a stockout, an upcoming absence, or a delay on the line. With this insight, planners can act before problems become disruptions.

Key Technologies That Help Prevent Downtime

These eight technologies form the core of modern AI-based APS systems, empowering manufacturers to detect, prevent, and respond to disruptions before they cause downtime. This explanation is based on the work and expertise of the team behind Qlector Leap, who developed and implemented these capabilities in real manufacturing environments.

1. Probabilistic Machine Learning: Recognizing Patterns That Lead to Downtime

Probabilistic machine learning enables accurate forecasting in manufacturing, even when data is incomplete or highly variable.

Instead of relying on a single “most likely” outcome, probabilistic models assess multiple possible scenarios and their likelihood. For instance, the time needed to complete an order is influenced by many factors – such as machine availability, material supply fluctuations, or worker experience. Probabilistic models incorporate all these uncertainties to help planners make better-informed decisions.

By recognizing patterns that typically lead to bottlenecks or downtime, these models enable the system to anticipate and mitigate risks before they occur.

2. Digital Twin: Detecting and Predicting Potential Disruptions

A digital twin is a real-time, virtual representation of all production processes on the shop floor. Continuously updated with real-world data, it provides a dynamic “smart map” of manufacturing operations – capturing material flows, tool changes, workforce schedules, and machine statuses.

One of its key strengths lies in detecting and predicting potential disruptions or downtime. By combining historical insights with live process signals, the system can identify issues such as imbalanced workloads, critical material shortages, or delays due to inefficient tool changeovers. Through simulation, the digital twin also enables companies to evaluate the impact of such disruptions in advance and take proactive measures to optimize flow and minimize downtime.

3. Monte Carlo Simulations: Repeated Calculations Using Random Sampling

Monte Carlo simulations are a method where the system performs repeated calculations using random sampling to generate realistic scenarios that support decision-making.

In manufacturing, these simulations help answer questions such as: “What’s the probability that this order will be completed on time?” By modeling thousands of possible outcomes—considering machine breakdowns, supply delays, or variations in worker efficiency— AI-based APS systems can provide planners with a clear view of potential risks and uncertainties.

This enables early identification of process bottlenecks and supports the testing of various strategies to resolve issues before they occur.

4. Genetic Algorithms: Inspired by natural evolution

Inspired by natural evolution, genetic algorithms are used to find optimal solutions through iterative improvement.

In manufacturing, they are often applied to schedule optimization – such as the best way to allocate machines and workers to reduce downtime and improve throughput. Rather than testing every possible combination, the system uses a “survival of the fittest” approach to generate and refine increasingly effective production plans.

Genetic algorithms help eliminate organizational downtime by optimizing resource allocation and identifying the most efficient configurations of production processes.

5. Active Learning: Enhancing Models Through Human Expertise

Active learning is an approach where AI systems actively involve human experts to improve prediction accuracy—especially in unfamiliar or exceptional situations.

In manufacturing, this means the system doesn’t just passively analyze data—it also learns from operator feedback. For example, when the system proposes a schedule change, operators can validate its feasibility, helping the model adjust based on real-world human expertise.

This interaction helps identify organizational challenges that automated models alone may overlook, and supports continuous improvement through human-machine collaboration.

6. Reinforcement Learning: A Trial-and-Error Approach for Smoother Operations

Reinforcement learning works through trial and error, continuously adjusting to new conditions to improve outcomes.

Just like a person learning to ride a bike, the system learns which actions lead to the best results. In production planning, this means continuously monitoring the manufacturing process, suggesting improvements, and refining its strategies based on feedback.

By detecting bottlenecks and experimenting with corrective actions, reinforcement learning contributes to the ongoing improvement of manufacturing efficiency.

7. Robust Regression: Trustworthy Planning Despite Imperfect Data

Robust regression is a modeling technique designed to learn from data even when that data includes extreme values or errors. In manufacturing environments, this is critical – data may be affected by faulty sensors, incorrect entries, or rare operational events. Rather than allowing these anomalies to distort predictions, robust regression identifies and downweights their influence.

This increases the reliability of planning and scheduling systems, particularly in complex, noisy, or nonlinear production conditions.
By ensuring that rare or erroneous data points do not mislead the model, robust regression enables more stable, trustworthy decision-making.

8. Non-Parametric Empirical Distributions: Turning Variability into Predictive Power

Traditional modeling approaches often assume data follows a known shape, like a normal (bell-curve) distribution. But in real-world manufacturing, data often behaves differently.

Non-parametric empirical distributions allow models to learn directly from historical data without imposing assumptions on the data’s shape. This enables them to capture complex, real-life patterns – such as multimodal distributions or long-tailed behavior.

By working with realistic distributions, AI-based APS systems can make more accurate predictions and more effectively detect anomalies, predict downtime, and identify potential bottlenecks in production.

The shift is Happening Today

The shift toward AI-enhanced production planning is no longer theoretical. It’s happening today – quietly but profoundly changing how manufacturers approach downtime. Tools like Qlector Leap give planners and managers not just data, but foresight. And in modern manufacturing, foresight is everything.

Learn More with Qlector Team

Want to learn more about how Qlector Leap uses these technologies to support production planners?

Book your 20-minute introductory consultation below.

The post How AI Is Quietly Revolutionizing Downtime Management in Manufacturing appeared first on Qlector.

The ‘Reality Gap’ – A Silent Killer of Your Manufacturing Operations

Qlector LEAP — Sat, 14 Jun 2025 11:56:26 +0000

An hour of unplanned downtime can cost up to $2.3 million for large manufacturing companies operating in the automotive sector. For small and medium-sized enterprises, the cost can reach $150,000 per hour.

These staggering figures underscore the critical importance of addressing the Reality Gap – the disconnect between production plans and actual shop floor operations. This gap contributes significantly to unplanned downtime, leading to missed deadlines, inflated operational costs, and diminished customer trust.

Why Traditional Planning Falls Short

In addition to volatile demand, supply chain uncertainty, and pressure for operational excellence, today’s manufacturing sector faces a quiet threat – one that many leaders don’t even realize exists.

While they continue to rely heavily on spreadsheets and outdated Enterprise Resource Planning (ERP) systems, they often overlook the fact that these legacy tools mistakenly assume fixed (or even normative) lead times, perpetually functioning machinery, and a constantly available workforce.

In reality, however, production floors are dynamic – full of unexpected breakdowns, absences, and delays – creating a chasm between theoretical planning and real-life execution. This mismatch is one of the key contributors to costly and recurring downtime in manufacturing operations.

From Static Planning to Constant Chaos

Legacy planning systems, built on fixed timelines and oversimplified models, are fundamentally inadequate. Shop floors constantly grapple with fluctuating setup times, variable performance levels, and unforeseen constraints. This persistent disconnect results in chronic operational issues—missed deadlines, excess inventory, and a reactive, crisis-driven workplace culture.

Bridging the Reality Gap

Addressing this hidden challenge requires manufacturers to transition from reactive to proactive management. By anticipating issues before they occur, taking preventive measures based on accurate data, and shifting from constant firefighting to strategic improvement, manufacturers can gain greater control. This transformation helps factories respond effectively to disruptions, ensuring smoother, more productive operations and significantly reducing the risk of unplanned downtime.

Why Advanced Planning & Scheduling (APS) Tools Are Essential

The solution lies in Advanced Planning and Scheduling (APS) tools enhanced by Artificial Intelligence and Machine Learning technologies. Unlike traditional methods, these solutions integrate directly with Manufacturing Execution Systems (MES), capturing real-time data from the production floor. Additionally, they create a digital process twin, offering an accurate, dynamic simulation of actual shop-floor behavior. Such advanced capabilities result in realistic and resilient schedules that genuinely reflect manufacturing realities—and help mitigate downtime before it happens.

Realistic Predictions – A New Foundation for Operational Excellence

The primary benefit of adopting AI-based APS tools is realistic, data-driven planning. Through realistic predictions, manufacturers achieve optimized schedules that are not only theoretically sound but also achievable in real-time operations. This significantly improves resource utilization and reduces unnecessary expenditures such as waste, excessive inventories, and expedited shipping costs. Manufacturers adopting APS see immediate improvements in operational excellence, translating into higher customer satisfaction through reliable delivery and improved On-Time Delivery (OTD) performance.

The Transformative Power of Machine Learning

Machine learning-based APS systems harness historical data to close the gap effectively. With MES integration ensuring instant data capture, manufacturers gain unprecedented insights into real-time operations. The digital twin further enhances predictive accuracy, enabling achievable and resilient scheduling. These sophisticated predictive tools transform planning processes, dramatically enhancing efficiency and adaptability in an increasingly volatile manufacturing environment.

Real-Life Benefits: From Firefighting to Thriving

Ultimately, implementing modern APS solutions results in a host of practical benefits. Manufacturers enjoy schedules they can trust, controlled costs, climbing On-Time Delivery rates, and teams that shift from daily firefighting to strategic improvement. This transformation isn’t merely about adopting new tools—it’s about a fundamental shift in operational mindset, from guesswork to grounded execution and from reactive tactics to resilient strategies.

Close the Gap: A Real-World Perspective

In one of our recent projects, we partnered with Domel, a leading manufacturer of electric motors and components with 1,200 employees and €200 million in revenue, to close the Reality Gap with a more realistic approach to planning and scheduling, achieving:

€220,000 in annual savings at just one plant
25% reduction in downtimes
75 hours per week saved for planners
10% improvement in JIT delivery

If you’re curious to explore the details, you’re welcome to book a free consultation to walk you through the case study.

Downtime cost estimations referenced in this article are based on findings from Siemens ”The True Cost of Downtime 2024” Report.

The post The ‘Reality Gap’ – A Silent Killer of Your Manufacturing Operations appeared first on Qlector.

AI Agents Are Coming to the Shop Floor – Here’s Why It Matters

Qlector LEAP — Thu, 15 May 2025 12:03:13 +0000

Have you wondered what’s next in production planning? While AI continues to dominate the conversation, two terms are quickly rising: AI Agents and Agentic Workflows.

In this blog, we’ll explain them in simple terms—what they are, how they work on the shop floor, and why they matter to you.

If you’re still juggling multiple systems and spreadsheets, you should keep reading.

What are AI agents and agentic workflows?

Imagine a factory full of systems, each knowing a different part of the story – ERP manages supply and business operations, MES tracks production on the shop floor, QA monitors product quality, and HRM oversees workforce data. All of them are busy “talking,” but no one’s quite coordinating the whole conversation.

That’s where AI agents come in.

They’re like smart assistants that:

Spot when something happens (e.g., a delivery delay or quality alert)
Decide on the best response (shop for alternative parts, alert the planner, adjust schedules)
Either handle it themselves or bring in a human when needed.

These agents carry out tasks that are traditionally managed manually, significantly enhancing efficiency, reducing errors, and freeing human planners for strategic decision-making.

When you link several AI agents in sequence, you create an agentic workflow: a living chain of automated steps that routes data, applies logic, and hands off to people only at the right moment.

Everything is tracked, compliant, and ready for audit

What does this mean for Qlector LEAP?

At the recent event “Artificial Intelligence in Practice – Innovations and Challenges”, hosted by Slovenian Sovereign Holding (SDH) and the Jožef Stefan Institute, our CEO Mateja Lavrič and CPO Viktor Jovanoski took the stage to share not only what Qlector is today, but where it’s headed next.

They announced that we plan to enhance our solution, Qlector LEAP, by focusing on AI agents and agentic workflows, and by introducing new features such as:

Chat with Documentation

Soon, LEAP users will be able to interact with various types of documentation (e.g., user manuals, internal documentation, records of past incidents, etc.) through a chat interface powered by Large Language Models (LLMs).

When a problem arises, users (such as planners) will be able to simply ask a question and receive fast, relevant answers based on documentation and past experiences.

Smart Daily Summaries for Planners

LEAP will also be able to generate daily insights such as summaries of recent production downtimes, stock-related warnings or workforce-related warnings, and suggested mitigation actions for each issue.

This automation will reduce time spent on manual reporting and help planners start their day better informed and ready to act.

Both features run on the same agentic backbone, proving that agents aren’t a buzzword, but rather a real engine.

Why this matters now

Modern shop floors are more complex than ever, and planners shouldn’t have to track every detail alone.

Qualified planners are in short supply, yet decisions still need to be timely, accurate, and fully auditable.

By automating context gathering, planners will free up their time to think strategically rather than hunt for data. Agentic workflows will handle the routine noise—connecting systems, surfacing insights, and logging every step—so planners can focus on the big picture.

Ultimately, this technology is not here to replace planners, but to give them clarity and the time to act where it counts. This new layer of intelligence is only just beginning, and we’re proud to be at the forefront of its development.

Want to see Qlector LEAP in action?

Book a DEMO to explore how LEAP can transform your shop floor — and stay tuned for the next wave of updates coming soon!

Photo Credit: Anže Godec

The post AI Agents Are Coming to the Shop Floor – Here’s Why It Matters appeared first on Qlector.