Nenad Miric – Qlector

Agentic AI in Production Planning: The Hardest Job in the Factory Just Got Easier

Nenad Miric — Tue, 26 May 2026 09:24:21 +0000

At Hannover Messe 2026, one thing was impossible to ignore: absolutely everyone was talking about AI agents.

Tech giants like SAP, Microsoft, AWS, and Salesforce all placed Agentic AI at the center of their manufacturing vision. The message was loud and clear: the next phase of industrial software is reserved for autonomous decision support.

But after speaking with dozens of manufacturing executives and operations leaders, we noticed a major problem: almost everyone seems to define Agentic AI differently.

Some view it as just an advanced chatbot. Others describe it as a glorified digital assistant. A few even imagine fully autonomous robots making decisions completely on their own. The reality sits somewhere in between.

Before manufacturers rush to implement the latest buzzword, there is one critical question to answer: Do we actually understand what Agentic AI is, and is our organization really ready for it?

That is exactly why we wrote this article. We want to cut through the hype, clear up the confusion, and show you what Agentic AI actually looks like in practice, specifically in the most chaotic, high-stakes part of any factory: production planning.

The Hardest Job on the Factory Floor

Imagine being the central nervous system of an entire factory. That is exactly what a production planner is. Their work touches production, sales, buying, and the warehouse. So when the plan is slow or wrong, it sends shockwaves through the entire company’s success.

The job usually has three parts: making the plan, watching the plan, and fixing problems when something goes unexpectedly wrong. Whether a machine suddenly breaks down, a delivery is late, or a priority customer rushes in with an urgent order, the planner is the one who has to resolve it. To do all of this well without burning out, a planner needs agility and a clear view of what is happening.

Is your data working for you, or are you working for your data?

Instead of drowning in spreadsheets, modern planners use two main technologies to make their lives easier on the shop floor:

Machine Learning (The Numbers): This works with numerical data. It can analyze information, find anomalies, build schedules, and run “what-if” simulations. It is also great for data cleaning, because finding a wrong number early stops bigger mistakes later.
Large Language Models (The Text): These are tools like ChatGPT. They can summarize text, extract specific information, search by meaning, and answer questions about your own documentation in simple language.

From Simple Workflows to Autonomous Agents

For years, companies have used standard digital workflows to automate simple, repetitive tasks using strict “if-this-then-that” logic. These systems work fine until an exception occurs, instantly requiring a human to step in and figure it out.

But what happens when we add AI into the mix? Suddenly, the process gets a “brain”, allowing the system to understand context, analyze unstructured data, and dynamically suggest the next best action.

In practice, this intelligent automation takes two powerful forms on the factory floor:

First, an agentic workflow uses AI in specific steps to execute tasks. It can trigger on demand or at a specific time. The best part? You can give it instructions in natural language, so a planner can adjust the workflow themselves without needing a programmer.

Second, an autonomous agent goes even further. It is a standalone program that works in a loop to find a solution. It gathers data on its own, has a certain level of autonomy, and asks people for help at the right moments. The smartest agents even build their own skills and learn from past examples.

But what happens when a machine actually breaks?

Example 1: The Unexpected Machine Stop

This is a technical event, but the planner must react fast to minimize the damage. If a planner does this manually, they need to gather data, make a guess in their head or in a spreadsheet, and decide if something must move.

But with AI, you can write these steps once, and they run by themselves next time:

Look at past stops on this line
Find similar stops and guess how long this one will take
Check what happens to the plan if everything moves by a few hours

What once took a planner 10 to 30 minutes to figure out (often happening multiple times a week) is now solved in seconds. But the real value is that the problem stays small, the stress goes away, and the customer never notices.

And what about the repetitive morning chaos?

Example 2: The 7:00 AM Reality Check

Every morning, planners waste precious time reviewing the same things: what the night shift made, if the stock is correct, and if anyone needs a call.

An agent can prepare this check automatically. It can forecast material shortages, analyze inventory, and have everything ready for review. Planners have the flexibility to adjust the context, like watching the most important line or the one material they absolutely cannot run out of. This directly saves 10 to 20 minutes a day and ensures faster action if there are warnings.

Don't fall for the AI hype

Before you start, keep these practical tips in mind:

Start with the pain: Tie your goals to actual efficiency metrics. Don’t be guided by the vague desire to “do something with AI”.
Know (and trust) your data: Identify your data streams. Cultivate a culture where data is treated as a core asset.
Pick the biggest wins: Focus on the 80/20 rule, targeting the situations where the impact will be the biggest.
Expect exceptions: Let AI cover 90% of the cases, but always leave a manual option for the planner.
Engage your team: Ensure the active engagement of your end-users. Without their support, the project won’t move forward.

Go Step by Step, But Stay Safe

Take it slowly. First, map out the steps and digitalise the process, even if some steps stay manual. Ensure your data is reliable enough to make real decisions, not just reports. Later, give the AI more freedom, step by step, from “show me the data” to “do it for me”.

As agents do more independent work, safety rules are a must.

Be highly aware of GDPR and data sensitivity.
Give agents a clearly defined role and framework.
Set clear rules for when human oversight is required.
Keep an eye on costs, as AI consumption can add up.

Most importantly, always have a scenario prepared for handling catastrophic errors, including answering the question of who is ultimately responsible.

In short

Agentic AI does not replace the planner. It gives them more time to react and a clearer view, and it can turn a stressful 20-minute problem into one minute. The recipe is simple: start with a real problem, fix your data and process, keep a person in control, and give the AI more freedom only as trust grows.

Let's talk

If any of this sounds familiar, whether it is firefighting stoppages, wrangling endless spreadsheets, or just trying to work out where AI realistically fits into planning, we are always happy to have a conversation.

We would be glad to walk through what it could look like on your shop floor.

The post Agentic AI in Production Planning: The Hardest Job in the Factory Just Got Easier appeared first on 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.

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

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

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.