Want a Supply Chain AI Win This Quarter? Update Your Planning Parameters
When executives ask me where AI can make an immediate impact in the supply chain, most expect an answer involving autonomous planning, digital twins, or advanced forecasting algorithms.
My answer is usually much simpler.
Use AI to improve your planning parameters.
It may not be the flashiest use case, but it is one of the fastest ways to improve inventory performance, increase service levels, and reduce planner workload—without replacing your ERP system.
The Problem Most Companies Don't See
Most manufacturers already have planning systems in place.
They run MRP.
They use min-max replenishment.
They have safety stock.
But they have stock outs and are carrying too much inventory.
The problem isn't the planning engine.
The problem is that the planning engine is only as good as the parameters feeding it.
Over time, those parameters drift away from reality.
Supplier lead times change.
Demand patterns evolve.
Forecast accuracy improves—or deteriorates.
Product mix shifts.
New suppliers are added.
Customer expectations change.
Yet many planning parameters haven't been reviewed in months or even years.
The result is predictable:
Higher inventory than necessary
Lower service levels than expected
Endless exception messages
Excessive expediting
Planners overriding system recommendations
Firefighting becoming the normal way of operating
In many organizations, the ERP system is functioning exactly as designed. The underlying assumptions simply no longer reflect the business.
Why This Is the Perfect AI Use Case
Most companies know these parameters should be updated.
The challenge is scale.
A manufacturer may have thousands—or tens of thousands—of active items across multiple plants, warehouses, and suppliers.
No planning team has enough time to continuously review and maintain the parameters driving every planning decision.
That's where AI creates value.
Instead of relying on periodic reviews, AI can continuously monitor supply chain performance, identify where assumptions have drifted from reality, and recommend updates before those issues become inventory shortages or excess stock.
The best part?
You can do this using the data already sitting inside your ERP system.
No ERP replacement required.
No multi-year transformation program.
No need to wait until every piece of AI infrastructure is in place.
The Five Planning Parameters Worth Updating First
1. Supplier Lead Times
Lead time is one of the most important inputs in any planning system.
It represents the total time required from purchase order creation to material availability for production.
Unfortunately, lead times are often maintained manually and updated infrequently.
Over time, actual supplier performance diverges from what's stored in the ERP system.
AI can analyze purchase order history and identify suppliers, commodities, and items where actual lead times no longer match planning assumptions.
The result:
Better material planning
Fewer expedites
Improved inventory positioning
More realistic schedules
2. Safety Stock
Safety stock exists to protect against uncertainty.
The challenge is that uncertainty changes.
Demand variability changes.
Supplier reliability changes.
Lead times change.
Many organizations either never calculate safety stock correctly or fail to update it as conditions evolve.
AI can continuously evaluate service level targets, demand variability, lead time performance, and supplier reliability to recommend more accurate safety stock levels.
The result:
Lower inventory investment
Improved service levels
Reduced stockouts
Better inventory utilization
3. Reorder Points (ROP)
The reorder point determines when replenishment begins.
Many reorder points were established years ago using assumptions that no longer reflect current business conditions.
AI can identify items where demand, lead times, or service requirements have changed and recommend updated reorder points.
The result:
Earlier identification of shortages
Fewer emergency purchases
Improved inventory availability
4. Min-Max Levels
Min-max policies are widely used because they are simple and effective.
The problem is that many min-max settings are established during implementation and rarely revisited.
AI can evaluate current demand patterns, lead times, and inventory performance to recommend more effective min-max ranges.
The result:
Reduced inventory
Better product availability
Improved working capital performance
5. Lot Sizes
Lot sizes determine how replenishment orders are grouped and executed.
Examples include:
Fixed Order Quantity (FOQ)
Economic Order Quantity (EOQ)
Minimum Order Quantity (MOQ)
Order Multiples
These settings have a direct impact on inventory levels, ordering costs, transportation costs, and supplier efficiency.
AI can evaluate purchasing patterns, demand trends, and inventory performance to identify opportunities for improvement.
The result:
Lower purchasing costs
Reduced excess inventory
Improved working capital
More efficient replenishment
Start Small. Create Momentum.
One of the biggest mistakes companies make with AI is waiting for the perfect transformation program.
The organizations generating the most value are starting with focused use cases that solve real business problems today.
Planning parameter optimization is one of those opportunities.
Most manufacturers already own the planning technology they need.
What they lack is a practical way to continuously keep planning assumptions aligned with reality.
AI changes that equation.
It allows organizations to monitor, analyze, and improve planning parameters at a scale that was never practical using manual processes.
Sometimes the fastest path to better supply chain performance isn't replacing the planning system.
It's improving the inputs feeding it.
And that is a supply chain AI win you can deliver this quarter.
P.S. This also works with MRO Inventory
AI Disclosure:
Writing & Personal Experience: Greg Pitstick
Editing: ChatGPT
Image: Google Gemini