Expert opinion

How Agentic AI is Filling the Gaps in Inventory Management

Among the plethora of Warehouse Management modules, Inventory Management is the one with the most significant AI adoption with great potential for further evolution. We've talked with Piotr Pernej, .NET Competency Manager at ELEKS, to discuss how agentic AI is impacting warehouse inventory management processes and what its evolution may look like in the coming years.

What's the role of Inventory Management Systems within the WMS ecosystem?

A modern Warehouse Management System (WMS) typically consists of multiple interconnected software modules designed to support all warehouse operations. Efficient WMS solutions are sophisticated systems that pay special attention to factors such as:

Optimising storage space
Ensuring swift picking and packing
Maintaining consistently accurate stock levels

The Inventory Management System (IMS) is the module that excels at processing stock levels. It plays a crucial role within the WMS components, ensuring that warehouses maintain the proper quantity of goods. The IMS, as the heart of every WMS, directly affects the speed, cost, and efficiency of order fulfilment. It also acts as a safeguard, helping prevent understocking and overstocking.

What are the challenges of Inventory Management Systems?

Maintaining low discrepancies between the system and physical stock level is an undisputed must for any WMS. Beyond that, IMS systems face several larger challenges, including:

Develop your agentic solution

Discover our logistics solutions

Understock and overstock

Demand predictions

Stock refilling process

Optimal usage of storage space

Modern WMS solutions often struggle to predict optimal stock levels for specific commodities accurately. Too low stock levels may cause commodity shortages, disrupt the sales process, and eventually result in financial losses. They may also cause delays across the supply chain, especially when the stored items are semi-finished products required for assembling a larger product. On the other hand, keeping stock levels too high while seemingly safer can result in excess inventory. This can block valuable storage space, increase waste, and raise the risk of commodity expiration.

Demand forecasting is a typically heavy process that produces static data with limited flexibility to adapt once the report is finalised. This clashes with the market realities, where customer demand frequently fluctuates, often abruptly. Current IMS systems are not good at tracking it in real time, as the volume of data is simply too vast to be processed quickly by humans.

Slow or inaccurate re-ordering of missing stock can lead to understocking, financial losses, or, at the very least, delays in the supply chain. Adjusting stock levels dynamically to match changing demand is one of the key challenges faced by Inventory Management Systems.

Inaccurate demand predictions can result in the warehouse storage locations being blocked by slow-moving stock. Conversely, storing slow-moving inventory in fast-moving locations causes suboptimal use of warehouse space. This is simply a consequence of erroneous demand forecasts.

How might agentic AI transform Inventory Management Systems?

The AI agent integrates with tools and service providers and can utilise external APIs to make independent business decisions. In the context of IMS, the goal could be to forecast commodity demand and maintain optimal stock levels based on those predictions.

Explore the impact of AI in supply chain management

AI in Supply Chain: A Real-world Case Study on Harnessing AI's Potential

In particular, the areas within IMS subsystems where agentic AI could drive significant improvements include:

Real-time demand predictions

The traditional approach to forecasting demand involves market research, expert opinions, trend examination, and analysis of historical data. While these methods rely heavily on human processes, agentic AI elevates those techniques to the next level. Analysing vast amounts of historical data becomes a matter of seconds for AI, enabling it to identify sales patterns that would not be possible for humans to recognise within a reasonable time frame. Moreover, predictions made by agentic AI can effortlessly incorporate information gathered from social media.

Additionally, cumbersome and hard-to-tune demand prediction reports could be replaced by swift, real-time AI forecasting that adjusts as soon as new data arrives. For example, a social media post might influence sales by triggering a flash sale. This is especially important during seasonal sales or market fluctuations that could undermine the entire forecast. Real-time forecasting significantly reduces that risk.

Accessing and combining multiple data sources can be a game-changer for accurate stock predictions. Agentic AI in the Inventory Management System has no problem with accommodating data from sources such as:

Economic reports
Specialists' predictions
Social media posts
Extensive historical sales reports
Weather reports and forecasts
Market condition indicators
Competitors' situation reports

Storage cost and supply chain optimisation

With more accurate demand predictions, stock levels are optimised, reducing the cost of storing commodities that cannot be sold within a reasonable time. This also minimises supply chain delays, especially when semi-finished commodities are a part of the process.

Strategic Technology in 2025: An Expert Assessment of Market Predictions

Refilling stock levels

Traditionally, ordering stock when it reaches minimum levels has been a human responsibility - or at least subject to human approval. However, Inventory Management AI agents can significantly accelerate this process and make it less error-prone by automating commodity ordering. The IMS AI agent operates autonomously to reorder commodities, though setting a maximum order limit can act as a safeguard, ensuring human oversight remains in place. For example, the agent can be configured to make autonomous ordering decisions up to $ 5,000 without human approval. These decisions are triggered automatically by predicted demand and market trends. Above this threshold, it waits for human approval by generating alerts or suggestions.

Order picking process

Dynamically relocating trending commodities from slow-moving to fast-moving storage locations - without human intervention - reduces congestion points in the inventory picking process, thereby shortening the overall picking time.

It's also worth noting that the agentic AI approach includes built-in learning capabilities. For example, it can be rewarded for making effective decisions, such as ordering a commodity or relocating it to a fast-moving storage location when it later sells out quickly.

Skip the section

FAQs

What does Inventory Management System (IMS) do?

IMS helps warehouses track stock availability. It manages inventory and triggers stock reordering. With the support of an IMS, a company can avoid shortages or excess inventory by providing real-time stock-level data.

How does agentic AI differ from traditional inventory systems?

What kind of data do agentic AI inventory systems need to function effectively?

Talk to experts

Skip the section

Full name*
We need your name to know how to address you

Email*
We need your email to respond to your request

Phone number*
We need your phone number to reach you with response to your request

Country*
We need your country of business to know from what office to contact you

Company*
We need your company name to know your background and how we can use our experience to help you

Message*

Attach file
Accepted file types: jpg, gif, png, pdf, doc, docx, xls, xlsx, ppt, pptx, Max. file size: 10 MB.

Add an attachment

(jpg, gif, png, pdf, doc, docx, xls, xlsx, ppt, pptx, PNG)

- I want to receive news and updates once in a while

We will add your info to our CRM for contacting you regarding your request. For more info please consult our privacy policy

Name
This field is for validation purposes and should be left unchanged.

What our customers say

The breadth of knowledge and understanding that ELEKS has within its walls allows us to leverage that expertise to make superior deliverables for our customers. When you work with ELEKS, you are working with the top 1% of the aptitude and engineering excellence of the whole country.

Sam Fleming

President, Fleming-AOD

Right from the start, we really liked ELEKS’ commitment and engagement. They came to us with their best people to try to understand our context, our business idea, and developed the first prototype with us. They were very professional and very customer oriented. I think, without ELEKS it probably would not have been possible to have such a successful product in such a short period of time.

Caroline Aumeran

Head of Product Development, appygas

ELEKS has been involved in the development of a number of our consumer-facing websites and mobile applications that allow our customers to easily track their shipments, get the information they need as well as stay in touch with us. We’ve appreciated the level of ELEKS’ expertise, responsiveness and attention to details.

Samer Awajan

CTO, Aramex