Descartes expands AI innovation on the Global Logistics Network

Descartes Systems Group announced expanded artificial intelligence (AI) capabilities on its Global Logistics Network™ (GLN) with the introduction of the Descartes Fleet Data Intelligence™ platform. Built on the scale and real-world operational data of the GLN, the platform combines a new AI agent and machine learning (ML) capabilities to enhance on-time delivery, strengthen service level compliance and reduce cost per delivery while providing the visibility needed to measure, sustain and scale fleet performance improvements over time.

“For fleets operating private or dedicated distribution networks, the highest-impact opportunity for AI lies in improving real-world execution,” said James Wee, General Manager, Fleet Management at Descartes. “Execution data contains the signals needed to enhance fleet performance but, historically, it hasn’t been fully leveraged. With the Fleet Data Intelligence platform, we apply AI to the trusted execution data flowing through the GLN to separate signal from noise and turn everyday fleet operations into a continuous source of learning and improvement.”

New AI agent simplifies fleet performance analysis and drives continuous improvement:

• The Fleet Data Intelligence platform introduces René, an AI agent that surfaces both real-time insights and longer-term improvement opportunities without requiring manual data extraction or specialized analytics expertise.
• For day-to-day fleet performance, René enables planners, dispatchers and operations leaders to quickly investigate issues, test hypotheses and get immediate answers simply by asking questions, such as why routes ran faster in a given period, what is driving overtime or where service levels are at risk.
• René also uncovers deeper, systemic patterns by analyzing large volumes of fleet execution data to identify trends and surface root causes of inefficiencies—for example, a group of drivers consistently logging excess miles due to manual route deviations—to take targeted action to improve performance.

ML improves route density:

• The platform also introduces ML capabilities that have increased route density by up to 30% in early deployments, enabling fleets to complete more stops without adding vehicles or drivers.
• It generates more accurate service time predictions by learning from real-world delivery durations and route conditions across variables such as customer type, product characteristics, delivery volume, vehicle type, charging stop locations and geography.
• Improved planning precision minimizes excess buffer time, idle capacity, missed delivery windows and route plans that diverge during execution, allowing companies to schedule more stops per driver within the same working hours.

Performance visibility helps sustain and scale improvements:

• In addition, the platform provides structured visibility into key performance metrics, enabling organizations to benchmark service levels and track the impact of operational changes over time.
• By measuring improvements in areas such as route efficiency, service compliance and driver productivity, fleets can validate results, reinforce best practices and scale performance gains across their operations.

“For organizations operating high-density, repeat-route delivery models—such as foodservice, beverage distribution and wholesale logistics—even small improvements in fleet performance can deliver significant financial impact,” said Ken Wood, EVP, Product Management at Descartes. “The ability to leverage trusted, real-world operational data from the GLN allows fleets to apply AI at scale to continuously improve execution using the data they generate every day to drive measurable performance gains.”