Supply Chain Optimization
SiB Solutions needed a scalable, open and low-error way to process warehouse video and logistics events across customer sites without getting trapped in rigid monolithic architectures or vendor lock-in.
Reported impact
The platform supports more than 30 sites across Europe and North America while helping SiB Solutions reduce infrastructure and operational expenses and deliver logistics services designed to eliminate costly warehouse errors.
SiB Solutions built its intelligent video and AI services on IBM Cloud beginning in 2020, using IBM Code Engine and IBM Event Streams, the managed Apache Kafka service, as the backbone for warehouse telemetry and video events. In customer warehouses, video analytics run onsite for data residency, and edge computers apply deep-learning models to the camera feeds so errors can be identified close to the process being observed. Those outputs are published by Kafka producers to Kafka topics and sent to cloud servers, where application logic executes and microservices coordinate logistics workflows. Event Streams gives the company the high-volume streaming fabric it needed to avoid brittle monoliths and connect onsite industrial environments to cloud services, while Code Engine supports the cloud-side runtime used to develop and operate the broader platform.
Video is analyzed onsite in customer warehouses, edge computers process the footage with deep-learning models, and Kafka producers send the resulting events through IBM Event Streams to cloud servers on IBM Cloud where application logic and microservices coordinate logistics actions.
"Event Streams on IBM Cloud is core in everything we develop"
"SiB Solutions has developed and improved its solutions since starting on IBM Cloud in 2020, using IBM Code Engine and IBM Event Streams"
"The output of this process is sent from Kafka producers over Kafka topics to cloud servers, where application logic takes place."
"the company now services over 30 sites across Europe and North America"
"video analytics are run onsite to comply with data residency regulations"
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
LinkedIn's Organization JSON-LD lists addressLocality "Lund", addressCountry "SE", and numberOfEmployees value 30.
Related
In-house Sample Jun 3, 2026 Urban-Transporte Warehouse staff handling KION spare parts orders faced intense end-of-day workload peaks because containers could not be closed until it was clear whether customers would add more items before the shipping cutoff,… accuracy rate of around 96% Extreme Gradient Boosting (XGBoost) 
Snowflake Sample Archived · Feb 11, 2026 GLS GLS needed to replace a high-maintenance on-prem analytics platform that could explain past delays but could not predict future delivery problems, and whose slow queries, outages, and operational overhead limited the… 21 months Amazon Web Services (AWS) · Snowflake AI Data Cloud 
IBM Sample Jan 15, 2026 IBM IBM needed to reduce the time employees spent on repetitive work across HR, procurement, IT, supply chain, tax, and sales while creating a repeatable enterprise blueprint for scaling AI, automation, and hybrid-cloud… 15K AI agents proposed by employees during the 2025 IBM watsonx Challenge IBM Apptio · IBM Turbonomic · IBM Watson Discovery 