TransportationGenerative AI

A large European transport operator generates safety fact sheets with Claude 4.5 on a serverless AWS workflow, built by Sopra Steria

Sopra Steria

Sopra Steria built a serverless AWS solution for a large European transport operator that extracts, summarises and renders safety regulation content from the 'Document Unique' portal into print-ready fact sheets using Claude 4.5 via the client's AI Gateway. The source reports time per fact sheet falling from about 30 hours per month to 2 minutes, a 95% effort reduction, a ten-fold increase in fact sheets released, and a roughly 12% drop in safety-related incidents.

Overview

Sopra Steria built a serverless AWS solution for a large European transport operator that extracts, summarises and renders safety regulation content from the 'Document Unique' portal into print-ready fact sheets using Claude 4.5 via the client's AI Gateway. The source reports time per fact sheet falling from about 30 hours per month to 2 minutes, a 95% effort reduction, a ten-fold increase in fact sheets released, and a roughly 12% drop in safety-related incidents.

This entry has 10 published fields tied to exact passages in an immutable source capture.

Inspect the highlighted source

The challenge

A large European transport operator needed a faster, consistent way to turn the sprawling "Document Unique" safety regulations into short, visual fact sheets that could be displayed in every technical center.

The solution

Sopra Steria built a serverless solution on AWS that automatically extracts, summarizes and renders the required safety content using Claude 4.5 via the client's AI Gateway. The workflow is triggered by a change in the Document Unique portal, runs through API Gateway, Lambda and S3, and returns a ready-to-print PDF in under two minutes, with data encrypted and access-controlled with IAM and KMS.

Generative AI

Reported business value

The source reports that time to produce a safety fact sheet fell from about 30 hours per month to 2 minutes per fact sheet, a 95% reduction in effort, enabling a ten-fold increase in fact sheets released; it also reports a roughly 12% drop in safety-related incidents and an estimated $60k annual cost saving.

Sources

Open any source and check the claim yourself — that is the point of the register.

This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)

Related entries

Other transportation entries in the register.

All entries
TransportationMachine LearningUnknown

How Schiphol is leveraging tech, design, data and AI-powered intelligence to redefine airport capacity and flow management

Royal Schiphol Group built in-house AI-powered tools — Dynamic Time Slots, (Passenger) Flow Balancing, and Gate Planning Insights — to align passenger demand with security and gate capacity. Dynamic Time Slots lets passengers pre-book security check times, steering an average of 7.5% of passengers away from peak moments (up to 22% on critical days), with 99.6% of passengers waiting under 10 minutes. Flow Balancing uses real-time sensor data, predictive models and simulation (a digital twin) to steer passenger groups, preventing over 4,000 minutes of crowding in 2024. Gate Planning Insights uses machine learning to optimise gate stand planning and turnaround operations. Overall passenger satisfaction score is 4.4 out of 5.

92/100HighPrimary source
Royal Schiphol GroupDigital Twin Simulation · Private 5G Network · Real-time Sensor Data
TransportationDocument IntelligencePublic Cloud

AirAsia drives 97% invoice posting accuracy

AirAsia implemented Oracle Fusion Cloud ERP with AI-based invoice data capture, duplicate detection, supplier validation, approvals, posting, and exception review in a single platform for its accounts payable operations. For its initial top-nine-vendor group, invoice processing cycle time fell by 80%, invoice posting accuracy reached 97%, manual data entry effort dropped by 80%, and more than 30% of routine AP tasks became fully automated. AirAsia is positioned to evaluate Fusion Agentic Applications, including Payables Agent and Payments Agent, to further automate exception handling.

96/100HighPrimary source
AirAsiaOracle Fusion Cloud ERP
TransportationGenerative AIPublic Cloud

Hapag-Lloyd enhances corporate audit efficiency with GenAI on Databricks

German shipping company Hapag-Lloyd fine-tuned Databricks' open-source DBRX model and built a RAG chatbot to automate audit finding generation and executive summaries, cutting review time per finding by 66% and executive summary review time by 77%.

96/100HighPrimary source
Hapag-LloydAgent Bricks · MLflow
TransportationComputer VisionHybrid

Amphitrite Rides AI Wave to Boost Maritime Shipping, Ocean Cleanup With Real-Time Weather Prediction and Simulation

France-based startup Amphitrite fuses satellite data and AI to simulate and predict oceanic currents and weather, using the NVIDIA AI and Earth-2 platforms. Its fine-tuned, three-kilometer-scale AI models (dubbed ORCAst), trained on NVIDIA GPUs, analyze ocean current, wave, and wind data to help ships optimize routes and reduce fuel consumption and carbon emissions. Amphitrite trains and runs its AI models using NVIDIA H100 GPUs on premises and in the cloud, building on the FourCastNet model from Earth-2. Fusing AI and satellite imagery, Amphitrite can improve the accuracy of global ocean current analyses by up to 2x compared with traditional methods. A case study along the Mediterranean Sea found the NVIDIA-powered Amphitrite fine-scale routing solution helped reduce one shipping line's carbon emissions by 10%. Shipping and oceanographic companies using Amphitrite's solutions include CMA-CGM, Genavir, Louis Dreyfus Armateurs, and Orange Marine; the company also works with an NGO to track and remove plastic pollution in the Pacific Ocean.

96/100HighPrimary source
Amphitrite· FranceNVIDIA Earth-2 · NVIDIA H100 GPUs · FourCastNet

Was this helpful?

Your feedback helps us improve our use case database