Automotive tech supplier Marelli has introduced an artificial intelligence (AI)-based tool with Amazon Web Services (AWS) to automate system test case creation for software-defined vehicle validation.

The company said the system test generation (STG) agent focuses on a critical stage in validation by transforming engineering system requirements into structured, traceable test cases.

As vehicle architectures become increasingly software-driven, engineering teams are managing expanding volumes of requirements, data and specifications, while maintaining consistency and traceability across development processes.

The STG agent was created with support from the AWS Generative AI Innovation Centre.

It uses Amazon Nova foundation models, Amazon Bedrock Knowledge Bases and the Strands Agents framework.

Marelli Electronics Engineering team system performance optimisation head Daniele Russo said: “The STG Agent represents an important step forward in how we validate solutions for software-defined vehicles.

“By combining our engineering expertise with advanced AI capabilities from AWS, we significantly accelerate validation cycles and ensure consistent quality across global programs.”

According to the company, the system is intended to enhance validation efficiency and consistency by improving alignment between system requirements and verified product behaviours.

The tool is also designed to integrate with requirement management systems, allowing it to fit into existing automotive engineering workflows.

Within Marelli’s development process, customer requirements are first converted into system requirements by R&D engineers, the company added.

The STG agent then evaluates these inputs, determines expected behaviours and automatically produces corresponding system test cases to support validation.

Marelli said the approach is aimed at shortening validation timelines, enabling faster development of software-defined vehicle platforms and improving reliability in delivering new functions.

AWS Italia country leader Giulia Gasparini added: “Marelli's approach to automating system validation demonstrates the transformative potential of generative AI in automotive engineering.

“By leveraging Amazon Nova foundation models and Amazon Bedrock, companies are setting new standards for how software-defined vehicles are developed and validated.”