MathWorks, the leading developer of mathematical computing software for designing engineered systems, today announced an expansion of its TÜV SÜD certification. The certification now covers generic AI tool classification guidance under the automotive standard ISO 26262. It applies to MATLAB®, Simulink®, Stateflow®, and System Composer™ included with the IEC Certification Kit. As a result, engineers gain a clearer path to apply agentic AI in functional safety projects.
MathWorks became the first tool vendor to provide guidance for select AI-assisted engineering workflows in functional safety applications. Specific use cases evaluated by TÜV SÜD inform the guidance. Moreover, it covers practical applications of AI-assisted Model-Based Design. These workflows use Simulink Agentic Toolkit for agentic model development, model review, and test case generation. Furthermore, the guidance shows how teams can fit these use cases into safety-critical development in a controlled and auditable manner. Consequently, organizations can speed up development while preserving engineering rigor, traceability, and standards compliance.
Agentic AI Capabilities Extend Model-Based Design
MathWorks integrates agentic AI capabilities with Model-Based Design workflows. These capabilities let engineers move beyond prompting AI systems. Instead, AI agents operate directly on Simulink models and engineering workflows. Meanwhile, MathWorks keeps adding new skills that guide agents in applying MATLAB and Simulink functionality to engineering tasks.
Simulink Agentic Toolkit helps AI agents understand model structure. Agents can also create and modify designs, run simulations, generate tests, and connect requirements to models. The toolkit pairs Simulink-specific tools with expert-authored skills for Model-Based Design workflows. MathWorks engineers and domain experts write these skills. They guide agents through model development, algorithm specification, plant modeling, testing, validation, and requirements generation. Additionally, the skills steer agents toward the right functionality for each task. Engineers, however, remain responsible for validating results.
Polyspace Agentic Toolkit Supports Software Verification
Polyspace Agentic Toolkit extends these workflows into software analysis and verification activities. It supports code robustness analysis, coding-standard compliance, and defect detection. Together, the two toolkits let organizations bring AI agents into the development lifecycle. At the same time, teams keep their established validation and review practices.
“Engineering teams are looking for ways to benefit from agentic AI without sacrificing the rigor that system development demands,” said Michael Carone, Principal Product Marketing Manager – Simulink Platform, MathWorks. “By connecting AI agents to Simulink models, simulations, and testing workflows, MathWorks is helping engineers apply agentic AI within established engineering processes while preserving the accountability required for complex engineered systems.”
Organizations that expand the use of agentic AI in engineering need approaches that combine AI capabilities with domain-specific engineering context. They also need the deterministic verification that engineering workflows require. Therefore, MathWorks connects AI agents to executable engineering assets such as models, simulations and tests. This approach helps teams apply AI within established engineering processes.
Built on Model Context Protocol (MCP), the capabilities support AI agent platforms including GitHub Copilot, Codex, Gemini CLI, Claude Code, and other MCP-compatible agents. Thus, organizations can choose the platforms that suit their engineering workflows. Engineers can automate more development activities with AI assistance grounded in engineering results. Still, they remain responsible for final decisions and approvals.
Explore IT Tech News for the latest advancements in Information Technology & insightful updates from industry experts!
News Source: Businesswire.com
