MathWorks Adds AI Copilots to MATLAB and Simulink for Embedded Systems Work
MathWorks released version 2026a of its MATLAB and Simulink product families, introducing AI-assisted tools designed to help engineering teams move faster without sacrificing rigor or traceability in embedded systems development.
The release brings three new copilots: Simulink Copilot for model-based design, Polyspace Copilot for code analysis, and MATLAB Copilot for test generation. Each tool grounds its suggestions in the user's existing models, team processes, and MathWorks documentation rather than generic responses.
What the Copilots Do
Simulink Copilot generates explanations of model behavior, answers questions about designs, and helps engineers locate relevant blocks within complex models. It can isolate issues, suggest fixes, and guide next steps to keep design work moving forward.
Polyspace Copilot interprets static analysis findings and helps teams understand and resolve software issues faster. A companion feature called Polyspace as You Code checks C and C++ code as developers write it, catching defects and vulnerabilities-including those introduced by AI-assisted code generation tools.
MATLAB Copilot now generates starter tests, equivalence tests, and tests based on command history, reducing manual test creation work.
Broader Software Quality Updates
The release includes a new Polyspace desktop application that consolidates configuration and results management. Polyspace Bug Finder now supports custom checkers and additional coding standards. Polyspace Test added software-sanitizing capabilities for dynamic analysis of runtime errors.
Together, these changes create a more unified workflow for quality activities across development, testing, and verification stages.
Other Product Updates
MATLAB Course Designer is a new product for educators building courses and assessments. Simulink FMU Builder creates standalone Functional Mockup Units from Simulink models and C or C++ code to support model exchange workflows.
MATLAB now allows engineers to build and share interactive webpages with visualizations without installing MATLAB locally. It also improved Python environment management and data exchange between MATLAB and Python workflows.
Simulink simplified its context menus to surface commonly used actions faster. It can now simulate C and C++ code within models without additional wrappers or language limitations.
New toolboxes and updates include Wireless Network Toolbox for modeling and analyzing communication networks, enhanced Mapping Toolbox with 3D building visualization and raster map capabilities, and Signal Processing Toolbox with new Filter Designer and Filter Analyzer apps.
The Design Philosophy
MathWorks is embedding copilots directly into the environments engineers already use rather than requiring separate tools. The company also integrated MATLAB and Simulink into agentic workflows through MATLAB MCP Core Server and MATLAB Agentic Toolkit.
For teams considering these tools, the value proposition centers on three outcomes: understanding designs faster, addressing software issues earlier, and applying development workflows more consistently across projects.
Learn more about AI Coding Courses and Generative AI and LLM Courses to understand how these technologies work in practice.
Your membership also unlocks:
