Simulink Copilot

About Simulink Copilot

Simulink Copilot brings generative AI-powered capabilities to Simulink and Model-Based Design. Educators, students, and researchers can use it to explain models and errors, teach or learn tools and techniques, and get design guidance. Whether navigating a complex model or diagnosing issues, users receive explanations and suggestions that guide them through modeling and simulation workflows.

Generative AI is rapidly becoming an essential skill for future engineers and scientists. Educators can support their students’ generative AI skills through Simulink Copilot, included with Campus-Wide access.

Split screen of a simulation diagram and menu item selection for Explain with Simulink Copilot (left) and a chat window with an explanation (right).

Opportunities for Generative AI in the Classroom

The use of generative AI tools requires students to learn additional skills such as creating prompts, refining prompts, iterating on ideas, and assessing the generated results. Each of these is an opportunity to teach students questions to ask themselves and new skills that they can use in the classroom and later in their careers.

Prompting: What are the best practices for creating prompts? How is prompting different from traditional search? What context can you provide to improve the prompt?

Refining and iterating: Did the generated results match your design intent? How can you get more targeted guidance from the system?

Assessing: How do you trust or verify the generated results? What tests or simulations can you run to build confidence in the results?

By teaching students how to use generative AI tools properly, you can establish a foundation to accomplish more in a course than previously possible. You can spend less time troubleshooting models, leaving more time for implementing course learnings through hands-on projects.

Generative AI tools, like Simulink Copilot, also provide real-time feedback and assistance to students so they can get help when they need it:

  • Simulink Copilot recommends appropriate tools and blocks, guiding students to the right examples and documentation for their modeling and simulation tasks.
  • Students gain insights into model behavior, understand architecture and algorithms in complex systems, search for specific components, and learn about best practices for Model-Based Design.
  • Students receive detailed guidance on modifying existing models or creating new models, helping them make necessary changes.
  • Simulink Copilot provides students with explanations of error messages and potential fixes so that they can identify issues.
  • Simulink Copilot documentation offers student resources on how to write targeted prompts, improving the quality of their interactions.

Concerns about Generative AI in the Classroom

While generative AI tools bring many benefits, they can also be disruptive to assessing student skills. This can be true in foundational courses where fundamental concepts are assessed with homework problems that are now trivial for a modern generative AI tool. In this case, instructors may wish for students to perform exercises without generative AI assistance (see the Configuring Simulink Copilot section below). In response, many instructors are exploring assessments that emphasize skills and activities, which remain relevant and professionally valuable:

These approaches align with competencies required for Model-Based Design, where students must make design decisions, justify tradeoffs, and iterate on complex engineered systems.

In the context of project-based learning, Simulink Copilot can serve as a valuable learning companion, enabling students to spend less time troubleshooting and more time developing the system-level reasoning that defines effective practices for Model-Based Design.

Research on using generative AI tools for assessing student work underscores the potential risks in terms of bias, validity, and transparency. Simulink Copilot is not intended for evaluating student submissions or determining grades. Instead, it provides valuable assistance to instructors who use MATLAB Course Designer to create Simulink-based courses, providing help in developing model examples, drafting explanations, and building instructional content. Because MATLAB Course Designer and MATLAB Grader are designed to teach students how to solve problems independently, Simulink Copilot is disabled when students complete MATLAB Course Designer or MATLAB Grader learning activities.

Configuring Simulink Copilot Classroom

While Simulink Copilot excels at providing modeling guidance and explanations, it is still crucial for students to build a solid foundation in modeling independently so they can address more complex tasks in the future. Educators can choose to allow or restrict access to Simulink Copilot. MATLAB Settings can be used to control the functionality of Simulink Copilot by enabling or disabling Simulink Copilot entirely.