Engineering with Agentic AI: Using Skills to Improve Your Agent

AI agents are already remarkably good at writing code, but engineering requires more than code generation. It requires domain expertise, established workflows, validation practices, and lessons learned from experienced engineers. Learn how to use skill files to provide that expertise to agentic AI systems. By packaging engineering knowledge into reusable skills, engineers can guide AI agents to consistently follow best practices across projects instead of relying solely on prompts. Through a MATLAB® system identification example, you’ll see how an AI agent can be enhanced with engineering guidance such as validation workflows, residual analysis, stability assessment, and reporting requirements. The result is an agent that not only generates code but also follows engineering processes aligned with real-world development practices. Related information: - Can Agentic AI Develop Embedded Systems with Model-Based Design?: https://youtu.be/-G4H2DmhR28 - MATLAB Agentic Toolkit: https://bit.ly/4vu96I5 - Simulink Agentic Toolkit: https://bit.ly/3QvkNPj Chapters: 00:00 Why AI agents are good at writing code but not engineering 02:25 Setting up the systems engineering example 03:04 Solving the example with the default agent 05:48 Building the skill file 07:30 Solving the example with the skilled agent 09:47 Engineering skills in the agentic toolkits -------------------------------------------------------------------------------------------------------- Get a free product trial: https://goo.gl/ZHFb5u Learn more about MATLAB: https://goo.gl/8QV7ZZ Learn more about Simulink: https://goo.gl/nqnbLe See what's new in MATLAB and Simulink: https://goo.gl/pgGtod © 2026 The MathWorks, Inc. MATLAB and Simulink are registered trademarks of The MathWorks, Inc. See www.mathworks.com/trademarks for a list of additional trademarks. Other product or brand names may be trademarks or registered trademarks of their respective holders.