{"id":19391,"date":"2026-10-13T10:53:38","date_gmt":"2026-10-13T14:53:38","guid":{"rendered":"https:\/\/blogs.mathworks.com\/deep-learning\/?p=19391"},"modified":"2026-10-13T10:53:38","modified_gmt":"2026-10-13T14:53:38","slug":"jump-into-test-authoring-straight-from-requirements-using-an-ai-agent","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/deep-learning\/2026\/10\/13\/jump-into-test-authoring-straight-from-requirements-using-an-ai-agent\/","title":{"rendered":"Jump into Test Authoring Straight from Requirements Using an AI Agent"},"content":{"rendered":"
\r\n
\r\n
<\/h6>\r\n\r\n\r\n\r\n
Guest writer: Pat Canny<\/strong>\r\n
<\/h6>\r\nPat Canny <\/span>is a Principal Technologist at MathWorks specializing in safety-critical systems development, Model-Based Design, and digital engineering workflows for aerospace and defense.<\/td>\r\n<\/tr>\r\n<\/tbody>\r\n<\/table>\r\n<\/div>\r\n
<\/div>\r\n
\r\n
Authoring test cases is a tedious process. Authoring good<\/em>, requirements-based, systematic test cases is\u2026 well it\u2019s not always fun. When I created test cases to test my colleague\u2019s designs in Simulink, the day-to-day requirements work often looked something like this:<\/div>\r\n
\"This<\/div>\r\n
This reflects what day-to-day requirements work can feel like.<\/div>\r\n
This is a time-consuming workflow, and I haven\u2019t even talked about test coverage!<\/div>\r\n
This is an ideal use case for Agentic AI because an Agent can help \u201cautomate the boring stuff\u201d and allow me, an engineer with domain expertise, to focus on authoring the best<\/em> requirements-based test case possible while minimizing the context-switching between a text-based requirement and a Simulink model.<\/div>\r\n
To do this, I created a set of skill files in Codex which:<\/div>\r\n