{"id":19305,"date":"2026-06-08T09:11:46","date_gmt":"2026-06-08T13:11:46","guid":{"rendered":"https:\/\/blogs.mathworks.com\/deep-learning\/?p=19305"},"modified":"2026-06-08T09:11:46","modified_gmt":"2026-06-08T13:11:46","slug":"an-ai-coding-agent-for-embedded-ai","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/deep-learning\/2026\/06\/08\/an-ai-coding-agent-for-embedded-ai\/","title":{"rendered":"An AI Coding Agent for Embedded AI"},"content":{"rendered":"
\r\n
\r\n
<\/div>\r\n
\r\n
<\/h6>\r\n\r\n\r\n\r\n
\"Arkadiy<\/td>\r\nGuest blogger: Arkadiy Turevskiy<\/a><\/strong>\r\n
<\/h6>\r\nArkadiy Turevskiy <\/span>is the Product Manager for AI and Controls products at MathWorks. Arkadiy has been with MathWorks for over 20 years. Before MathWorks he designed aircraft engine control systems at Pratt & Whitney.<\/td>\r\n<\/tr>\r\n<\/tbody>\r\n<\/table>\r\n
<\/h6>\r\n<\/div>\r\n
<\/div>\r\n<\/div>\r\n
<\/div>\r\n
When I deploy a deep learning model from MATLAB to an embedded target, I follow a specific workflow. I know which Deep Learning Toolbox blocks to use in Simulink for simulation speed and code generation. I know when to apply pruning, projection, or quantization to fit a model onto a constrained processor. I've built that expertise over years.<\/div>\r\n
The first time I asked Claude Code to help with this workflow, it didn't have any of that context. It burned tokens trying approaches I would have skipped, and missed tools I would have reached for immediately.<\/div>\r\n
That was the gap I wanted to close.<\/div>\r\n
For the last several weeks my colleague Lucas Garcia and I have been building a skill file for Embedded AI that captures that workflow knowledge and gives it to an agent to avoid the frustrating iterations I experienced. I'm excited to share this skill with you: embedded-ai-deployment<\/a>.<\/div>\r\n

What We Mean by Embedded AI<\/h2>\r\n
Embedded AI is AI that runs on resource-constrained hardware, integrated alongside control logic, signal processing, and application code, and validated as part of a larger engineered system. Model accuracy is necessary, but not sufficient: the algorithm must also behave correctly under real-world constraints and remain maintainable.<\/div>\r\n
The skill covers two workflow patterns that account for most projects:<\/div>\r\n