Videos

Jacob Beningo explains why agentic firmware development is already here and how embedded teams can move beyond ad hoc AI prompting. He covers skills, agents, RAG databases, and MCP servers, shows how NXP's new agentic AI tools put them into practice, and offers practical steps for building an agentic firmware workbench.

Chapters:
00:00 Introduction: Agentic Firmware Development Is Here
00:51 Conference AI Class Poll: Ad Hoc Prompting vs. Real AI Workflows
03:11 What Agentic AI Development Really Means (Skills, Agents, RAG, MCPs)
05:07 AI as a Tool to Make Embedded Developers More Productive
07:05 NXP's New Agentic AI Tools for Developers
09:23 Validating AI-Generated Code and Building Test Harnesses
10:22 Skills, MCP Connectors, and an Agentic Development Workbench
12:28 How Embedded Development Will Change in the Next 6–12 Months
14:16 Code Quality, Integrated Tooling, and the Evolving Embedded Engineer
16:31 Teaching AI Workshops and Why AI Mistakes Mirror Agile Iteration
18:11 How to Get Started: When to Build Skills, Agents, RAG, and MCP Servers
19:37 Resources, Upcoming AI for Embedded Developers Class, and Closing Thoughts

Key Takeaways:
• In a poll of 50 embedded developers at a conference, everyone used AI, but only two were building skills, agents, or RAG databases, and only one was using MCPs.
• Ad hoc prompting is not agentic development. Agentic workflows combine skills, agents, RAG, and MCPs to get repeatable results.
• Encode your company's coding style guide in a RAG database and give an agent access to it so code reviews and driver generation follow your standards.
• If you use AI for the same task more than two or three times, build a skill for it.
• Build an agent when you keep orchestrating the same skills and sub-agents, and use RAG for knowledge you keep pasting into prompts.
• MCP servers give AI "hands" in the physical world, such as debug sessions, power supplies, and oscilloscope or logic analyzer data, so it can work iteratively in a loop.
• Silicon vendors like NXP are releasing LLM-independent agentic toolkits with around 100 prebuilt skills, MCP connectors, AI-powered documentation, and prompt libraries.
• As AI produces thousands of lines of code, validation and test harnesses around AI tooling become critical.
• AI makes mistakes like human engineers do, and iterating on them is similar to agile. Used well, it can handle the boring infrastructure work so developers can focus on innovation.
• Jacob expects embedded development to change dramatically in the next 6–12 months, so start learning these techniques now rather than falling behind.