English-language podcasts

The Embedded Frontier

#028 - From Coding Assistants to Autonomous Engineering

26 min

Listen through the publisher, then discuss the episode here or arrange an in-person Roundtable. Your city determines where to meet.

Roundtables are designed for groups of four, with a shared subject and room for everyone to speak. Come for discussion, with no dating expectation.

Jacob Beningo explores the shift from using AI as a coding assistant to agentic firmware development, where AI agents autonomously build, debug, test, and verify embedded systems. He shares a real experiment using an NXP MCX N947 board and an AI-written I2C driver. He also covers hardware safety guardrails, simulation, and how embedded engineers can evolve into systems engineers. Key Takeaways: • Most teams use AI only as a coding assistant. The bigger gains come from agentic workflows where AI builds, debugs, tests, and verifies firmware. • AI doesn't get firmware right on the first try, and neither do human engineers. It needs the ability to iterate, as with test-driven development. • Connecting an AI agent to real hardware or a simulator lets it observe results, find root causes, and fix problems instead of guessing. • In the I2C experiment, the agent correctly diagnosed a hardware problem (a backwards click board) that the engineer had wrongly blamed on the software. • Once the board was fixed, the agent produced a tested, production-grade temperature and humidity sensor driver within about an hour. • A robust agentic workbench combines skills, agents, RAG, and MCP servers, with an orchestration agent following your own development processes. • Give agents access to debuggers, oscilloscopes, logic analyzers, and adjustable power supplies. This brings real risk, including fire hazards, hardware damage, and liability. • Build safety into MCP servers. For example, require users to set voltage and current limits up front, and prompt for approval whenever the agent tries to exceed them. • Simulation offers a safe, continuous way to validate AI-generated code, especially when hardware is dangerous to leave unattended. • Start small. Pick a repetitive daily task with a clear outcome, automate it, then expand the workflow gradually while keeping human verification and static analysis in place.

Episode information is provided by the publisher. Listening takes place on the publisher’s service.

Listen at the source ↗

Featured places to meet in Palo Alto, CA

Explore these places and arrange a conversation through ThinkMatch.

City guide for Palo Alto, CA

More from The Embedded Frontier

The Embedded Frontier

#029 - How to Write Fast RTOS Code

35 min

Jacob Beningo talks with RTOS pioneer Bill Lamie, creator of Nucleus, ThreadX, and PX5 RTOS, about how to write efficient, high-performance real-time code. They cover POSIX pthreads, keeping software simple, RTOS benchmarking, test-driven development, using AI as a development teammate, and practical tips for structuring RTOS applications. Key Takeaways: • Keep it simple: complexity is the biggest enemy of embedded software, and a complex solution is probably not the right one. • Minimize nested function calls in critical paths, since pushing and popping registers and return addresses is expensive. • Design for performance from the start. Every comparison and data reference matters in the real-time path, and performance can't be bolted on at the end. • Use an error-checking veneer selectively. Enable it for new or untrusted code and call the direct API for proven code to save cycles. • Standardizing on the POSIX pthreads API makes it easier to share code between Linux and RTOS-based pr

Discuss this episode

Community Poll

Representatives should revise campaign promises when strong new evidence shows a better course.

Share your view, then see how readers voted. No sign-in required. This poll is shared across stories.

Do you agree or disagree?

Choose one answer

Common Quandary

A Common Quandary to discuss

Another conversation to explore, separate from this news story.

Your friend spent five years writing a terrible novel. What do you say?

A close friend asks for your candid opinion of a novel they have spent five years writing. You find it confusing and unlikely to be published, but writing it has given them purpose during a difficult period.

Is kindness sometimes a reason to withhold an honest judgment?

Explore this quandary