OnTrack · 16 Jun 2026 · 43m · Episode 344
EMC expert Dr. Anton Tishchenko joins host Zach Peterson to discuss why 70% of PCBs fail EMC testing and how AI is exacerbating the issue. Tishchenko explains that large language models often generate confident but incorrect layouts, leading to 'garbage in, garbage out' scenarios when constraints are misapplied. He demonstrates his web-based tool, pcb4emc.com, which performs EMC design rule checks directly from Gerber files to evaluate ground plane quality, impedance, and crosstalk risk without requiring sensitive schematic data. The conversation highlights the distinction between AI as a helpful enhancement for literature reviews and simulation optimization versus its failure as a replacement for human engineering judgment.
Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.
Engineering & simulationClaude
The host used an LLM to read through 1000+ page Xilinx datasheets and architecture documents to quickly locate specific DDR timing constraint information, saving significant manual review time.
“So give it to Claude and let Claude read through it and find at least find the pages where they talk about it and I can go there and read it…”
Speaker 1 · Hear it at 14:30
Engineering & simulationAltium Designer
The speaker notes that AI capabilities have been introduced into Altium Designer to enhance existing tools, allowing him to perform tasks that were previously difficult or impossible to do easily.
“Introduction of additional capabilities within the tools that I like, I don't know, uh, 3D filth sobers, or autumn designer, for example, itself, like, and the use of, um, AI, uh, within those tools, it is definitely a positive because it it allows me to do things that I couldn't do easily before.”
Speaker 2 · Hear it at 13:34
early-stage companies
Other shows on the same ground, closest first.
Zachariah Peterson, founder of Northwest Engineering Solutions and Altium's technical consultant, discusses the state of PCB design, the industry's shift toward EMC expertise, and the impact of AI tooling. He details Altium's acquisition by Renesas, the critical need for engineers to understand manufacturing constraints and stack-ups, and the risks of relying on semiconductor data sheets for EMC guidance. Peterson also shares insights from his 'Layout Review' content series, highlighting common DRC errors and the value of mentorship in a lean industry.
Sergiy Nesterenko, CEO of Quilter.ai, explains how his company uses generative AI and parallel cloud compute to automate PCB layout from schematics. He discusses the company's pivot from hardware sensors to software, drawing on his experience at SpaceX where manual routing became a critical path bottleneck. Nesterenko details how Quilter handles constraints, validates designs using built-in Maxwell equation solvers, and targets specific fabs like JLCPCB and Oshpark to ensure manufacturability.
Chris Gammell and Dave Jones discuss troubleshooting a dead short in a PCB where a manufacturer modified Gerber files, causing a via to be placed on the wrong layer. They analyze why standard e-test fails to catch such errors and debate whether two-layer PCBs are sufficient for complex designs, referencing tools like KiCad and JLC. The conversation shifts to Dave Jones's decision to stop designing his own products, citing the high NRE costs, lack of discipline in solo projects, and the competitive advantage of rebranding existing hardware. They also touch on industry news, including the retirement of Jack Gansell and the passing of BBS inventor Ward Christensen.
Chris Gammell discusses his new video podcast, The Contextual Electronics Podcast, and details a Gerber file resolution error he encountered with JLCPCB while designing the ABC board. Dave Jones explains the technical nuances of Gerber resolution and aperture settings, while both hosts analyze the industry implications of ARM being up for sale, Intel's manufacturing struggles, and Google's new $300 engineering certification program.
Elecia White and Christopher White discuss Elecia's upcoming third edition of 'Making Embedded Systems' and Christopher's contract work with Logical Elegance. They debate the design of a potential embedded.fm branded PCB, weighing the utility of a simple radio against the complexity of a full development board, and explore the ethical implications of using Large Language Models for creative and professional tasks. Christopher also provides an update on his progress assembling a QRP Labs QCX+ transceiver for amateur radio communication with his father.
The summary, chapters and topics are generated from the episode’s audio by this directory, not written by OnTrack. The episode itself belongs to its publisher.