Hardware Podcasts

AI PCB Design: Turning a 100-Page Spec Into an MCU Shortlist

OnTrack · 25 Aug 2026 · 31m · Episode 351

AI in practice: 2 real uses of AI described

What this episode covers

Marco Witzmann, Head of Requirements Portal at Altium, demonstrates the new AI-powered engineering assistant within the Altium Requirements Portal, formerly known as Requirements Manager. He walks through a live demo of converting a high-level email about a wind-farm inspection drone into structured requirements, using skills to enforce team standards and generate TBD placeholders. The workflow highlights the AI's ability to break down specs into mechanical, electronics, and flight software categories with full traceability, and specifically how it extracts MCU-driving parameters from a 100-page IMU PDF for Octopart parametric search. Witzmann and host Zach Peterson discuss the tool's role in faster iteration, team standardization, and future roadmap items like API access and ECAD integration.

AI in practice

Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.

Engineering & simulationAltium Requirements Portal (Engineering Assistant)

The AI agent analyzed a high-level email description of a wind-farm inspection drone to generate structured, well-formulated technical requirements with TBD placeholders for unknown values, enabling faster initial specification discovery.

“basically what you see now is the engineering assistant will now try to come up with actually well formulated requirements for this … It actually formulates requirements in the way that I and my company wanted these kinds of things to be formulated.”

Marco Witzmann · Hear it at 8:59

Engineering & simulationAltium Requirements Portal (AI-assisted Importer)50+ requirements extracted from PDF

The AI imported a 100-page IMU PDF specification, filtering out non-requirement content like tables of contents and revision history to identify and extract only the actual technical requirements for review.

“So we do have like an AI assisted importer, right? And what you can do here is you can just take the PDF. You just drag and drop it here, and it will now actually go ahead and analyze. … look through this, analyze what are the actual requirements that I hear that you want to import…”

Marco Witzmann · Hear it at 17:43

Most relevant to

early-stage companies

Topics

Mentioned

Companies
Altium
Products
Requirements Portal
Tools
Octopart
Also
Nexar

Related episodes from other shows

Other shows on the same ground, closest first.

  • The Amp Hour · 1h 00m

    Layout Review with Zachariah Peterson

    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.

    EDA & CAD toolsSensors & measurement in products
    9 chapters

  • IoT For All Podcast · 21m

    Can AI Design IoT Hardware? | Flux's Matthias Wagner | Internet of Things Podcast

    Matthias Wagner, Founder and CEO of Flux, explains how his company uses agentic AI to democratize PCB design, allowing non-engineers to create hardware via natural language prompts. He discusses the historical bottlenecks of hardware design, the necessity of iterative back-and-forth for complex devices like smartphones, and the economic advantages of designing custom boards for products like vending machines. Wagner also outlines future integration challenges, including firmware generation and enclosure design, and predicts that lowering the cost of iteration will unlock significant innovation in robotics and IoT.

    AI & machine learningPCB design & layout
    8 chapters

  • Product Startup · 23m

    205: Advances in Electronic Product Engineering Methods

    Tomide Adesanmi, founder of Circuit Mind, explains how hardware startups are outpacing large corporations in electronics innovation by leveraging agile design processes and modern tools. He details the traditional electronic product development lifecycle, from requirements and component selection to schematic capture, PCB design, and multiple prototype iterations (EVT, DVT, PVT). Adesanmi highlights the archaic nature of legacy hardware engineering compared to software and introduces Circuit Mind’s platform, which uses deterministic algorithms to automate schematic generation and optimize designs for cost, power, and supply chain availability.

    PCB design & layoutEmbedded firmware
    5 chapters

  • EE Times Current · 34m

    Improving PCB Structural Design and Reliability through Numerical Simulation

    Jean Baptiste Moyet, a multiphysics architect at Altair Engineering, explains how numerical simulation, high-performance computing (HPC), and artificial intelligence are transforming PCB structural design and reliability. He details the workflow from early-stage meshing and material property assignment to complex load case modeling for thermal cycling and drop tests. Moyet highlights how AI-driven optimization helps engineers find the best compromise between cost, manufacturability, and durability, significantly reducing the time needed to iterate on designs compared to traditional experimental campaigns.

    PCB design & layoutAI & machine learning
    6 chapters

  • Moore's Lobby · 55m

    Freeing EEs to Design Like Tony Stark

    Tomide Adesanmi, co-founder and CEO of Circuit Mind, explains how his background designing head-worn displays for fighter pilots at BAE Systems revealed the inefficiencies of manual schematic design. He founded Circuit Mind to replace tedious spreadsheet work and datasheet searching with deterministic algorithms that generate optimized circuit schematics from block diagrams. Adesanmi details the platform's ability to explore millions of design combinations for cost, size, and power, positioning the tool as a 'circuit solver' that allows engineers to act as architects rather than manual drafters.

    EDA & CAD toolsStarting a product company
    6 chapters

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.