Hardware Podcasts

B2S Operators — Structured AI | The 3D QA Agent

Built 2 Scale · 26 Aug 2026 · 38m

What this episode covers

Raymond Zhao and Ben Remy of Structured AI explain how they are building an AI-native quality assurance layer for construction, using agents to read complex Revit models and 2D drawings to find design clashes and code violations. They discuss the technical challenge of managing context in large 'vector soups' of construction documents and the strategic decision to combine software engineers with domain experts to ensure agents understand engineering physics, not just syntax. The conversation covers their evolution from suggesting errors to executing isolated fixes in Revit, the difficulty of scaling a customizable product in a fragmented industry, and the future of agent-to-agent verification to manage hallucinations.

Most relevant to

early-stage companies

Topics

Mentioned

Companies
Structured AI, Y Combinator, Goldman Sachs, London Stock Exchange
Tools
Revit, Microsoft Azure
Also
Oxford

Related episodes from other shows

Other shows on the same ground, closest first.

  • Oxide and Friends · 1h 32m

    Engineering Rigor in the LLM Age

    Bryan Cantrill, Adam Leventhal, Rain Paharia, and David Crespo of Oxide Computer Company discuss using LLMs like Claude Code and Opus 4.5 to increase engineering rigor rather than just velocity. They share specific examples of using AI to refactor the Helios kernel, build the 'iddqd' Rust map library, debug the Ghostty terminal in Zig, and manage type drift in Oxide's APIs. The group argues that rigorous documentation and strong typing are essential for effective LLM collaboration, contrasting this with the 'vibe coding' narrative.

    AI & machine learningEmbedded firmware
    6 chapters

  • EE Times Current · 23m

    Beyond Automation: Self-Verifying AI Agents for Semiconductor and PCB Design

    Amit Gupta, Chief AI Strategy Officer at Siemens EDA, and Tim Costa, VP and GM of Industrial and Computational Engineering at NVIDIA, discuss their collaboration to build self-verifying AI agents for semiconductor and PCB design. They explain how the Fuse EDA AI agent uses NVIDIA's GPU-accelerated libraries and Nemotron models to execute long-running engineering workflows while verifying outputs against physics-based EDA engines. The speakers highlight a specific case study with NVIDIA's silicon team, where the Salido characterization suite achieved a 10x reduction in turnaround time and token costs by automating manual setup and error handling. They outline three milestones for the future: workflow coverage, verified repeatability, and integration into core engineering infrastructure, aiming to cut tape-out schedules in half.

    AI & machine learningChips, FPGAs & semiconductors
    9 chapters

  • OnTrack · 58m

    Inside Simberian's AI-Driven Design Automation

    Yuriy Shlepnev, founder of Simberian, discusses the integration of Large Language Models (LLMs) into signal integrity (SI) workflows via Simbeor Commander. He contrasts this agentic approach with previous machine learning attempts that relied on training data, arguing that LLMs are better suited for orchestrating deterministic solvers than for optimization or prediction. Shlepnev demonstrates how the AI agent can autonomously create stackups, import complex data from PDFs, and compare designs, effectively acting as an engineer that calls the underlying simulation tools.

    AI & machine learningPCB design & layout
    6 chapters

  • The Manufacturing Executive

    Agentic AI and the Future of Asset Lifecycle Management w/ Kendra DeKeyrel

    Kendra DeKeyrel, Vice President of Asset Lifecycle Management Products and Engineering at IBM, discusses the evolution of AI in manufacturing, moving from simple visual inspection to autonomous 'agentic' workflows. She highlights practical applications like computer vision for defect detection and AI-optimized field service, citing a case study with Shioda Technology that reduced repair times by 31%. DeKeyrel emphasizes that data quality is the primary barrier to adoption and outlines how chaining AI agents can automate complex maintenance and scheduling tasks.

    AI & machine learningConnected products & IoT
    7 chapters

  • EE Times Current · 24m

    Trust at Scale: The Next Challenge for AI-Driven Semiconductor Development

    Dr. Jim Shiely, Chief of Staff for Calibre Semiconductor R&D at Siemens EDA, discusses the 'trust bottleneck' emerging in semiconductor development as AI becomes embedded in engineering workflows. He explains that while AI accelerates tasks, it creates an overflow of data that requires 'trustworthy engineering intelligence'—grounded in independent verification tools like Calibre and physics-based models—to prevent hallucinations and ensure decision confidence. Shiely argues that successful companies will use digital twins and agentic flows to provide structured, traceable intelligence rather than just raw data, enabling humans to make rapid, confident decisions in a high-pressure environment.

    AI & machine learningChips, FPGAs & semiconductors
    7 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Built 2 Scale. The episode itself belongs to its publisher.