What is mattwood.fyi?

A live, structured feed of riffs and links from Matt Wood, Chief AI & Technology Officer at AWS — readable by people and queryable by agents as a typed knowledge graph.

Is there an API and is it free?

Yes. A public, read-only query API is available with no authentication and no API keys. See https://mattwood.fyi/openapi.json and https://mattwood.fyi/docs.

How should an AI agent use this site?

Fetch https://mattwood.fyi/feed.json for the full structured feed, or query the API for keyword/semantic search and the connection graph. See https://mattwood.fyi/agents/ for when-to-use guidance.

Can AI Design Circuit Boards Yet?

Connections

Challenges

AI is removing the middle class of software engineering If AI can competently design circuit boards (a specialized EE skill), it further challenges the notion that hardware engineering roles are insulated from AI displacement

Related to

Comparing 11 Different AI Models Both articles use structured benchmarks to compare AI model capabilities, though EEBench introduces a domain-specific metric for electronics vs. general model comparison
Nova3D: Code-Native Generation of Programmable 3D Assets Both explore AI generating complex technical artifacts through declarative/code-native approaches rather than GUI tools - Nova3D for 3D assets and EEBench for circuit designs

Supports

Claude Writes macOS Driver for Windows-Only HP Printer Both demonstrate AI tackling real hardware engineering challenges - Claude writing a printer driver and AI designing PCBs represent the frontier of AI in physical computing systems
SWE-bench Science: Coding Agents for Engineering Tasks EEBench follows the same scientific benchmarking philosophy as SWE-bench, extending rigorous AI capability measurement from software engineering tasks into hardware/electronics design domains

Develops into

GPT-6 Astra System Card The article explicitly evaluates GPT-6 Astra on circuit board design tasks, making EEBench a practical capability assessment of that specific model's engineering competence

Supported by

Copperhead: Circuit Board Design Cursor Copperhead is a specialized cursor tool for PCB layout, directly relevant to the question of whether AI can design circuit boards - it represents a concrete tool enabling such workflows
Jalapeño Shows Power of LLMs for Chip Design Jalapeño's demonstrated success with LLMs for chip design directly answers the question 'Can AI Design Circuit Boards Yet?' with a positive case study

Introducing OUI-1: Generative UI Model Both items interrogate whether AI models can generate functional domain-specific artifacts (PCB layouts vs. user interfaces), exploring AI's practical design generation capabilities

Type:	link
First published:	Friday, 4 September 2026 at 22:47 UTC
Location:	https://eebench.org/blog/can-ai-design-circuit-boards-yet/
URL:	https://mattwood.fyi/i/623d49af

I'm Matt Wood, and this is For Your Information. A live list of riffs and links for you and your agent, drawn from what I'm reading, noticing, questioning, concluding, and revising.

Connections