← Retour au blog
tech 5 September 2026

Can AI Design Circuit Boards Yet?

Is AI ready to revolutionize printed circuit board design? Between automation and human expertise, let's explore where this technology stands in 2023.

Article inspired by the original source
Can AI design circuit boards yet? ↗ eebench.org

Introduction

Printed circuit board (PCB) design is a complex field that requires both technical expertise and creative intuition. With the advent of artificial intelligence, a burning question arises: Can AI design circuit boards as efficiently as human engineers? This article explores the current capabilities of AI, focusing on recent advancements and the remaining challenges.

AI and Circuit Board Design

OpenAI recently showcased the capabilities of its GPT-6 Astra model working with KiCad, a PCB design tool. This demonstration has sparked excitement in the electronics world, although we are still far from asking an AI to design an entire device in one command. The crucial question remains: how do we measure the quality of circuits produced by AI?

AI models have absorbed an impressive amount of knowledge in electronics, sourced from textbooks, datasheets, and code. However, leveraging this knowledge in traditional design tools remains limited. EEBench, for instance, uses a declarative code approach with atopile, allowing AI to directly work on components and connections without getting lost in graphical interfaces.

Use Case: Residential Energy Meter

A concrete example is testing a residential energy meter. When a power outage occurs, the circuit must keep the processor alive long enough to save accumulated readings. The intuitive solution is adding a capacitor. However, reality is more complex: real parts have tolerances, and capacitor behavior can vary under voltage. EEBench uses simulations to test the robustness of designs under these constraints.

Current Advantages and Limitations

AI offers undeniable advantages, such as speed and the ability to explore thousands of possible configurations quickly. However, it still faces significant challenges, including understanding the physical nuances and tolerances of components. According to a 2023 study, AI can reduce design time by 30% but still requires human validation to ensure reliability.

Towards Human-Machine Collaboration

The future of circuit board design may lie in a close collaboration between AI and engineers. AI could handle repetitive tasks and configuration exploration, while humans focus on creative and critical aspects. This symbiosis could not only accelerate the design process but also open new possibilities for creativity and innovation.

Conclusion

So, can AI design circuit boards? The answer is nuanced. While AI shows considerable promise, it is not yet ready to replace human engineers. However, it is on the right path to becoming a powerful tool in their arsenal, transforming how we approach electronic design.

Let's discuss your project in 15 minutes.

AI PCB design automation electronics collaboration
Deepthix newsletter · 100% AI · every Monday 8am

An AI agent reads tech for you.

Our AI agent scans ~200 sources per week and ships the best articles to your inbox Monday 8am. Free. One click to unsubscribe.

Visit the newsletter page →

Want to automate your operations?

Let's talk about your project in 15 minutes.

Book a call