Neural Concept introduces MCP to help AI agents operate commercial CAD tools

Switzerland-based artificial intelligence-based engineering company Neural Concept SA today launched Model Context Protocol Bridge, a feature that will help AI agents operate commercial computer-aided design and simulation tools.

This will also help large engineering organizations automate complex software environments that are fundamental to the design and simulation of physical products.

This is an important part of manufacturing and testing prototypes before preparing them for the real world. In a typical simulation cycle, running solvers is the only step that does not require human engineers. It is already largely automated, fetching the correct physical geometry, cleaning it and converting it into a virtually simulated mesh.

Founded in 2019, Neural Concept serves leading original equipment manufacturers and engineering organizations in the automotive, aerospace, energy, consumer, electronics, semiconductor and defense industries. It integrates an AI-powered engineering platform and deep learning directly into computer-aided design and computer-aided engineering workflows.

With the new MCP Bridge, the platform gives AI agents access to the tools that make this possible and the technical know-how to use them, while companies retain control and ownership of their software and data.

“For the first time, the software that shapes every physical product can be powered by enterprise-level AI,” said CEO and co-founder Pierre Baqué.

Ideally, Baqué added, the opportunity is to reduce boredom for engineers, who can then tackle harder problems and work faster. This comes at a time when manufacturers are looking to shorten development cycles due to fewer technical experts available.

When an agent can work on an approved task in design and simulation software, every hour it takes is an hour given back to an expert for more important work.

In one customer case, an engineer using MCP Bridge cleaned the geometry of a wheel rim in three minutes, compared to a day using a manual process. This is the work required to take a physical product from physical to virtual model preparation and into simulation.

This process, the preparation and simulation of virtual models, shifts technology from reaction and physical trial and error to proactive data-driven digital environments through the creation of “digital twins.” These digital twins can be simulated with high fidelity, but only if they are “cleaned up” before manufacturing to behave, look and react like their real-world counterparts using real-world physics. This preparation is based on data sheets, material guidelines and large amounts of data. It can be an extremely tedious and tedious job that requires extensive validation.

Once this is done, engineers can test thousands of design scenarios simultaneously in virtual labs instead of having to wait for real physical prototypes. However, it can take weeks or longer to create a draft and have a rough draft that an expert can refine. An AI agent working in computer-aided engineering software can reduce this time to hours. Leave the fine-tuning of the result to an engineer.

“AI agents have completely changed the way I work,” said Ciro Alosa, an electromagnetic design engineer at Traton SE, a Volkswagen Group subsidiary that manages its heavy truck, bus and light commercial vehicle brands. “I can do more work in parallel and going from a research paper to a validated script in our simulation toolchain now takes a few days.”

Image: SiliconANGLE/Microsoft Designer