Switzerland-based artificial intelligence-native engineering company Neural Concept SA today launched Model Context Protocol Bridge, a capability 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 designing and simulating physical products.
This is an important part of manufacturing and proving prototypes before they are prepared for the real world. In a typical simulation cycle, running solvers is the only step that doesn’t require human engineers; it is largely already automated through retrieving proper physical geometry, cleaning it up and turning it into a virtual simulated mesh.
Founded in 2019, Neural Concept serves leading original equipment manufacturers and engineering organizations in industries throughout automotive, aerospace, energy, consumer, electronics, semiconductors and defense. It integrates an AI-augmented engineering platform and deep learning directly into computer-aided design and computer-aided engineering workflows.
With the new MCP Bridge, the platform will give AI agents access to the tools that make this happen, as well as the engineering 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 operated by AI at enterprise scale,” said Chief Executive and co-founder Pierre Baqué.
Ideally, Baqué added, the opportunity is to reduce the tedium for engineers, who can then take on harder problems and work faster. This comes at a time when manufacturers are looking to shorten development lifecycles with fewer engineering experts available.
If an agent can handle an approved task in design and simulation software, every hour it takes is an hour handed back to an expert for more critical work.
In one customer case, an engineer using MCP Bridge cleaned up the geometry of a wheel rim in three minutes, compared with a day using a manual process. This is the work needed to get a physical product from physical to virtual model preparation and into simulation.
This process, virtual model preparation and simulation, shifts engineering from reaction, physical trial-and-error into proactive data-driven digital environments by creating “digital twins.” These digital twins can be simulated in high fidelity, but only if they are “cleaned up” to act, look and react like their real-world counterparts with real-world physics before manufacturing happens. This preparation works off spec sheets, materials guidelines and vast amounts of data. It can be extremely tedious, long work that requires extensive validation.
Once done, engineers can test thousands of design scenarios simultaneously in virtual labs instead of waiting for real-world physical prototypes. However, getting one set up and into a rough draft an expert can refine can take weeks or more; an AI agent working in computer-aided engineering software can cut that time to hours. Letting an engineer fine-tune the result.
“AI agents have completely changed the way I work,” said Ciro Alosa, an Electromagnetic Design Engineer at Traton SE, a subsidiary of Volkswagen Group that manages its heavy truck, bus and light commercial vehicle brands. “I can run more work in parallel and going from a research paper to a validated script in our simulation toolchain now takes a couple of days.”