Edge AI agent lets users control equipment with spoken commands
9 September 2026 
A UK product development and manufacturing consultancy, 42 Technology (42T), has developed a natural-language edge AI agent that allows production engineers and technicians to control complex industrial equipment using everyday language, and to get help when troubleshooting. They can speak or type their questions to access technical information, without having to navigate through multiple interfaces or search through technical documents.
The system combines natural-language understanding with real-time equipment control and awareness of machine states.
The Cambridge-based company has a working demonstration of its natural-language control, running on local edge AI hardware, that shows how its approach could be applied across industries such as manufacturing, process engineering and printing.
Industrial engineers often have to work across multiple systems and interfaces to keep production equipment running smoothly. 42T’s Edge AI agent removes the need to memorise specialist commands, refer to technical documents or navigate complex interfaces when something goes wrong. The new AI tool has the potential to reduce the need for training, improve efficiency, and make equipment easier and safer to operate.
The system combines natural-language understanding with real-time equipment control and machine-state awareness, allowing users to issue commands, ask questions, and get context-aware support, using either spoken or typed instructions. It can retrieve information rapidly from a library of operator manuals, technical documents and fault-finding guides, to give users immediate contextual help without interrupting their workflows
Unlike consumer voice assistants, 42T’s system runs entirely on edge AI hardware, with all of the data being stored and processed locally on a user’s own premises. This protects sensitive operational data, gives companies complete control over their AI models, and enables constant offline operation without having to rely on third-party cloud services or subscriptions.
The system has been designed for use in industrial environments, and offers options such as foot-pedal activation for the wake command, and wireless headsets. It can interpret a user’s requirements in noisy environments, even if spoken commands are incomplete. It operates within pre-defined guardrails and can be configured to require human confirmation before acting in safety-critical applications.
The technology is said to be suitable for applications ranging from laboratory automation – where hands-free operation can boost productivity significantly – to manufacturing and industrial process control. The natural-language interface is said to be particularly valuable where technical knowledge is spread across several manuals, embedded in software, and retained by experienced operators.
“Production engineers and technicians often need quick, reliable guidance while working on live equipment, but the information they need is usually buried across multiple manuals or in complex, menu-driven interfaces,” explains Mike Sales, head of AI at 42 Technology. “Using a natural-language AI agent as a user interface means they can easily get accurate, context-aware answers without interrupting their workflow. They can simply ask questions such as, ‘How do I calibrate channel three?’ or ‘Why won’t the pump start?’ to get the support they need.”
42T has developed a working demonstrator that shows its natural-language control running on compact, embedded hardware. The demonstrator allows a signal generator to be controlled using spoken commands via a small language model (SLM) running locally on a single-board computer. The SBC handles the complete edge AI workload, including speech detection, speech-to-text conversion and agent orchestration.
42T is also working closely with an industrial equipment manufacturer to integrate its natural-language AI agent into selected products. The project is providing insights into how this technology can best be deployed across complex industrial systems with multiple inputs from sensors and sub-systems.
Looking ahead, natural-language AI agents could evolve beyond controlling individual pieces of equipment into a “digital foreman” system capable of monitoring multiple production assets simultaneously, prioritising and highlighting issues requiring immediate operator attention. This approach would reduce the need for operators to monitor multiple screens, lights and other devices, while improving manufacturing efficiency and reducing costs.
42 Technology was founded in 1998 and works with customers to solve complex technical problems and develop products. Its team includes engineers, scientists and designers. It has a particular expertise in optimising manufacturing processes – for example, improving energy efficiencies, reducing waste, and reconfiguring production assets to accommodate sustainable materials or new product formats.
Earlier this year, 42T was acquired by Newcastle-based British Engines Group, which was founded in 1922 and currently employs 1,600 people in nine businesses worldwide. At the time of the acquisition, British Engines said that it would allow 42T to pursue larger and more ambitious opportunities, supported by the group’s global reach, engineering depth and investment capacity. It will also allow 42T to broaden its innovation and manufacturing capabilities, and to take on larger-scale developments.
42 Technology: LinkedIn
