Conversational Prototyping: Leveraging generative AI to support iterative device production and testing
The Challenge
Artificial Intelligence (AI) systems based on Large Language Models (LLMs) are rapidly becoming a tool that many people rely on for daily tasks in both the home and the workplace. Models like ChatGPT can aid with everything from writing emails to scheduling dinner parties, and they are already being used in prototyping electronic devices, particularly when it comes to writing code.
Developing hardware can be more complex, however, especially when making use of things like sensors and actuators. Iterating for small or large scale production can require considerable time and resources.
The Solution
This project is seeking to leverage the power of LLMs through a novel approach called ‘Conversational Prototyping’. It will allow developers and end users to work in conversation with an AI system to develop the functionality of a prototype, incorporating sensing and actuation.
The project is aiming to produce three primary outcomes: a physical testbed that connects an LLM with sensors and actuators; a set of prompts and commands guiding the LLMs interaction with the testbed; and an evaluation of this approach to prototyping.
The project was successful in responding to the pro2 network’s 2024 funding call ‘Infrastructure for Device Production‘, which seeks infrastructure solutions beyond traditional manufacturing that support the production of digital devices.
