The time machine: future scenario generation through generative AI tools
Contemporary society faces unprecedented challenges—from rapid technological evolution to climate change and demographic tensions—compelling organisations to anticipate the future for informed decision-making. This case study aimed to design a digital system for end-users called the Time Machine, wh...
| Autores: | , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2025 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/423594 |
| Acceso en línea: | https://hdl.handle.net/2117/423594 https://dx.doi.org/10.3390/fi17010048 |
| Access Level: | acceso abierto |
| Palabra clave: | Scenarios Futures Generative AI Large language models (LLMs) Prompt engineering Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial |
| Sumario: | Contemporary society faces unprecedented challenges—from rapid technological evolution to climate change and demographic tensions—compelling organisations to anticipate the future for informed decision-making. This case study aimed to design a digital system for end-users called the Time Machine, which enables a generative artificial intelligence (GAI) system to produce prospective future scenarios based on the input information automatically, proposing hypotheses and prioritising trends to streamline and make the formulation of future scenarios more accessible. The system’s design, development, and testing progressed through three versions of prompts for the OpenAI GPT-4 LLM, with six trials conducted involving 222 participants. This iterative approach allowed for gradual adjustment of instructions given to the machine and encouraged refinement. Results from the six trials demonstrated that the Time Machine is an effective tool for generating future scenarios that promote debate and stimulate new ideas in multidisciplinary teams. Our trials proved that GAI-generated scenarios could foster discussions on +70% of generated scenarios with appropriate prompting, and more than half included new ideas. In conclusion, large language models (LLMs) of GAI, with suitable prompt engineering and architecture, have the potential to generate useful future scenarios for organisations, transforming future intelligence into a more accessible and operational resource. However, critical use of these scenarios is essential |
|---|