• Melo, A. T.,  Teixeira, A. S., Caves, L., Renault L.,  Lopes, P. D., Garnett, P., Ribeiro, R., Santos, F. (2024).  Requirements and challenges for AI-supported systems of (co)augmented intelligences organised by complex thinking. Lightning talk and Poster presentation at the Satellite meeting "Complex Systems and Collective Intelligence, at the Conference on Complex Systems 2025, Exeter, UK, by organisation of the Complex Systems Society.

• Teixeira de Melo, A., Renault, L., Caves, L.S.D., Garnett, P., Lopes, P. D., Ribeiro, R., Santos, F. An AI tool for scaffolding complex thinking: challenges and solutions in developing an LLM prompt protocol suite. Cogn Tech Work (2025). https://doi.org/10.1007/s10111-025-00817-6 

  • Abstract: This paper reports an exploratory study examining the interaction between a theoretical framework for Complex Thinking and AI (LLMs), in terms of its potentialities and constraints. The aim was to develop and conduct a preliminary pilot evaluation of a tool comprising a prompt protocol suite for use with an LLM, to scaffold Complex Thinking. The tool is designed for use by an individual or group in relation to a given Target System of Interest (i.e., a real-world system, a problem, or a concern), supporting the development of more complex understandings of such systems that can guide more effective and positive actions and decisions. We describe the process of developing a suite of prompt protocols for scaffolding particular properties of Complex Thinking and report on the outcomes of a pilot test evaluation with a set of users across different domains.

CT & AI project final event "Complex Thinking & Artificial Intelligence"

An online event held on 28 October 2024

Videos

• Welcome Session: YouTube LINK

• Outcomes, challenges and reflections: YouTube LINK  

• Discussion panel "Complex thinking and artificial intelligence": YouTube LINK

A Zenodo Community is available that contains the documents generated by the CT & AI project, including background literature, development/support, technical reports, preprints and the prompt protocols (also available on GitHub - see below).

A GitHub repository is available with the CT & AI protocol suite developed in the project. 

Further description and licensing information: README.md