# CHAI-DT: A Framework for Prompting Conversational Generative AI Agents to Actively Participate in Co-Creation

arXiv: https://arxiv.org/abs/2305.03852 · HTML: https://mlsanity.com/paper/2305.03852/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 10 references that are in the map.
- First posted on arXiv 5 May 2023.

## Builds on (most cited first, 2 of 2)

- [Nine Potential Pitfalls when Designing Human-AI Co-Creative Systems](https://mlsanity.com/paper/2104.00358/) (2021)
- [Conversational AI-Powered Design: ChatGPT as Designer, User, and Product](https://mlsanity.com/paper/2302.07406/) (2023)

## Abstract (arXiv)

This paper explores the potential for utilizing generative AI models in group-focused co-creative frameworks to enhance problem solving and ideation in business innovation and co-creation contexts, and proposes a novel prompting technique for conversational generative AI agents which employ methods inspired by traditional 'human-to-human' facilitation and instruction to enable active contribution to Design Thinking, a co-creative framework. Through experiments using this prompting technique, we gather evidence that conversational generative transformers (i.e. ChatGPT) have the capability to contribute context-specific, useful, and creative input into Design Thinking activities. We also discuss the potential benefits, limitations, and risks associated with using generative AI models in co-creative ideation and provide recommendations for future research.