Can AI support inquiry, co-creation, and integration functions in Citizens’ Assemblies?

Citizens’ Assemblies and other deliberative mini-publics (DMPs) are institutions designed to foster democratic deliberation. AI systems, especially large language models (LLMs), have been suggested as tools to scale up the breadth and depth of DMPs. We distinguish six core functions within democratic deliberation – representation, perspective-giving and taking, inquiry, co-creation, integration, and decision-making – and point out some potential benefits of AI in each of these functions. Our case study presents the results of the Citizens’ Assembly on Energy, organised in Finland in 2025, in which an LLM was used in inquiry, co-creation, and integration. We found that while LLMs have some shortcomings in terms of inquiry, especially in creating questions for experts, they can ease the workload of human facilitators and deliberators in co-creation and integration. Our findings contribute to the emerging debate on the optimal division of labour in deliberative processes between human deliberators, facilitators, and generative AI.