"Nobody Told me Farming is not Only Farming": A Conversational AI Agent for Causal Loop Reasoning with Japan Farmers

As the agricultural industry becomes more interconnected and shaped by globalized markets, smallholder farmers face mounting challenges in navigating an increasingly complex and highly competitive business landscape. This paper reports a study in which a conversational AI system, Seseragi was used to help synthesize systemic knowledge through participatory causal loop diagramming with four farmers who possessed extensive lifelong experience in local agricultural practice. Despite some technical limitations posed by latency, the farmers provided promising feedback and acknowledged the benefits of reflective brainstorming guided by our system. Our findings and design implications offer valuable insights into co-designing AI agents that support individuals navigating complex systemic problems that exceed the scope of their own professional expertise, as exemplified by the agricultural context.