Enhancing Human-AI Collaboration through a Conversational Agent for Energy Efficiency

Among the many scenarios where humans and AI agents can collaborate, Energy Efficiency (EE) is one where such collaboration could most effectively contribute to the goal of net zero emissions, while also reducing costs and improving comfort. In this context, new AI solutions can support customers in making their energy consumption more efficient and aligned with renewable sources. In this work, we investigate the strengths and challenges of Human-AI Collaboration by proposing an AI-based Conversational Agent whose inspiration principles are derived from the theories of Human-Centered Artificial Intelligence (HCAI). It is specifically designed to augment users' capabilities in achieving EE by providing them with recommendations and practical tips. The Agent uses a Knowledge Graph (KG) trained on domain-specific energy-related documents, coupled with a RAG (Retrieval Augmented Generation) architecture to ensure factual accuracy, source accountability, fairness, and transparency. By tailoring responses to users' profiles and preferences, the system prioritizes human needs and values while addressing perceptions of technological usability and acceptability. The Agent is validated in a real-world application scenario with international customers, with the aim to test content accuracy and adaptation to the user context and uncertainties. The results show the effectiveness of the system in fostering Human-AI Collaboration for EE.