Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models
Chatting with AI to understand why buildings use so much energy
Researchers built a conversational system that lets building managers ask natural questions about energy forecasting models instead of staring at technical dashboards. The system correctly understands 94% of questions asked, compared to 76.8% in previous attempts, and energy experts unanimously preferred talking to it over traditional interfaces.
Building operators make real decisions about heating, cooling, and power use based on energy forecasts—but they often can't trust models they don't understand. A system that explains predictions through normal conversation means managers can catch errors, spot patterns, and actually act on what the AI recommends rather than guessing or ignoring it entirely.