CIMplify Chat: A Standards-based Agentic-AI Interface for Power Systems Data

Recent advances in artificial intelligence (AI) and development of large language models (LLMs) present the opportunity to develop a new generation of power systems applications. In contrast with early power system AI applications based on structured numerical data, LLMs offer unique capabilities to perform logical reasoning using semantic standards, such as the IEC 61970 Common Information Model (CIM). In this work, an agentic AI tool service is developed using graph retrieval augmented generation (graph-RAG) and model context protocol (MCP) to create verifiable and explainable answers to common user questions about power system models without exposing any model data to a LLM, paving a path for utilities to create AI agents compliant with the NERC critical infrastructure protection (CIP) cybersecurity standards.