Speaker
Description
The deployment of agentic AI systems at the Advanced Light Source (ALS) marks a major step toward autonomous, intelligent facility operations. By connecting large language models (LLMs) with diverse data sources, we are developing agents that not only interface with the control system but also provide a natural language interface for operators and scientists. This allows users to interact with complex control infrastructure through intuitive queries, lowering the barrier to expert-level system insights. This paper outlines the architecture of the agentic framework, highlights the integration of natural language interfaces, and discusses early results, implementation challenges, and future directions for distributed autonomous control in light source environments.
