Osprey: Production-Ready Agentic AI for Safety-Critical Control Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hellert, Thorsten, Montenegro, João, Sulc, Antonin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914197846097920
author Hellert, Thorsten
Montenegro, João
Sulc, Antonin
author_facet Hellert, Thorsten
Montenegro, João
Sulc, Antonin
contents Operating large-scale scientific facilities requires coordinating diverse subsystems, translating operator intent into precise hardware actions, and maintaining strict safety oversight. Language model-driven agents offer a natural interface for these tasks, but most existing approaches are not yet reliable or safe enough for production use. In this paper, we introduce Osprey, a framework for using agentic AI in large, safety-critical facility operations. Osprey is built around the needs of control rooms and addresses these challenges in four ways. First, it uses a plan-first orchestrator that generates complete execution plans, including all dependencies, for human review before any hardware is touched. Second, a coordination layer manages complex data flows, keeps data types consistent, and automatically downsamples large datasets when needed. Third, a classifier dynamically selects only the tools required for a given task, keeping prompts compact as facilities add capabilities. Fourth, connector abstractions and deployment patterns work across different control systems and are ready for day-to-day use. We demonstrate the framework through two case studies: a control-assistant tutorial showing semantic channel mapping and historical data integration, and a production deployment at the Advanced Light Source, where Osprey manages real-time operations across hundreds of thousands of control channels. These results establish Osprey as a production-ready framework for deploying agentic AI in complex, safety-critical environments.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15066
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Osprey: Production-Ready Agentic AI for Safety-Critical Control Systems
Hellert, Thorsten
Montenegro, João
Sulc, Antonin
Multiagent Systems
Information Retrieval
Operating large-scale scientific facilities requires coordinating diverse subsystems, translating operator intent into precise hardware actions, and maintaining strict safety oversight. Language model-driven agents offer a natural interface for these tasks, but most existing approaches are not yet reliable or safe enough for production use. In this paper, we introduce Osprey, a framework for using agentic AI in large, safety-critical facility operations. Osprey is built around the needs of control rooms and addresses these challenges in four ways. First, it uses a plan-first orchestrator that generates complete execution plans, including all dependencies, for human review before any hardware is touched. Second, a coordination layer manages complex data flows, keeps data types consistent, and automatically downsamples large datasets when needed. Third, a classifier dynamically selects only the tools required for a given task, keeping prompts compact as facilities add capabilities. Fourth, connector abstractions and deployment patterns work across different control systems and are ready for day-to-day use. We demonstrate the framework through two case studies: a control-assistant tutorial showing semantic channel mapping and historical data integration, and a production deployment at the Advanced Light Source, where Osprey manages real-time operations across hundreds of thousands of control channels. These results establish Osprey as a production-ready framework for deploying agentic AI in complex, safety-critical environments.
title Osprey: Production-Ready Agentic AI for Safety-Critical Control Systems
topic Multiagent Systems
Information Retrieval
url https://arxiv.org/abs/2508.15066