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

arXiv: https://arxiv.org/abs/2508.15066 · HTML: https://mlsanity.com/paper/2508.15066/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 4 of its 34 references that are in the map.
- First posted on arXiv 20 Aug 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 4 of 4)

- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [CRISPR-GPT for Agentic Automation of Gene-editing Experiments](https://mlsanity.com/paper/2404.18021/) (2024)
- [Human-In-the-Loop for Bayesian Autonomous Materials Phase Mapping](https://mlsanity.com/paper/2306.10406/) (2023)
- [VISION: A Modular AI Assistant for Natural Human-Instrument Interaction at Scientific User Facilities](https://mlsanity.com/paper/2412.18161/) (2024)

## Built on by (most cited first, 4 of 4)

- [Safe-SDL:Establishing Safety Boundaries and Control Mechanisms for AI-Driven Self-Driving Laboratories](https://mlsanity.com/paper/2602.15061/) (2026)
- [Toward a Fully Autonomous, AI-Native Particle Accelerator](https://mlsanity.com/paper/2602.17536/) (2026)
- [Networked Intelligence: Active Shared Context Graphs for Human-AI Team Science](https://mlsanity.com/paper/2607.13220/) (2026)
- [Autonomous discovery of accelerator commissioning algorithms](https://mlsanity.com/paper/2608.07138/) (2026)

## Abstract (arXiv)

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.