Architecting AgentOps Needs CHANGE

TL;DR

This paper highlights the need to rethink system architecture for Agentic AI, proposing the CHANGE framework to manage their continuous evolution and non-deterministic behavior effectively.

Contribution

It introduces CHANGE, a novel conceptual framework with six capabilities, to guide the architecting of AgentOps platforms for evolving Agentic AI systems.

Findings

CHANGE enables dynamic management of Agentic AI systems.

Framework supports lifecycle management of non-deterministic agents.

Illustrated through a customer-support scenario.

Abstract

The emergence of Agentic AI systems has outpaced the architectural thinking required to operate them effectively. These agents differ fundamentally from traditional software: their behavior is not fixed at deployment but continuously shaped by experience, feedback, and context. Applying operational principles inherited from DevOps or MLOps, built for deterministic software and traditional ML systems, assumes that system behavior can be managed through versioning, monitoring, and rollback. This assumption breaks down for Agentic AI systems whose learning trajectories diverge over time. This introduces non-determinism making system reliability a challenge at runtime. We argue that architecting such systems requires a shift from managing control loops to enabling dynamic co-evolution among agents, infrastructure, and human oversight. To guide this shift, we introduce CHANGE, a conceptual framework comprising six capabilities for operationalizing Agentic AI systems: Contextualize, Harmonize, Anticipate, Negotiate, Generate, and Evolve. CHANGE provides a foundation for architecting an AgentOps platform to manage the lifecycle of evolving Agentic AI systems, illustrated through a customer-support system scenario. In doing so, CHANGE redefines software architecture for an era where adaptation to uncertainty and continuous evolution are inherent properties of the system.