From Goals to Aspects, Revisited: An NFR Pattern Language for Agentic AI Systems
This work addresses the challenge of engineering reliable agentic AI systems for developers by providing a principled approach to modularize crosscutting concerns, though it appears incremental as it builds on an existing methodology.
The paper tackles the problem of poor modularization of crosscutting concerns like security and reliability in agentic AI systems, which contributes to high failure rates in production, by extending a goals-to-aspects methodology to this domain with a pattern language of 12 reusable patterns validated through a case study.
Agentic AI systems exhibit numerous crosscutting concerns -- security, observability, cost management, fault tolerance -- that are poorly modularized in current implementations, contributing to the high failure rate of AI projects in reaching production. The goals-to-aspects methodology proposed at RE 2004 demonstrated that aspects can be systematically discovered from i* goal models by identifying non-functional soft-goals that crosscut functional goals. This paper revisits and extends that methodology to the agentic AI domain. We present a pattern language of 12 reusable patterns organized across four NFR categories (security, reliability, observability, cost management), each mapping an i* goal model to a concrete aspect implementation using an AOP framework for Rust. Four patterns address agent-specific crosscutting concerns absent from traditional AOP literature: tool-scope sandboxing, prompt injection detection, token budget management, and action audit trails. We extend the V-graph model to capture how agent tasks simultaneously contribute to functional goals and non-functional soft-goals. We validate the pattern language through a case study analyzing an open-source autonomous agent framework, demonstrating how goal-driven aspect discovery systematically identifies and modularizes crosscutting concerns. The pattern language offers a principled approach for engineering reliable agentic AI systems through early identification of crosscutting concerns.