AgentSLA : Towards a Service Level Agreement for AI Agents

TL;DR

This paper introduces a quality model and a domain-specific language for defining SLAs tailored to AI agents, addressing the challenge of ensuring quality and service guarantees in autonomous AI-driven systems.

Contribution

It proposes a novel quality model based on ISO/IEC 25010 and a domain-specific language for SLA specification for AI agents, filling a gap in quality assurance methods.

Findings

A comprehensive quality model for AI agents is developed.

A domain-specific language for SLA definition is introduced.

The approach facilitates better quality assurance for AI-driven systems.

Abstract

AI components are increasingly becoming a key element of all types of software systems to enhance their functionality. These AI components are often implemented as AI Agents, offering more autonomy than a plain integration of Large Language Models (LLMs), moving from a Model-as-a-Service paradigm to an Agent-as-a-Service one, bringing new challenges to the development of smart software systems. Indeed, while support for the design, implementation, and deployment of those agents exist, the specification of Quality of Service (QoS) and definition of Service Level Agreements (SLAs) aspects for those agents, important to ensure the quality of the resulting systems, remains an open challenge. Part of this is due to the difficulty to clearly define quality in the context of AI components, resulting in a lack of consensus on how to best approach Quality Assurance (QA) for these types of systems. To address this challenge, this paper proposes both a quality model for AI agents based on the ISO/IEC 25010 standard, and a domain specific language to support the definition of SLAs for the services provided by these AI agents.