AgentSLA : Towards a Service Level Agreement for AI Agents
Gwendal Jouneaux, Jordi Cabot
TL;DR
The paper tackles the challenge of ensuring QoS for AI agents by extending ISO/IEC 25010 with AI-agent–specific quality dimensions and proposing AgentSLA, a DSL to define SLAs for AI agents. It provides a metamodel and a JSON-based concrete syntax, plus a Python validating parser to instantiate and validate SLAs, enabling automatic monitor generation and SLA enforcement. Core contributions include the extended quality model, a core metrics set, and the AgentSLA DSL with tool support, designed to integrate with existing AI agent protocols such as A2A. The work enables SLA-driven selection, monitoring, and enforcement of AI-agent services, with future work aimed at broader validation, extensibility, graphical interfaces, and deeper ecosystem integration, increasing practical impact for developers and operators of AI-enabled software systems. For example, SLOs such as $AVG\ TTFT$ < 1 and other derived metrics illustrate how performance guarantees can be composed and evaluated over time.
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.