Grafana 将 SLO 与错误预算应用于 AI Agent 行为
原标题：Grafana Applies SLOs and Error Budgets to AI Agent Behaviour
AI 摘要
Grafana Labs 提出将站点可靠性工程中的 SLO 与错误预算方法应用于 AI Agent 行为评估，把幻觉、任务完成度、毒性、成本等行为转化为可测量的 SLI 与 SLO 目标。该方法强调质量是多维的，应分别度量而非合并为单一分数，并通过错误预算消耗来发现 Agent 质量的渐进式漂移。文章同时指出，SLO 的有效性取决于底层评估的准确性，仍需代表性数据集、确定性检查与人工复核。
正文节选
Grafana Labs is proposing a familiar reliability engineering approach for one of the less familiar problems in modern software: how to measure whether an AI agent is actually behaving well. In a recent article, the company describes using evaluations, service-level objectives (SLOs) and error budgets to turn behaviours such as hallucination, task fulfilment, toxicity, and cost into measurable targets that can be monitored over time. The idea addresses a fundamental limitation of conventional app