一句话：提出一套 AgentOps 软件工程工作流，用于关联智能体执行证据并实施运行时治理。
智能体 AI 系统能够进行规划、调用工具、与其他智能体协作并作用于外部软件服务。这类系统的失效难以诊断：控制流在运行时才生成、执行具有随机性，且错误行为常表现为目标漂移、不安全的工具使用或虚假的成功报告，而非直接崩溃。本教程给出一套面向 AgentOps 的软件工程工作流，将高层意图、模型层决策、工具调用、内存访问与底层系统效应贯通起来，并强调所得证据既能支持事后诊断、也能支持运行时干预。参与者将学习如何构造智能体 trace、关联执行证据、识别静默行为与漂移行为，并应用策略检查、风险追踪、隔离约束与人工升级等运行时治理模式。
Agentic AI systems increasingly plan, call tools, coordinate with other agents, and act on external software services. Their failures are difficult to diagnose because control flow is generated at runtime, execution is stochastic, and incorrect behavior often appears as goal drift, unsafe tool use, or false success reports rather than as crashes. This tutorial presents a software engineering workflow for AgentOps that connects high-level intent, model-level decisions, tool calls, memory accesses, and low-level system effects. It emphasizes evidence that can support both retrospective diagnosis and runtime intervention. Participants will learn how to construct agent traces, correlate execution evidence, identify silent and drifting behavior, and apply runtime governance patterns such as policy checks, risk tracking, containment, and human escalation.