К содержимому
learnspaceYOUR NEXT CHAPTER
ПРОСТРАНСТВО ОБУЧЕНИЯ
ГлавнаяКаталог курсовМоё обучениеCoursera

Знания без границ

Учитесь у лучших университетов и компаний мира.

Открыть Coursera
Интеграция
Пространство университета
Моё пространствоСтраница курса
↵
ЯЛичный кабинетСтудент
© 2026 LearnSpaceКаждый день — возможность узнать больше.Помощь
Building Safe and Reliable AI Agents on AWS · LearnSpace
Назад в каталог
courseraПрограммирование

Building Safe and Reliable AI Agents on AWS

Курс от Amazon Web Services
Средний≈ 4.7 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

This course teaches learners how to design AI agents that are trustworthy enough for production use. Using a customer service agent example built on AWS, learners explore the major ways agents fail in real-world environments and the architectural patterns used to reduce those risks. The course covers agent harness design, layered guardrails, steering, tool safety, policy enforcement, evaluations, observability, and cost controls. By the end of the course, learners will be able to explain and apply practical mitigation techniques for deploying safer AI agents with AWS services such as Amazon Bedrock, Strands Agents SDK, Agent Runtime, Agent Gateway, Lambda, and AgentCore policy.

Навыки, которые вы освоите

AI SecurityAuthorization (Computing)Generative AI AgentsVerification And ValidationEnterprise ArchitectureModel Context ProtocolAgentic WorkflowsSecurity ControlsDevelopment TestingAgentic systemsResponsible AIAI OrchestrationAmazon BedrockAmazon Web ServicesApplication Performance ManagementTool CallingAI WorkflowsMiddlewarePrompt EngineeringPrompt Patterns

Программа курса

5 модулей · 30 учебных материалов

01Why Production Agents Need a Safety Harness6 материалов

Lesson: Module 1: Why Production Agents Need a Safety Harness

Welcome to Building Trustworthy AI AgentsВидеоThe Risks of Production AI AgentsВидеоFailure Modes of AI AgentsЧтениеDiagnosing an Agent FailureDIALOGUE

Учитесь у экспертов

Morgan Willis

Principal Cloud Technologist

Building Safe and Reliable AI Agents on AWS
В каталоге вашей программы

Инвестируйте в себя

Новые знания — в удобное для вас время.

Начать на Coursera

Обучение откроется на Coursera
в новой вкладке

Обучение на Coursera

≈ 4.7 ч

5 модулей

Язык: Английский

Часть программы вашего университета
Agent Risks and Failure ModesЗадание
Explore the Course GitHub RepositoryЧтение
02AWS Foundations for a Production Agent5 материалов

Lesson: Module 2: AWS Foundations for a Production Agent

The Customer Service Agent and AWS StackВидеоDefining a Basic Agent in StrandsВидеоAWS Service Map for the Agent HarnessЧтениеActivity: Map the Agent ArchitectureЧтениеAgent Components on AWSЗадание
03Guardrails and Steering for Safer Agent Behavior6 материалов

Lesson: Module 3: Guardrails and Steering for Safer Agent Behavior

Layered Guardrails for Adversarial AbuseВидеоWhen Is a Guardrail Enough?DIALOGUESteering Agents to Follow PolicyВидеоGuardrails vs SteeringЧтениеActivity: Design a Refund Safety FlowЧтениеGuardrails and SteeringЗадание
04Safe Tool Use, Policy Enforcement, and Access Control5 материалов

Lesson: Module 4: Safe Tool Use, Policy Enforcement, and Access Control

Interceptors and Tool Design for Safer ActionsВидеоTrusted Inputs and Tool AuthorizationЧтениеActivity: Redesign Unsafe ToolsЧтениеPolicy Enforcement with CedarВидеоTool Safety and Policy ControlsЗадание
05Evaluations, Observability, Cost Controls, and End-to-End Architecture8 материалов

Lesson: Module 5: Evaluations, Observability, Cost Controls, and End-to-End Architecture

Evaluating Agents Beyond the Happy PathВидеоActivity: Build an Agent Evaluation PlanЧтениеObservability and Cost Controls for ProductionВидеоResponding to a Cost SpikeDIALOGUEThe Full Production Architecture WalkthroughВидеоEnd-to-End Safety Architecture GuideЧтениеOperating Reliable Agents in ProductionЗаданиеAdditional ResourcesЧтение