AWS Certified Generative AI Developer - Professional (AIP-C01)AWS 认证生成式 AI 开发者 - 专业 (AIP-C01)
The AWS Certified Generative AI Developer - Professional (AIP-C01) exam is intended for individuals who perform a GenAI developer role. The exam validates a candidate's ability to effectively integrate foundation models (FMs) into applications and business workflows. This certification demonstrates practical knowledge of how to implement GenAI solutions into production environments by using AWS technologies.AWS 认证生成式 AI 开发者 - 专业 (AIP-C01) 考试面向执行 GenAI 开发者角色的个人。考试验证候选人有效将基础模型 (FMs) 集成到应用程序和业务工作流中的能力。此认证展示了使用 AWS 技术在生产环境中实施 GenAI 解决方案的实际知识。
Topics主题
Target candidate description目标候选人描述
Exam content考试内容
Content outline内容大纲
Content Domain 1: Foundation Model Integration, Data Management, and Compliance内容领域 1：基础模型集成、数据管理和合规性
Content Domain 2: Implementation and Integration内容领域 2：实施与集成
Content Domain 3: AI Safety, Security, and Governance内容领域 3：AI 安全、安全性和治理
Content Domain 4: Operational Efficiency and Optimization for GenAI Applications内容领域4：生成式人工智能应用的运营效率与优化
Content Domain 5: Testing, Validation, and Troubleshooting内容领域5：测试、验证和故障排除
Technologies and concepts that might appear on the exam考试可能出现的技术和概念
Mentions of AWS services on the exam考试中提到的AWS服务
In-Scope AWS Services范围内的AWS服务
Out-of-Scope AWS Services范围外的AWS服务
Survey调查
Introduction
The AWS Certified Generative AI Developer - Professional (AIP-C01)
The exam also validates a candidate's ability to complete the following tasks:考试还验证了候选人完成以下任务的能力：
Design and implement solutions by using vector stores, Retrieval Augmented Generation (RAG), knowledge bases, and other GenAI architectures.使用向量存储、检索增强生成（RAG）、知识库和其他生成式人工智能架构设计和实现解决方案。
Integrate FMs into applications and business workflows.将基础模型集成到应用程序和业务工作流程中。
Apply prompt engineering and management techniques.应用提示工程和管理技术。
Implement agentic AI solutions.实现代理 AI 解决方案。
Optimize GenAI applications for cost, performance, and business value.优化 GenAI 应用的成本、性能和业务价值。
Implement security, governance, and Responsible AI practices.实施安全、治理和 Responsible AI 实践。
Troubleshoot, monitor, and optimize GenAI applications.排查、监控并优化 GenAI 应用。
Evaluate FMs for quality and responsibility.评估 FM 的质量和责任。
Target candidate description
The target candidate should have 2 or more years of experience building production-grade applications on AWS or with open-source technologies, general AI/ML or data engineering experience, and 1 year of hands-on experience implementing GenAI solutions.目标候选人应拥有 2 年或以上在 AWS 或开源技术上构建生产级应用的经验，具备 AI/ML 或数据工程经验，以及 1 年实施 GenAI 解决方案的实际经验。
Recommended AWS knowledge推荐的 AWS 知识
The target candidate should have the following AWS knowledge:目标候选人应具备以下 AWS 知识：
Experience with AWS compute, storage, and networking services对 AWS 计算、存储和网络服务的经验
Understanding of AWS security best practices and identity management对 AWS 安全最佳实践和身份管理的理解
Experience with AWS deployment and infrastructure as code (IaC) tools使用 AWS 部署和基础设施即代码 (IaC) 工具的经验
Familiarity with AWS monitoring and observability services熟悉 AWS 监控和可观测性服务
Understanding of AWS cost optimization principles对 AWS 成本优化原则的理解
Job tasks that are out of scope for the target candidate超出目标候选人范围的工作任务
The following list contains job tasks that the target candidate is not expected to be able to perform. This list is non-exhaustive. These tasks are out of scope for the exam:下面的列表包含目标候选人不期望能够执行的工作任务。此列表并非穷尽的。这些任务为考试不在范围内：
Model development and training模型开发和培训
Advanced ML techniques高级机器学习技术
Data engineering and feature engineering数据工程和特征工程
Exam content
Question types题目类型
The exam contains one or more of the following question types:考试包含以下一种或多种题目类型：
Multiple choice: Has one correct response and three incorrect responses (distractors).多选题：包含一种正确答案和三个错误答案（干扰项）。
Multiple response: Has two or more correct responses out of five or more response options. You must select all the correct responses to receive credit for the question.多选题：在五个或更多选项中包含两个或更多正确答案。必须全部选择正确答案才能获得该题的学分。
Unanswered questions are scored as incorrect. There is no penalty for guessing. The exam includes 65 questions that affect your score.未回答的问题计为错误。猜测不受处罚。考试包含 65 个影响分数的问题。
Unscored content未计分内容
The exam includes 10 unscored questions that do not affect your score. AWS collects information about performance on these unscored questions to evaluate them for future use as scored questions. The unscored questions are not identified on the exam.考试包含10道未计分题目，这些题目不会影响你的分数。AWS会收集你在这些未计分题目的表现，以便评估它们是否可以作为未来的计分题目。未计分题目在考试中不会被标识。
Exam results考试成绩
The AWS Certified Generative AI Developer - Professional (AIP-C01) exam has a pass or fail designation. The exam is scored against a minimum standard established by AWS professionals who follow certification industry best practices and guidelines.AWS认证生成式AI开发者-专业（AIP-C01）考试采用通过或不通过的评级。考试的评分基于AWS专业人士依据认证行业最佳实践和指南设定的最低标准。
Your results for the exam are reported as a scaled score of 100–1,000. The minimum passing score is 750. Your score shows how you performed on the exam as a whole and whether you passed. Scaled scoring models help equate scores across multiple exam forms that might have slightly different difficulty levels.你的考试成绩以100–1000的计分制呈现。及格分线为750。你的分数反映了你在整场考试中的表现以及是否通过。计分模型有助于在不同难度略有差异的多个考试形式之间进行等分。
Your score report could contain a table of classifications of your performance at each section level. The exam uses a compensatory scoring model, which means that you do not need to achieve a passing score in each section. You need to pass only the overall exam.你的成绩报告可能包含各部分的绩效分类表。考试采用补偿性评分模型，这意味着你不必在每个部分都取得及格分数，只需通过整体考试即可。
Each section of the exam has a specific weighting, so some sections have more questions than other sections have. The table of classifications contains general information that highlights your strengths and weaknesses. Use caution when you interpret section-level feedback.考试的每个部分都有特定的权重，因此某些部分的题目数量多于其他部分。绩效分类表包含一般性信息，突出你的优势和劣势。在解读各部分反馈时请谨慎。
Content outline
This exam guide includes weightings, content domains, tasks, and skills for the exam. This guide does not provide a comprehensive list of the content on the exam.本考试指南包括考试的权重、内容领域、任务和技能。本指南并未提供考试内容的完整列表。
The exam has the following content domains and weightings:考试包含以下内容领域及权重：
Content Domain 1: Foundation Model Integration, Data Management, and Compliance (31% of scored content)内容领域 1：基础模型集成、数据管理和合规性（占已计分内容的31%）
Content Domain 2: Implementation and Integration (26% of scored content)内容领域 2：实现与集成（占已计分内容的26%）
Content Domain 3: AI Safety, Security, and Governance (20% of scored content)内容领域 3：AI安全、安全性和治理（占已计分内容的20%）
Content Domain 4: Operational Efficiency and Optimization for GenAI Applications (12% of scored content)内容领域 4：面向GenAI应用的运营效率和优化（占已计分内容的12%）
Content Domain 5: Testing, Validation, and Troubleshooting (11% of scored content)内容领域 5：测试、验证和故障排除（占已计分内容的11%）
Survey
How useful was this exam guide? Let us know by taking our survey
