COURSES

Amazon Web Services

A wide range of learning to choose from presented by professional instructors.

OUR COURSES SERIES

Amazon Web Services Course Directory

AIF-C01: AWS Certified AI Practitioner

Start your free trial

Course Name	Course Type	Syllabus
AWS AI Practitioner: Basic AI Concepts and Terminologies	Course	View details Course Syllabus \| Print Syllabus AWS AI Practitioner: Basic AI Concepts and Terminologies Overview/Description: Since Amazons idea of the machine learning flywheel was sketched on the back of a napkin, Amazon has been investing in specific key business operations driven by artificial intelligence (AI) and machine learning (ML) to reinforce other processes and create a positive feedback loop.In this course, explore what AI, ML, and deep learning are and basic AI terms such as natural language processing (NLP), training, and inferencing. Next, learn about large language models (LLMs) and the differences between AI, ML, and deep learning. Finally, examine inference types and data types in AI models and compare machine learning methods.This course is part of a collection that prepares you for the AIF-C01: AWS Certified AI Practitioner exam. Course Number: it_clawsaif_01_enus
AWS AI Practitioner: Basic Concepts of Generative AI	Course	View details Course Syllabus \| Print Syllabus AWS AI Practitioner: Basic Concepts of Generative AI Overview/Description: Generative AI is a newer form of artificial intelligence (AI) that differs from other AI approaches primarily because it creates original content, while other AI approaches analyze or classify existing data and information.In this course, learn generative AI concepts such as tokens, chunking, embeddings, vectors, prompt engineering, transformer-based LLMs, foundation models, multi-modal models, and diffusion models. Next, explore potential use cases for generative AI models, like image, video, and audio generation, as well as summarization, chatbots, translation, code generation, customer service agents, and search and recommendation engines. Finally, examine the foundation model lifecycle phases, including data selection, model selection, pre-training, fine-tuning, evaluation, deployment, and feedback.This course is part of a collection that prepares you for the AIF-C01: AWS Certified AI Practitioner exam. Course Number: it_clawsaif_05_enus
AWS AI Practitioner: Building Generative AI Applications with AWS	Course	View details Course Syllabus \| Print Syllabus AWS AI Practitioner: Building Generative AI Applications with AWS Overview/Description: Amazon Web Services (AWS) offers several tools and services to help you build generative AI applications, such as the Amazon Bedrock platform, the Amazon SageMaker fully managed service, and the Amazon Bedrock Studio web-based development environment.In this course, learn how to develop generative AI applications with Amazon SageMaker JumpStart, Amazon Bedrock, Amazon Q, and PartyRock. Next, explore the advantages of using AWS generative AI services for building applications. Finally, discover the benefits and cost tradeoffs of using the AWS infrastructure for generative AI applications.This course is part of a collection that prepares you for the AIF-C01: AWS Certified AI Practitioner exam. Course Number: it_clawsaif_07_enus
AWS AI Practitioner: Capabilities and Limitations of Generative AI	Course	View details Course Syllabus \| Print Syllabus AWS AI Practitioner: Capabilities and Limitations of Generative AI Overview/Description: Generative AI can produce text, images, and music that mimic human creativity and draft essays, design graphics, assist in coding, and answer complex questions. However, it is not all-powerful, as it cannot feel emotions, understand context deeply, or produce genuinely original ideas. In this course, explore the capabilities and limitations of generative AI for solving business problems in the real world, including the advantages and disadvantages of using AWS generative AI services to build applications. Next, learn how to select the appropriate generative AI models for your needs. Finally, examine how to determine the business value and metrics for generative AI applications.This course is part of a collection that prepares you for the AIF-C01: AWS Certified AI Practitioner exam. Course Number: it_clawsaif_06_enus
AWS AI Practitioner: Design Factors for Applications Using Foundation Models	Course	View details Course Syllabus \| Print Syllabus AWS AI Practitioner: Design Factors for Applications Using Foundation Models Overview/Description: An AI foundation model is a large-scale ML model trained on huge volumes of data that can perform a wide range of tasks. These models can be fine-tuned for specific applications with minimal additional training.In this course, explore design considerations for applications using foundation models at AWS, including identifying selection criteria for pre-trained models and the effect of inference parameters on model responses. Next, learn about Retrieval-Augmented Generation (RAG) and its business applications and AWS services for storing embeddings within vector databases. Finally, examine the cost tradeoffs of various approaches to foundation model customization and the role of agents in multi-step tasks.This course is part of a collection that prepares you for the AIF-C01: AWS Certified AI Practitioner exam. Course Number: it_clawsaif_08_enus
AWS AI Practitioner: Effective Prompt Engineering Techniques	Course	View details Course Syllabus \| Print Syllabus AWS AI Practitioner: Effective Prompt Engineering Techniques Overview/Description: AI prompt engineering is the process of designing and refining prompts to effectively guide generative AI (GenAI) models, like GPT-4, to produce desired outputs.In this course, explore the concepts and constructs of prompt engineering, beginning with differentiating between techniques for prompt engineering such as chain-of-thought, zero-shot, single-shot, and few-shot prompt engineering. Next, learn how to execute prompt engineering with prompt templates. Finally, discover the benefits and best practices for prompt engineering and its potential risks and limitations.This course is part of a collection that prepares you for the AIF-C01: AWS Certified AI Practitioner exam. Course Number: it_clawsaif_09_enus
AWS AI Practitioner: Guidelines for Responsible AI	Course	View details Course Syllabus \| Print Syllabus AWS AI Practitioner: Guidelines for Responsible AI Overview/Description: Responsible AI focuses on creating and deploying AI systems ethically and in line with societal values, taking bold steps to protect people and the planet. The mission is to ensure that AI technologies are fair, accountable, and beneficial for everyone.This course explores responsible AI features and tools, practices, legal risks, dataset characteristics, and transparent models like Amazon SageMaker Model Cards, open-source models, and licensing. It also addresses tradeoffs in model safety and transparency, and principles of human-centered design for explainable AI. This course is part of a collection preparing you for the AIF-C01: AWS Certified AI Practitioner exam. Course Number: it_clawsaif_11_enus
AWS AI Practitioner: ML Operations (MLOps)	Course	View details Course Syllabus \| Print Syllabus AWS AI Practitioner: ML Operations (MLOps) Overview/Description: MLOps, or machine learning operations, is a multidisciplinary approach that combines machine learning, data engineering, and DevOps to automate and improve the efficiency of machine learning (ML) workflows in development and production environments.In this course, examine MLOps experimentation, repeatable processes, and scalable systems, in addition to how to manage technical debt and achieve production readiness. Next, explore model monitoring and retraining and metrics for model performance, including accuracy, F1 score, and area under the ROC curve (AUC). Finally, learn about business metrics like cost per user, development costs, customer feedback, and return on investment (ROI).This course is part of a collection that prepares you for the AIF-C01: AWS Certified AI Practitioner exam. Course Number: it_clawsaif_04_enus
AWS AI Practitioner: Practical Use Cases for AI	Course	View details Course Syllabus \| Print Syllabus AWS AI Practitioner: Practical Use Cases for AI Overview/Description: AWS offers a broad, deep set of machine learning services and supporting cloud infrastructure, putting ML in the hands of every developer, data scientist, and expert practitioner.In this course, discover where AI/ML can add value, when their use may not be appropriate, and ML techniques for use cases and examples of real-world applications. Next, learn how to utilize Amazon SageMakers capabilities and the key features of Amazon Transcribe and Amazon Translate. Finally, learn the basic capabilities of Amazon Comprehend and Amazon Lex and how to utilize Amazon Pollys key features.This course is part of a collection that prepares you for the AIF-C01: AWS Certified AI Practitioner exam. Course Number: it_clawsaif_02_enus
AWS AI Practitioner: Security Compliance and Governance for AI Solutions	Course	View details Course Syllabus \| Print Syllabus AWS AI Practitioner: Security Compliance and Governance for AI Solutions Overview/Description: In our ever-changing world, AI is transforming our lives. While it poses challenges like bias and transparency issues, it also offers opportunities to enhance security and governance. In this course, explore AWS services and features that secure AI systems, including IAM roles, policies, permissions, and the AWS shared responsibility model. Discover best practices for data engineering, source citation, and security and privacy considerations for AI systems. Finally, learn about regulatory compliance standards, governance services like AWS Config and AWS Trusted Advisor, and data governance strategies. This course is part of a collection that prepares you for the AIF-C01: AWS Certified AI Practitioner exam. Course Number: it_clawsaif_12_enus
AWS AI Practitioner: The ML Development Lifecycle	Course	View details Course Syllabus \| Print Syllabus AWS AI Practitioner: The ML Development Lifecycle Overview/Description: Data scientists have discovered that machine learning (ML) is not successful when approached with traditional programming and coding methodologies and lifecycles. Although there are some similarities, ML development has unique pipeline components, model sources, production methods, and relevant services and features. In this course, you will examine components of an ML pipeline and sources of ML models. Next, discover methods for using a model in production and how to use Amazon SageMaker in an ML pipeline. Finally, learn about using SageMaker Data Wrangler, SageMaker Feature Store, and SageMaker Model Monitor in ML pipelines. This course is part of a collection that prepares you for the AIF-C01: AWS Certified AI Practitioner exam. Course Number: it_clawsaif_03_enus
AWS AI Practitioner: Training Fine-Tuning and Evaluating Foundation Models	Course	View details Course Syllabus \| Print Syllabus AWS AI Practitioner: Training Fine-Tuning and Evaluating Foundation Models Overview/Description: Foundation models (FMs) are designed to be highly adaptable, capable of performing a wide range of tasks such as natural language processing and image classification. However, they must also be properly trained, fine-tuned, evaluated, and tested. In this course, examine the elements for training and methods for fine-tuning a foundation model. Learn how to prepare data for fine-tuning and evaluate foundation model performance using human evaluation, benchmark datasets, and various metrics. Finally, discover the process used to determine if a foundation model effectively meets business objectives. This course is part of a collection that prepares you for the AIF-C01: AWS Certified AI Practitioner exam. Course Number: it_clawsaif_10_enus