​​"Generative AI Learning Plan for Developers"​​ is a comprehensive AWS training program designed for developers aiming to build scalable generative AI applications ​​without fine-tuning large language models (LLMs)​​. This 14-hour curriculum blends foundational knowledge with hands-on practice, covering ​​Amazon Bedrock​​, prompt engineering, retrieval-augmented generation (RAG), and LangChain integration. Developers will learn to prototype AI-driven solutions like chatbots, text/code generators, and vision-based applications while addressing security, bias mitigation, and cost optimization. The course culminates in building real-world projects using AWS services, preparing learners to deploy enterprise-ready AI systems and earn AWS certifications.

​​"Amazon Bedrock Getting Started"​​ is a foundational AWS course designed for developers and technical professionals seeking to leverage ​​generative AI​​ through Amazon Bedrock's fully managed service. This course introduces Bedrock's core features, including access to leading foundation models (FMs) like those from Anthropic, Cohere, and Amazon, while emphasizing privacy, security, and serverless architecture. Through guided tutorials, learners explore real-world applications such as chatbot development, embedding generation, and cost-optimized workflows. The curriculum also covers Bedrock's integration with AWS services, model customization via techniques like Retrieval Augmented Generation (RAG), and practical implementation using the AWS Management Console.

​​"Building Generative AI Applications Using Amazon Bedrock"​​ is an advanced 6-hour AWS course tailored for developers aiming to master generative AI application development. It focuses on integrating ​​Amazon Bedrock APIs​​ and ​​LangChain​​ to build scalable solutions like Retrieval Augmented Generation (RAG) systems, AI assistants, and text/code generators. Learners dive into architecture patterns, foundation models (e.g., Claude, Titan), and AWS services such as ​​Bedrock Knowledge Bases​​ and ​​Guardrails​​ for ethical AI deployment. Hands-on labs teach practical skills—from invoking models and optimizing prompts to deploying secure agents—using Jupyter notebooks and AWS console tutorials. Prerequisites include Python proficiency and foundational AWS knowledge.