Dive into the fascinating world of AI Agents in this comprehensive learning path that transforms beginners into creators. You'll explore what agents truly are and discover the inner workings that make them tick, from decision-making algorithms to execution frameworks. The journey continues with an in-depth look at the tools agents leverage and tasks they excel at, preparing you for the hands-on lab where you'll build your very own agent from scratch. By the end, you'll have both theoretical knowledge and practical experience in creating these powerful digital assistants that are revolutionizing how we interact with technology and solve complex problems.

This learning path introduces AI users to key concepts and practices for crafting effective prompts that maximize the value of AI tools. It begins by providing essential background knowledge to explain why prompt engineering is critical for generating high-quality responses. It will then culminate with the introduction of the Prompt Blueprint—a practical framework to help users design effective prompts.

The user of this learning path will learn the components of RoCE and why it is essential for clean, fast, and reliable AI/ML compute communication.

This learning path teaches you to build LLM applications using LangChain's composable building blocks. Three foundational articles explain orchestration frameworks, LangChain's place among them, and its core abstractions—prompts, chains, and pipelines. Hands-on labs then let you assemble these primitives into increasingly sophisticated patterns: structured output, memory management, RAG, and agentic tool use.

RAG, or Retrieval-Augmented Generation, is an AI solution that has gained popularity due to its ability to combine generative AI with external data sources to provide more accurate and up-to-date responses. However, these new abilities don't come without risk. In this learning path, you will gain a fundamental understanding of RAG security. Through a series of videos, you will explore topics such as RAG security risks, vector database security risks, and the best practices that can be used to help remediate some of these risks. Finally, you will take a look at all of it put together in the hands-on Training Data Poisoning lab.

This learning path covers vector search from concept to practice. Articles explain vectors, embeddings, similarity metrics, and vector store software — including how to choose the right database and index type. The hands-on lab then stress-tests embedding models, compares distance metrics, evaluates models of different sizes, and builds a framework for tuning chunking and measuring retrieval quality.

Understand InfiniBand AI fabric through its lossless architecture, SHARP in-network computing, and real-world economics. Then experience a full operational lifecycle from day-zero design through UFM deployment and predictive maintenance, reinforced with hands-on lab practice. Learn how self-driving operations and InfiniBand technologies are shaping the next generation of AI factories.

This is a learning path for the introduction of the deployment and lifecycle of AI infrastructure. Explore the NVIDIA GPU Operator, a Kubernetes-native tool that automates driver installation, container runtimes, and device plugins. Perfect for DevOps engineers aiming to streamline high-performance, GPU-accelerated clusters at scale.

Introduces LLM routing as a pattern for avoiding one-size-fits-all model usage, covering cost-based, complexity-based, and latency-based routing strategies and when adopting a router is (and isn't) worth it.

RAG, or Retrieval-Augmented Generation, is an AI solution that combines the power of Generative AI with external data sources to provide more accurate and up-to-date responses. This Learning Path explains the concept of RAG, its origins, and how it addresses key limitations of traditional GenAI systems. You'll learn about the benefits of RAG, including enhanced accuracy, reduced hallucinations, and its flexibility in integrating real-time information without the need for constant model retraining.