Embark on a journey to create AI agents with "Crafting Your First AI Agent." This hands-on lab introduces LangChain, LangGraph, and CrewAI frameworks, empowering you to build, run, and understand AI agents. Discover the intricacies of AI workflows and multi-agent systems, transforming curiosity into practical expertise.

Talk face to face with Sky, a real-time AI assistant running on two NVIDIA DGX Spark systems with no cloud in the loop. Start a video call, interrupt it mid-sentence and watch each turn split across both Sparks: one hears, thinks and animates the face, the other speaks and searches the lab's knowledge.

Why does a large language model write one token at a time, and how can a small drafter make it faster without changing the answer? Explore a real recorded run on an NVIDIA L40S through bets, interactive blocks and a head-to-head race. No GPU reservation needed: start anytime, finish in about 30 minutes.

Run Hermes Agent as an on-call operations team for a storefront outage. Fan out parallel investigators, adjudicate a risky change with a Mixture-of-Agents board, execute the fix under a goal contract with machine-verified proof, and review the agent run afterward.

In this lab you build two agent architectures from scratch in Python, with no framework hiding the mechanics: an orchestrator that routes work to specialized workers, and a ReAct loop that reasons, acts, and observes until it has an answer. You'll expose the strengths and weaknesses of these architectures first hand. You'll leave understanding how each pattern works under the hood, and gain a feel for how and where these patterns are best applied.

The recruitment of patients for clinical trials presents significant challenges for pharmaceutical companies, often delaying drug development, increasing cost, and lead to study failure. This lab explores how AI applied to anonymized health records enables efficient trial matching—at single, bulk, and multi-trial levels—reducing time, improving accuracy, and enhancing access for researchers, providers, and patients.

Routing LLM Requests with NVIDIA Switchyard teaches config-driven LLM routing through a hands-on Docker Compose lab. Students deploy an OpenAI-compatible proxy plus dashboard, use passthrough routes, binary and category-based LLM classifiers, then measure real cost, latency, and quality tradeoffs between routed and frontier-baseline models across six progressive modules.

Watch a multi-agent AI system run network operations on a live Cisco leaf-spine fabric. It detects configuration drift against a golden baseline, diagnoses root cause from live telemetry, and proposes Ansible remediation — but executes nothing without your approval. Work five realistic incidents, from a fat-finger mistake to a deliberate attack, and judge where agentic automation belongs.

Experience Cisco AI Defense in an interactive Capture the Flag (CTF), designed to showcase how Cisco is securing the future of GenAI.

A hands-on lab where learners configure LiteLLM as a local reverse proxy that intelligently routes requests between multiple LLM backends — a general model for simple prompts, a coding model and a reasoning model for complex ones — instead of hard-coding a single model into an application.

In this lab, we'll be focusing on the programatic steps of Retrieval Augmented Generation (RAG). First, we'll discuss data chunking, how we break down our documents. Then, we'll explore how these chunks become embeddings, numerical representations. Finally, we'll see how a vector database helps us efficiently retrieve this information.