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.

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.

In this lab, you will have access to a deployment of an AMD blueprint for a Financial Stock Intelligence Agent. It is deployed on AMD Instinct MI250X instance in the ATC. Built using LangChain and powered by AMD Inference Microservices (AIM), this solution combines real-time market data, technical indicators, and large language model analysis to deliver AI-generated stock insights through an interactive web interface. Financial analysts and developers can explore how AMD's open AI stack accelerates inference for financial workflows.

In this lab you will explore an NVIDIA Data Flywheel running on Cisco Secure AI Factory hardware with NVIDIA in WWT's AI Proving Ground. Built on the NVIDIA NeMo microservices platform, the flywheel automatically turns production traffic into evaluation and fine-tuning datasets, LoRA fine-tunes candidate models with NeMo Customizer, scores them against the incumbent with NeMo Evaluator, and deploys the winner as an NVIDIA NIM. Using a clinical coding application as the example workload, you will watch a 1-billion-parameter model close the accuracy gap on a 70-billion-parameter model at a fraction of the inference cost.

In this lab, customers explore the LLM Router deployed on AMD Instinct MI250 accelerators in the ATC. Built from the AMD Enterprise AI Suite solution blueprint catalog, the LLM Router puts a single OpenAI-compatible endpoint in front of a portfolio of models and decides, prompt by prompt, which model should answer. Lightweight requests are served by a small, fast model; hard reasoning and code generation are escalated to a large one. The result is a practical answer to the accuracy-versus-cost tradeoff that every organization running self-hosted inference eventually confronts — delivered on a fully open source AMD software stack.

Compare large language models side by side using WWT's AI Proving Ground GPU cluster. Send the same prompt to multiple models at once and evaluate their responses in real time — measuring response speed, reasoning quality, and output style across leading open-source and proprietary models. No setup required. The lab environment connects automatically to the LLMaaS AI Gateway, giving you direct access to production-grade inference endpoints used by WWT's AI engineering teams.

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.

Primary care and pediatric providers can spend significant time manually cross-referencing multiple sources to construct accelerated catch-up protocols for unvaccinated or under-vaccinated patients. The Pediatric Vaccine Assistant streamlines this workflow, reducing administrative burden and supporting evidence-based care.

Explore how InfiniBand fabrics power modern AI clusters through a guided tour of NVIDIA Unified Fabric Manager (UFM). Learn core InfiniBand concepts, RDMA, routing, telemetry, and fabric automation while examining a live GPU-focused environment. This read-only lab focuses on observing topology, health, performance, and management workflows used in large-scale AI and HPC deployments.

Deploy secure, always-on AI agents in minutes using NVIDIA NemoClaw's single-command installer. In this hands-on lab, you'll install NemoClaw, configure NVIDIA OpenShell's privacy and security guardrails, and run your first autonomous agent powered by local open models like NVIDIA Nemotron. You'll see firsthand how policy-based controls govern agent behavior and keep sensitive data secure.