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.

NVIDIA's AI Blueprint for RAG is a foundational guide for developers to build powerful data extraction and retrieval pipelines. It leverages NVIDIA NeMo Retriever models to create scalable and customizable RAG (Retrieval-Augmented Generation) applications. This blueprint allows you to connect large language models (LLMs) to a wide range of enterprise data, including text, tables, charts, and infographics within millions of PDFs. The result is context-aware responses that can unlock valuable insights. By using this blueprint, you can achieve 15x faster multimodal PDF data extraction and reduce incorrect answers by 50%. This boost in performance and accuracy helps enterprises drive productivity and get actionable insights from their data.

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.

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.