This lab is intended to give you an overview of HPE Private Cloud AI, HPE's turnkey solution for on-prem AI workloads. HPE has paired with NVIDIA's AI Enterprise software giving customers a scalable on-prem solution that can handle multiple different AI workloads from Inference, RAG, model fine-tuning, and model training.

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.

Explore the WWT Agentic Network Assistant, a browser-based AI tool that converts natural language into Cisco CLI commands, executes them across multiple devices, and delivers structured analysis. Using a local LLM, it streamlines troubleshooting, summarizes device health, and compares configs, demonstrating the future of intuitive, AI driven network operations.

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

Explore the hidden dangers of prompt injection in Large Language Models (LLMs). This lab reveals how attackers manipulate LLMs to disclose private information and behave in ways that they were not intended to. Discover the intricacies of direct and indirect prompt injection and learn to implement effective guardrails.

This lab will help users strengthen their prompt engineering skills using the prompt blueprint framework, which is a structured approach for writing effective prompts. Participants will refine prompts step by step and experiment with blueprint elements to achieve better model outputs.

In the current AI market, the demand for scalable and secure deployments is increasing. Public cloud providers (AWS, Google, and Microsoft) are competing to provide GenAI infrastructure, driving the need for multi-cloud and hybrid cloud deployments. However, distributed deployments come with challenges, including: Complexity in managing multi-cloud environments. Lack of unified visibility across clouds. Inconsistent security and policy enforcement. F5 Distributed Cloud provides a solution by offering a seamless, secure, and portable environment for GenAI workloads across clouds. This lab will guide you through setting up and securing GenAI applications with F5 Distributed Cloud on AWS EKS and GCP GKE.

Iterate.ai's Generate platform pairs with Intel Xeon CPUs, Gaudi 3 accelerators, Pure Storage FlashBlade//S, and Milvus vector DB. Deployed via Kubernetes/Slurm, it scales quickly, needs minimal tuning, and runs Llama 3, Mistral, and Inflection to accelerate AI training, inference, and search for healthcare, life-science, and finance workloads.

The WWT AI-Powered Predictive Maintenance Assistant uses machine learning and a large language model to predict equipment failures, schedule maintenance, generate instructions, and answer related questions. Through an interactive UI, users explore proactive, data-driven strategies to reduce downtime, extend machine life, and optimize resources, demonstrating AI's transformative potential in manufacturing environments.

In this lab a customer will deploy the Incident Knowledge Assistant on the HPE Private Cloud AI instance in the ATC. This Assistant is built on top of the NVIDIA NeMo Agent Toolkit and leverages Open AI OSS NIMs under the hood. Leveraging representative data from an IT Service Management Platform, the Incident Knowledge Assistant identifies the most relevant information from Incident, Change and Problem Management as well as the Knowledge Base to provide fast targeted guidance for IT Operations specialists.

In this lab, customers will deploy the Intelligent Resource Optimizer on the HPE Private Cloud AI instance in the ATC. Built using the NVIDIA NeMo Agent Toolkit and powered by Open AI OSS NIMs, this solution moves beyond static analysis to proactive infrastructure management. By integrating a specialized Time Series model, the Intelligent Resource Optimizer analyzes historical system utilization to accurately forecast future resource demands. This allows IT Operations teams to receive data-driven recommendations for scaling and optimization, ensuring peak performance and cost-efficiency across the environment.

Training data poisoning poses significant risks to Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) systems. This lab explores these dangers through a case study of an online forum, demonstrating how corrupted data can compromise AI effectiveness and security, and examines methods to mitigate such threats.