In this lab we will explore F5 AI Guardrails which is a runtime security platform for generative AI and agentic AI systems, focused on securing the AI inference layer—the point where models receive prompts and generate outputs.

In this lab, you will walk through an on‑premises solution for serving your private cloud AI system using VMware Private AI. Building on the foundational components of VMware Cloud Foundation (VCF), VMware Private AI leverages Tanzu Kubernetes to deliver a streamlined, enterprise‑ready platform. This solution is designed to help you accelerate your AI journey by enabling scalable, secure, and efficient deployment of AI workloads within your private cloud environment.

This lab will guide and educate you on what the F5 BIG-IP Next Cloud-Native Network Functions are, how they are deployed with NVIDIA DOCA, and how they will ultimately help show the gains in offloading traffic to DPUs instead of tying up resources for your applications on the CPU of the physical K8 host.

In this hands-on lab, you'll learn how to set up a disconnected installation of OpenShift, allowing you to deploy and manage OpenShift clusters in environments without direct internet access. You'll begin by downloading the necessary OpenShift components on a connected host, transferring them to a disconnected host, and proceeding with installing OpenShift on bare metal servers using the agent-based installer. By the end of this lab, you'll have a fully functional, disconnected OpenShift cluster. This lab is ideal for users working in secure or isolated environments where external connectivity is restricted or non-existent.