Browsing: Guides & Tutorials

Most AI agent conversations start in the wrong place. The first question is usually, “What can the agent do?” Can it answer questions? Can it search documents? Can it open tickets? Can it call APIs? Can it update records? Can it trigger a workflow? Those are useful questions, but they are not the first questions infrastructure and security teams need answered. The better first question is: Who is this thing when it acts? That question changes the architecture conversation. A chatbot is something a user talks to. An agent is something that can act inside your environment. Once an AI…

TL;DR VCF Operations is no longer just an observability tool sitting beside the VMware Cloud Foundation stack. In the VCF 9.x operating model, it is becoming a central part of how teams manage the fleet, monitor health, support lifecycle workflows, handle certificates and passwords, improve diagnostics, understand cost, and enforce operational governance. That shift matters. For years, many VMware environments treated operations tooling as something added after the platform was already built. Deploy vSphere. Add NSX. Configure vSAN. Bring in operations tooling later if the organization had the licensing, maturity, or pain level to justify it. That model does not…

AI demand rarely arrives as a clean infrastructure request. It usually starts as a conversation. A data science team has a model they want to test. A business unit wants an internal assistant. A security team wants retrieval-augmented generation close to sensitive data. A platform team is asked whether the existing private cloud can “just add GPUs.” That is where many infrastructure teams get pulled into the wrong first decision. The first decision is not which GPU server to buy, whether the workload should run on Kubernetes or a VM, or whether the cluster should be VxRail, Dell vSAN Ready…

Retrieval-augmented generation became popular because it solved a real problem. Large language models do not automatically know your internal policies, diagrams, runbooks, tickets, contracts, architecture decisions, or platform standards. RAG gives the model a way to answer with enterprise context instead of relying only on training data. That is the promise. The production reality is more complicated. Many RAG systems work well in demos and degrade when the document estate becomes messy, duplicated, permissioned, stale, contradictory, or operationally important. The failure is not always the model. Often, the failure is retrieval architecture. If the wrong context reaches the prompt, the…

TL;DR VCF Express Patches should be handled through a repeatable runbook, not an improvised maintenance window. The practical workflow is to confirm the current VCF and component baseline, synchronize depot metadata, review release-note applicability, validate backups and platform health, patch lifecycle and management services where needed, apply component updates through VCF Operations, and capture enough evidence to prove the environment returned to a known-good state. Scenario You are running VMware Cloud Foundation 9.1 and a new Express Patch appears in VCF Operations. Security wants the fix applied quickly. Operations wants to avoid breaking the management plane. Application owners want to…

Private AI will not fail in most enterprises because the model cannot run. It will fail because nobody can answer a simple question clearly: Who owns this thing? That question sounds basic until the first production AI use case crosses infrastructure, GPUs, model runtime, vector data, business logic, identity, audit logging, security policy, and operational support. In a traditional application stack, ownership is usually split across application teams, infrastructure teams, data teams, and security teams. Private AI compresses all of those concerns into one delivery path and then adds model behavior, prompt inputs, retrieval data, inference cost, and governance evidence…

How VCF 9.1 Reframes the Private Cloud Conversation For years, the VMware conversation was mostly about virtualization, consolidation, lifecycle management, and private cloud standardization. Those topics still matter. They are not going away. But AI has changed the center of gravity. The question is no longer just, “Can the platform run VMs reliably?” The better question is, “Can the platform run traditional applications, Kubernetes workloads, AI inference, agentic workflows, sensitive data pipelines, and GPU-backed services under one governed operating model?” That is the impact AI is having on VMware. AI is forcing VMware Cloud Foundation to become more than a…

Traditional virtualization design habits do not automatically translate to inference-heavy AI platforms. That is not because virtualization suddenly stopped being useful. It is because the constraint model changed. For years, many virtualization clusters were designed around CPU consolidation, memory overcommit, shared storage resilience, and generalized mobility. That model worked well for mixed enterprise workloads where the scheduler could balance demand across a relatively fungible resource pool. AI inference is different. Inference-heavy platforms introduce harder placement constraints, larger memory footprints, accelerator dependency, model-serving latency targets, and new lifecycle coupling between host drivers, guest drivers, firmware, runtime images, and model-serving frameworks. Deloitte’s…

Enterprise teams are moving past the point where an AI agent is just a prompt wrapped around a tool call. The real design question is no longer whether an agent can call an API. The question is whether the organization can control what happens before, during, and after that call. That is why choosing an agent framework is not just a developer preference. It is an operating model decision. A proof of concept can survive with a simple loop: receive a task, call a model, execute a tool, return an answer. A production agent cannot. Production agents need state, policy…

AI placement is becoming a real architecture decision. For the first wave of generative AI adoption, many organizations could experiment with hosted models, isolated copilots, and proof-of-concept retrieval systems without making hard infrastructure choices. That window is closing. AI is moving from isolated experiments into business workflows, operational systems, and agentic patterns that can retrieve information, make recommendations, and trigger actions. That shift changes the placement conversation. The question is no longer simply: Should AI run in the cloud or on-prem? A better question is: Where should inference, retrieval, orchestration, policy enforcement, and audit evidence live so the system can…