FPT Software Hanoi · NGT

From first pipeline to self-healing platform

Cloud, DevSecOps, platforms, AI and data — built on delivery experience, accelerated by AI, decided by our architects.

Explore capabilities
IntelligenceAI that acts, models that ship, operations that heal
DeliverySecure pipelines and self-service platforms
FoundationClouds landed properly, and paid for wisely
One delivery model for every capability: Assessment → MVP / PoC → Planning → Implementation → Operation

What's new

The latest in NGT's practice: each card opens a capability's pages.

AI & AgentsAI & Agents6 pages, starting with Assistants & RAGNew practiceDataOps6 pages, starting with LifecycleOperationsAIOps5 pages, starting with Service linesPlatformsPlatform Engineering6 pages, starting with Why platform engineering
8capabilities, foundation to intelligence
5clouds: AWS, Azure, Google Cloud, Huawei, Alibaba
144exam-based certifications from AWS, Microsoft Azure, Google Cloud, Huawei Cloud and Alibaba Cloud (November 2024)
65reference architectures, drawn with each cloud's own icons
Scope: NGT. Certificates: FPT Software Hanoi certification register (Nov 2024; 2025 records for Google Cloud), November 2024.

Real designs, drawn with each cloud's own icons. Select a component to see what it does.

Specialised agents behind one super-agent, acting on enterprise systems through an MCP gateway, inside guardrails, routing, audit and a hand-over to people.

Multi-Agent Harness for IT Operations
ticketsrequeststoken checkmodel callsknowledge · memorypolicy checksignalsopens a tickethand-overIdentity, models, runtime and policyWork coming inGateway pipelineAgent workflowsSpecialised agentsToolsEnterprise systemsKnowledge, memory and eventsAuditPeopleKeycloakSSO · SAML / OIDCAD / LDAPcustomer directoryLiteLLMmodel routing · budgetsLLMsClaude · OpenAIKubernetescontainer orchestrationAWS Secrets ManagerOPApolicy as codeITSM deskticketsChat and portalusers, IT operatorsMonitoring signalsapps, databases, servicesKongAPI gatewayGuardrails AIinput and output checksSuper-agentroutes by intentIntake agentclassify, routeKnowledge agentanswers with sourcesData agentquery → run → checkMonitoring agentdetects anomaliesRunbook agentconfirm, guide the fixChange agentplan → deploy → testMCP gatewayContextForgeTickets and changesITSM recordsDatabasesServers and legacyappsAPI · MCP · DBKafkaevent modelQdrantvectors · BM25 + RRFNeo4jknowledge graphPostgreSQLoperational dataMongoDBconversations, contextRedisshort-term memoryObservabilitylogs · traces · alertsEngineerhand-over · approvals

Point at a component to light its links; select it for what it does here and the practice that makes it right on AWS.

Point at a component to see what it does; select it for the best practice.Open the architecture

One delivery model for every capability

Every engagement starts from an assessment against our maturity checklist, and ends in something your team can run.

1Assessment2MVP / PoC3Planning4Implementation5Operation
AssessmentMVP / PoCPlanningImplementationOperationStrategy to execution

Five clouds, and the tools we run on them

awsmicrosoft-azuregoogle-cloudhuawei-cloudalibaba-cloud
kubernetesterraformgitlabgithubargobackstagevaultsonarqubeprometheusgrafanaopentelemetrydatadogmlflowkubeflowlanggraphopenaihuggingfaceservicenow