> ## Documentation Index
> Fetch the complete documentation index at: https://grandcentral.backbase.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Platform architecture

> Multi-cloud architecture, topology, and developer guide

The Agentic Platform provides a production-ready, multi-cloud infrastructure for building and deploying AI agents. This architecture uses Kubernetes, GitOps, and enterprise-grade observability to deliver 99.9% availability across any cloud provider.

## Architecture overview

<div className="web-image">
  <img src="https://mintcdn.com/ecosystems-documentation/3JBydSR0e3N4OKkt/assets/images/agentic-ai/core%20building%20blocks%20architecture.png?fit=max&auto=format&n=3JBydSR0e3N4OKkt&q=85&s=1963cabfe743e6b8a57a07434ad6a484" alt="Agentic Platform multi-cloud architecture diagram" width="2604" height="1254" data-path="assets/images/agentic-ai/core building blocks architecture.png" />
</div>

### Platform layers

The architecture diagram shows five foundational layers that work together:

<AccordionGroup>
  <Accordion title="1. foundation (infrastructure)" icon="layer-group">
    * **Kubernetes**: Container orchestration across any cloud provider
    * **Service Mesh**: Istio for traffic management, security, and observability
    * **Container Runtime**: Docker for containerization
    * **Packaging**: Helm charts for deployment configuration
  </Accordion>

  <Accordion title="2. data" icon="database">
    * **Vector Storage**: [PostgreSQL](/agentic-ai/architecture/data-protection) with pgvector for embeddings and RAG
    * **Caching**: Redis for session state and fast lookups
    * **Object Storage**: Cloud-native storage for artifacts and models
    * **Message Bus**: Azure Service Bus for async workflows
    * **Registries**: Container registries (ACR/ECR/GCR) and package registries (GitHub Packages)
  </Accordion>

  <Accordion title="3. AI gateway" icon="shield-halved">
    * **Provider Abstraction**: Unified interface to Azure AI Foundry, OpenAI, Gemini, Anthropic, or BYO models
    * **Policy Enforcement**: Guardrails, rate limiting, cost management, and content safety
    * **Traffic Management**: Semantic caching, load balancing, and intelligent request routing
    * **PII Protection**: Automatic detection and sanitization
    * **SDK Access**: BB AI SDK for standardized integration
  </Accordion>

  <Accordion title="4. agent runtime" icon="sitemap">
    * **Agent Workloads**: FastAPI-based APIs with background workers
    * **Orchestration**: Agno and LangGraph for multi-step workflows
    * **MCP Integration**: Model Context Protocol servers for tool access
    * **Banking Services**: Pre-integrated domain services (deposits, payments, loans, fraud)
    * **Guardrails and Safety**: Real-time evaluations, content safety filters, PII detection/sanitization, jailbreak prevention, prompt validation
    * **Observability**: OpenTelemetry traces, Langfuse runs, metrics, and logs
  </Accordion>

  <Accordion title="5. control plane and ingress" icon="gears">
    * **Ingress**: API Management (APIM) with DNS, WAF, SSL termination
    * **GitOps**: Argo CD for declarative, automated deployments
    * **CI/CD**: Automated pipelines with PR checks, builds, and releases
    * **Self-Service**: Repository provisioning and infrastructure automation
    * **Monitoring**: Grafana dashboards, PagerDuty alerts, real-time evaluations
  </Accordion>
</AccordionGroup>

### Runtime flow

<div className="web-image">
  <img src="https://mintcdn.com/ecosystems-documentation/3JBydSR0e3N4OKkt/assets/images/agentic-ai/hosted%20architecture.png?fit=max&auto=format&n=3JBydSR0e3N4OKkt&q=85&s=5778ec8d7eb819eac095e5414c22f401" alt="Agentic Platform runtime request flow" width="2790" height="1454" data-path="assets/images/agentic-ai/hosted architecture.png" />
</div>

When a client makes a request:

1. **Client → APIM → Agent API**: Request enters through API Management with authentication and rate limiting
2. **Agent → AI Gateway**: Agent calls LLM through gateway with guardrails and traffic control applied
3. **AI Gateway → LLM Provider**: Request routed to selected provider (Azure AI Foundry or BYO) with policies enforced
4. **Tool Execution**: Agent calls MCP servers (banking domains) or direct REST/GraphQL APIs
5. **Observability**: OTel traces and Langfuse runs capture every step; logs and metrics flow to platform sinks
6. **Real-time Evaluation**: Automated evaluations flag risks (safety, PII, jailbreaks) and feed continuous improvements

## Next steps

<CardGroup cols={2}>
  <Card title="Technology stack" icon="layer-group" href="/agentic-ai/architecture/technology-stack">
    Explore the detailed technology stack and implementation deep dive
  </Card>

  <Card title="Data protection and backup" icon="database" href="/agentic-ai/architecture/data-protection">
    Automated PostgreSQL backups, retention, and restore requests
  </Card>

  <Card title="Get started" icon="rocket" href="/agentic-ai/get-started/get-started">
    Start building your first AI agent on the platform
  </Card>
</CardGroup>