> ## 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.

# Technology stack

> Technologies, frameworks, and tools powering the Agentic Platform

The following sections outline the technology stack that powers the Backbase Agentic Platform, including supported languages, frameworks, observability tools, and deployment infrastructure.

## Programming languages

The platform supports agentic applications built in **any programming language**. However, developer enablement tooling, templates, and workflows are currently focused on **Python**.

<Tip>
  While Python is the primary supported language, you can deploy agents written in other languages (Node.js, Go, Java, etc.) as containerized workloads.
</Tip>

## SDKs and libraries

* **BB AI SDK**: Python SDK providing standardized connectors for AI Gateway, Observability, and common agent patterns. See **[BB AI SDK Overview](/agentic-ai/bb-ai-sdk/overview)**.

## Agentic frameworks

You can use **any agentic framework** to build your agents. The platform supports any framework, including:

* **Agno**: Lightweight Framework for building agentic applications with a very few lines of code
* **Google ADK**: Google's Agent Development Kit
* **LangChain**: Popular Python framework for building LLM applications
* **LangGraph**: State machine-based agent orchestration
* **Custom frameworks**: Any framework that can be containerized

<Note>
  **Starter kits** are currently available for **Agno-based** templates. Templates for other frameworks are coming soon.
</Note>

## Technology summary

<CardGroup cols={2}>
  <Card title="Languages" icon="code">
    Any language supported; Python-focused tooling
  </Card>

  <Card title="Frameworks" icon="layer-group">
    Agno, LangChain, LangGraph, Google ADK, or custom
  </Card>

  <Card title="SDK" icon="box-open">
    BB AI SDK for standardized platform connectivity
  </Card>

  <Card title="Observability" icon="chart-line">
    Langfuse (default), or custom OTel stack
  </Card>

  <Card title="Guardrails" icon="shield-halved">
    Nemo Guardrails for programmable rules
  </Card>

  <Card title="Evaluations" icon="check-double">
    Langfuse, Promptfoo, or custom
  </Card>

  <Card title="AI gateway" icon="server">
    Azure APIM with multi-provider support and content safety filters and policies
  </Card>

  <Card title="Models" icon="brain">
    Azure AI Foundry or BYO models
  </Card>

  <Card title="Deployment" icon="rocket">
    Argo CD with GitOps and Helm charts
  </Card>
</CardGroup>

## Platform technology deep dive

<AccordionGroup>
  <Accordion title="AI gateway and LLM management" icon="shield-halved">
    The AI Gateway provides a unified, provider-independent entry point for all LLM interactions:

    <div className="web-image">
      <img src="https://mintcdn.com/ecosystems-documentation/3JBydSR0e3N4OKkt/assets/images/agentic-ai/ai-gateway.png?fit=max&auto=format&n=3JBydSR0e3N4OKkt&q=85&s=254182821abbf1068d3eb355472caebd" alt="AI Gateway architecture diagram" width="906" height="341" data-path="assets/images/agentic-ai/ai-gateway.png" />
    </div>

    **Multi-Provider Support**

    * Azure AI Foundry (default)
    * OpenAI, Gemini, Anthropic
    * Bring Your Own (BYO) model providers

    **Traffic and Performance**

    * **Semantic caching**: Reduces latency and costs by recognizing similar queries
    * **AI-driven load balancing**: Predicts traffic patterns and distributes load intelligently
    * **Model routing**: Routes requests based on workload characteristics and cost optimization
    * **Rate limiting**: Per-agent and per-user controls

    **Access and Control**

    * Centralized access control and authentication
    * Cost management and budget enforcement
    * Request/response logging for audit trails
    * Accessed via **BB AI SDK** for standardized integration
  </Accordion>

  <Accordion title="Agent orchestration and runtime" icon="sitemap">
    **Deployment Model**

    * Kubernetes workloads with 99.5/99.9% availability SLA
    * FastAPI-based agent APIs with background worker support
    * Deployed via Argo CD with GitOps automation
    * Helm charts for packaging and configuration management
    * Optional Istio service mesh for advanced traffic policies

    **Orchestration Engines**

    * **Agno**: Production-grade agent orchestration
    * **LangGraph**: Graph-based multi-agent workflows
    * Multi-step process management
    * Team coordination and handoff patterns
    * Workflow state persistence
  </Accordion>

  <Accordion title="Banking services and MCP integration" icon="building-columns">
    Agents discover and call tools via the **Model Context Protocol (MCP)** - a standardized JSON-RPC protocol for agent-tool communication.

    **Integration Methods**

    * **Direct**: Agent connects to MCP server directly
    * **Via Grand Central**: Unified API layer for banking services
    * **Public MCP servers**: Third-party tool integrations

    **Available Banking Domain MCPs**

    The platform provides pre-integrated MCP servers for core banking operations:

    <CardGroup cols={2}>
      <Card title="Account services" icon="building-columns">
        * **Deposits**: Account management and operations
        * **Transactions**: History and queries
        * **Investment Account**: Investment management
      </Card>

      <Card title="Payments and transfers" icon="money-bill-transfer">
        * **Payments Initiation**: End-to-end payment lifecycle
        * **Batch Payment**: Bulk payment processing
        * **Currency Exchange**: FX operations
      </Card>

      <Card title="Lending and credit" icon="hand-holding-dollar">
        * **Loans**: Seamless lending journeys
        * **Party Access Entitlement**: Credit access control
      </Card>

      <Card title="Customer and security" icon="user-shield">
        * **Party Lifecycle**: Onboarding and verification
        * **Party Reference Data**: Customer data management
        * **Fraud**: Behavioral fraud management
        * **Device**: Card plastics lifecycle
      </Card>
    </CardGroup>

    <Tip>
      The platform is adopting **BIAN Coreless** for unified banking APIs and connectors.
    </Tip>
  </Accordion>

  <Accordion title="Data storage and performance" icon="database">
    **Vector and Knowledge Storage**

    * **PostgreSQL**: Vector database for embeddings and RAG applications. For backup and restore, see [Data protection and backup](/agentic-ai/architecture/data-protection).
    * **Redis**: Session state, short-term caching, and term-based search
    * **Object Storage**: Artifacts, models, and large file storage

    **Caching Strategy**

    * **Response caching**: Store LLM responses for identical queries
    * **Embedding caching**: Cache vector embeddings for knowledge retrieval
    * **Semantic cache**: AI Gateway-level similarity matching reduces redundant calls

    **Message and Event Handling**

    * Azure Service Bus for async workflows
    * Event-driven architectures for real-time updates
  </Accordion>

  <Accordion title="Security and governance" icon="shield-check">
    **AI Gateway Guardrails**

    * **PII detection and sanitization**: Regex-based detection with automatic redaction
    * **Content safety filters**: Toxicity, bias, and harmful content detection
    * **Prompt guard**: Compliance filtering and validation at the gateway level
    * **Jailbreak prevention**: Adversarial prompt detection

    **Security Layers**

    * **Input/output guardrails**: Programmable controls at gateway and prompt levels
    * **Red teaming**: Regular adversarial testing for injection attacks and misuse
    * **Prompt validation**: Pre-execution sanitization and approval workflows
    * **Secure SDLC**: Dependency scans, container scans, and code quality checks in CI/CD
    * **Agent sandboxes**: Mock API testing before production deployment
    * **RBAC**: Role-based access control for infrastructure, models, and data

    **Compliance and Audit**

    * Full request/response logging
    * Audit trails for all LLM interactions
    * Cost tracking per agent and team
    * Regulatory compliance reporting
  </Accordion>

  <Accordion title="Observability and continuous improvement" icon="chart-line">
    **Telemetry Stack**

    * **OpenTelemetry**: Distributed tracing across all components
    * **Langfuse**: Agent-specific run tracking and analysis
    * **Grafana**: Real-time dashboards and metrics visualization
    * **PagerDuty**: Automated alerting and incident management

    **Evaluation and Quality**

    * **Real-time evaluations**: Automated quality checks on every trace
    * **Langfuse**: Continuous monitoring and anomaly detection
    * **Promptfoo**: Systematic prompt testing and optimization
    * **Nemo Guardrails**: Runtime safety enforcement

    **Feedback Loops**

    * Trace analysis feeds prompt improvements
    * Automated quality scoring on agent responses
    * A/B testing for prompt variations
    * User feedback integration
  </Accordion>
</AccordionGroup>