> ## 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.

# Overview

> End-to-end lifecycle management for agentic applications

The **Agent Development Lifecycle (ADLC)** provides a structured, end-to-end approach to building, evaluating, deploying, and governing agentic applications on the Backbase Agentic Platform.

## What is ADLC?

ADLC is a comprehensive lifecycle management framework that guides you through four sequential phases, with continuous monitoring and governance applied throughout:

<CardGroup cols={2}>
  <Card title="Prepare" icon="database" href="/agentic-ai/adlc/phases">
    APIs and Data preparation
  </Card>

  <Card title="Build" icon="hammer" href="/agentic-ai/adlc/phases">
    Agent development and implementation
  </Card>

  <Card title="Evaluate" icon="check-double" href="/agentic-ai/adlc/phases">
    Testing and performance assessment
  </Card>

  <Card title="Run" icon="play" href="/agentic-ai/adlc/phases">
    Deployment and operations
  </Card>

  <Card title="Continuous monitoring and governance" icon="shield-halved" href="/agentic-ai/adlc/phases">
    AI guardrails, observability, security scanning, and compliance checks applied throughout all phases
  </Card>
</CardGroup>

## ADLC phases overview

| Phase                                    | Key activities                                                         | Tools and technologies                                             |
| :--------------------------------------- | :--------------------------------------------------------------------- | :----------------------------------------------------------------- |
| **Prepare**                              | Data ingestion, ML feature preparation, API unification                | Data pipelines, MCP servers, API management                        |
| **Build**                                | Framework selection, agent implementation, tool integration, RAG setup | Agno, LangChain, LangGraph, MCP, Vector DBs                        |
| **Evaluate**                             | Unit tests, LLM judges, human annotations, tracing analysis            | Langfuse, Promptfoo, Red teaming                                   |
| **Run**                                  | CI/CD deployment, API exposure, monitoring, scaling                    | Argo CD, APIM, Kubernetes, Observability stack                     |
| **Continuous Monitoring and Governance** | Guardrails, security scans, compliance checks, performance monitoring  | AI Gateway, Nemo Guardrails, Observability tools, Security tooling |

## Benefits

<CardGroup cols={3}>
  <Card title="Structured approach" icon="sitemap">
    Clear phases reduce complexity and ensure nothing is missed.
  </Card>

  <Card title="Quality assurance" icon="shield-check">
    Evaluation, monitoring, and governance at every step.
  </Card>

  <Card title="Production ready" icon="rocket">
    End-to-end tooling ensures agents are ready for production.
  </Card>
</CardGroup>

## Get started

<Steps>
  <Step title="Understand the phases">
    Review the **[ADLC phases](/agentic-ai/adlc/phases)** documentation to understand what happens in each phase.
  </Step>

  <Step title="Start with prepare">
    Begin by preparing your APIs and data. Ensure MCP servers are available and data pipelines are set up.
  </Step>

  <Step title="Use starter kits">
    Use **[starter kits](/agentic-ai/starter-kits/overview)** to jumpstart the Build phase with pre-configured templates.
  </Step>

  <Step title="Follow CI/CD">
    Use the platform's **[CI/CD workflows](/agentic-ai/ci-cd-workflows/overview)** to automate the Run phase.
  </Step>
</Steps>

<Tip>
  **Best Practice**: Start with a simple agent (Level 0-1) to understand the lifecycle, then progress to more complex implementations.
</Tip>