Agentic AI Engineering는 LangChain, LangGraph, RAG, MCP, 로컬 모델 및 배포 가능한 Python 서비스를 갖춘 현대 에이전트 AI 시스템을 구축하기위한 생산 수준의 엔지니어링 리소스입니다.

저장소는 Chapter 5: 독립 MCP 서버와 연결된 멀티 노드 LangGraph 조수, 인트 라우팅, 도구 실행, 응답 요약, 이메일 툴링, 수학 도구, 자동화된 테스트, GitHub Actions CI와 함께 구현된 아키텍처를 향해 이동합니다. Earlier 챕터는 필요한 레이어를 구성합니다. 제공 업체 요약, LCEL 오케스트라션, 벡터 검색, 메모리, ReAct 에이전트, 라우터 그래프, 순차적 워크플로우, 다중 시약 협력 및 인간 인 루프 제어.

이것은 초보자 chatbot walkthrough입니다. 그것은 상태, 도구, 라우팅, retrieval, Observability, modularity 및 model-provider 유연성을 필요로하는 개발자 건물 시스템에 대한 구조 엔지니어링 경로입니다.

당신이 빌드 할 것

• Multi-node LangGraph Assistant 라우터, 실행, 요약, 대화 노드.
• MCP 도구 서버 분리된 서버 경계를 통해 격리된 수학 및 이메일 도구.

Agentic AI Engineering

Agentic AI Engineering is a production-grade engineering resource for building modern agentic AI systems with LangChain, LangGraph, RAG, MCP, local models, and deployable Python services.

The repository leads toward the architecture implemented in Chapter 5: a multi-node LangGraph assistant connected to a standalone MCP server, with intent routing, tool execution, response summarization, email tooling, math tools, automated tests, and GitHub Actions CI. Earlier chapters build the required layers underneath it: provider abstraction, LCEL orchestration, vector retrieval, memory, ReAct agents, router graphs, sequential workflows, multi-agent collaboration, and human-in-the-loop control.

This is not a beginner chatbot walkthrough. It is a structured engineering path for developers building systems that need state, tools, routing, retrieval, observability, modularity, and model-provider flexibility.

What You’ll Build

• Multi-node LangGraph assistant with router, execution, summarization, and conversation nodes.
• MCP tool server exposing isolated math and email tools over a decoupled server boundary.
• Tool-using ReAct workflows that call external capabilities through typed tool contracts.
• RAG pipelines using vector stores, embeddings, retrieval chains, and local document context.
• Provider-flexible LLM interfaces across OpenAI, Gemini, and Ollama.
• Agent routing systems for sequential, router-based, ReAct, and multi-agent workflows.
• Human-in-the-loop execution paths for safer agent behavior in production-style flows.
• Tested agent components with pytest coverage for Chapter 5 node behavior and tool contracts.
• CI-backed agent validation through GitHub Actions for repeatable checks on graph and MCP behavior.

Engineering Roadmap