طراحی ایجنت‌ها و سیستم‌های خودکار با LangChain و LangGraph

عنوان دوره : Udemy – LangChain & LangGraph AI Engineer: Agents, Agentic RAG & MCP

سطح : مبتدی

زمان کل دوره : 20 ساعت و 21 دقیقه

تعداد فايل ها : 202 (1080p:152, 720p:43)

سال آموزش : 2026

فایل تمرینی : HTML:139, PDF:4

مربی دوره : Eden Marco

نرم افزار : –

زیرنویس انگلیسی و فارسی : دارد

Udemy – LangChain & LangGraph AI Engineer: Agents, Agentic RAG & MCP

This course contains the use of artificial intelligence :)

2026- COURSE WAS RE-RECORDED and supports- LangChain Version 1.2+ Jev

**Ideal students are software developers / data scientists / AI/ML Engineers**

Welcome to the AI Engineering with LangChain and LangGraph course.

In this course you will learn how to design and build AI agents and agentic AI systems using LangChain and LangGraph, the most powerful frameworks for developing modern LLM applications.

Agentic AI Engineering focuses on building AI systems that can reason, plan, use tools, and autonomously complete tasks. With LangChain and LangGraph, you will build AI agents, RAG systems, and advanced LLM applications and understand the challenges of deploying such to production.

What is LangChain?LangChain is an open-source development framework designed to simplify creating applications powered by large language models (LLMs).

Using LangChain, LangGraph, MCP, and modern LLM frameworks, you will build production-ready AI agents, multi-agent systems, and advanced RAG applications.

Please note that this is not a course for beginners. This course assumes that you have a background in software engineering and are proficient in Python. I will be using Pycharm IDE but you can use any editor you’d like since we only use basic feature of the IDE like debugging and running scripts .You will build real-world Agentic AI systems using LangChain and LangGraph:

Search Agent

Documentation Helper – A chatbot over Python package docs (and any data you choose), using advanced retrieval and RAG.

Prompt Engineering Theory

Context Engineering Theory

Introduction to LangGraph

Model Context Protocol (MCP)

Deep Agents

Agentic AI Engineering Topics Covered:

Agentic AI Fundamentals

AI Agents

Agentic AI architectures

Multi-agent systems

AI engineering principles

LLM and Prompt Engineering

Prompt Engineering

Few-Shot Prompting

Chain of Thought

ReAct prompting

Context Engineering

Agent Frameworks

LangChain

LangGraph

Skills

Tool Calling

AI Agent Infrastructure

Vector databases (Pinecone, FAISS, Chroma)

Retrieval Augmented Generation (RAG)

Memory systems

LangSmith tracing

System One Decision Models (Jev by TypeSafe AI)

What is Jev?

Noul, Score, Choice

Running Locally Decision Models

Throughout the course, you will work on hands-on exercises and real-world projects to reinforce your understanding of the concepts and techniques covered. By the end of the course, you will be proficient in using LangChain to create powerful, efficient, and versatile LLM applications for a wide array of usages.Why This Course?

Up-to-date: Covers LangChain V.1+ and the latest LangGraph ecosystem.

Practical: Real projects, real APIs, real-world skills.

Career-boosting: Stay ahead in the LLM and GenAI job market.

Step-by-step guidance: Clear, concise, no wasted time.

Flexible: Use any Python IDE (Pycharm shown, but not required).

Targeting a Forward Deployed Engineer (FDE) role? This course covers the technical FDE toolkit that AI labs and enterprise AI teams hire for:

RAG and Agentic RAG over customer data → RAG Foundations, Documentation Assistant, Agentic RAG

Tool calling, structured outputs and agent workflows → Search Agent, ReAct from scratch, LangGraph

Integrating agents with customer systems → MCP servers & clients

Production, observability and security → AI Applications in Production, LangSmith tracing, Agent Security

Agent harness engineering → Deep Agents, Skills, Middleware & Harness Engineering

This course is ideal for developers who want to learn Agentic AI Engineering, AI agents with Python, and LLM application development.

You will learn how to design agent architectures, implement tool-using agents, and build scalable agentic AI systems using LangChain and LangGraph.

DISCLAIMERS

Please note that this is not a course for beginners. This course assumes that you have a background in software engineering and are proficient in Python. I will be using Pycharm IDE but you can use any editor you’d like since we only use basic feature of the IDE like debugging and running scripts.

What you’ll learn:
– Build AI agents with the latest LangChain and LangGraph, from your first tool-calling agent to multi-step agentic systems
– Build an agent loop from scratch to understand exactly how AI agents work under the hood
– Build RAG and Agentic RAG systems with embeddings and vector databases (Pinecone, FAISS, Chroma)
– Design Reflection, Reflexion and multi-step agents as LangGraph graphs with nodes, edges and state
– Create your own MCP server and client with LangChain and connect them to Cursor and Claude
– Build a Deep Agent that plans and uses Skills and middleware to handle complex tasks
– Explain the AI engineering fundamentals behind agents: tokens, context windows, embeddings and function calling
– Debug agents by tracing every LLM and tool call in LangSmith
– Apply the technical forward deployed engineer (FDE) toolkit to ship agents into real customer environments

Requirements:
– This is not a beginner course. Basic software engineering concepts are needed
– I assume students will be familiar software engineering subjects such as: git, python, uv, environment variables, classes, testing and debugging
– No Machine Learning experience is needed.

Who this course is for:
– Software engineers who want to transition and break into AI engineering by building real AI agents with LangChain and LangGraph
– Backend and full-stack developers moving into AI engineering who want to add agentic AI, RAG and MCP to their products
– Data scientists and ML engineers expanding into AI engineering and shipping LLM-powered applications
– Not for programming beginners: you should be comfortable with Python, git and debugging before starting your AI engineering journey
– Engineers preparing for Forward Deployed Engineer (FDE), AI solutions engineer and applied AI roles