English | MP4 | AVC 1920×1080 | AAC 44KHz 2ch | 217 Lessons (11h 45m) | 11.57 GB
Complete AI Agent Engineer Training: AI Agent Architecture, n8n, LangChain, RAG, LangGraph, LangSmith, ReAct, ReWOO
The Problem
Agentic AI is the future of AI-powered organizations. It helps businesses innovate faster than ever before. Therefore, it’s not surprise that the demand for AI Agent Engineers has been surging in the job marketplace.
Supply, however, has been minimal, and acquiring the skills necessary to be hired as an AI Agent Engineer can be challenging.
So, how is this achievable?
Universities have been slow to develop specialized programs focused on practical AI agent engineering skills. The few attempts that exist are expensive and time-consuming. At the same time, most online courses offer high-level walkthroughs of individual techniques for building agentic systems, yet integrating these skills remains challenging.
The Solution
AI agent engineering is a multidisciplinary field covering:
- AI agent foundations
- AI agent design and architecture
- Python programming
- Working with low-code automation platforms like n8n
- AI agent optimization for speed and cost
- Connecting agents to tools, memory, and APIs with LangChain
- Model AI agent workflows with LangGraph
- AI agent evaluation with LangSmith
- Applying agents to real-world problems
- Launching and optimizing agents in production
Each topic builds on the previous one, and skipping steps can lead to confusion. For instance, optimizing agent performance without a fundamental understanding of agent architecture is rarely achievable.
So, we created the AI Agent Engineer Bootcamp 2026 to provide the most effective, time-efficient, and structured AI agent training available online.
This pioneering training program overcomes the most significant barrier to entering the AI agent field by consolidating all essential resources in one place.
Our course is designed to teach interconnected topics seamlessly—providing all you need to become an AI agent engineer at a significantly lower cost and time investment than traditional programs.
The Skills
1. Intro to AI Agents
Decision-making logic, actuators, updated environment, single agents, multi-agents, guardarails—there are familiar AI agent buzzwords; what exactly do they mean?
Why study AI agent basics?
Build a solid foundation that will support your learning journey. Understand the big picture and how different building blocks fit together.
2. AI Agent Architecture
We build AI agents to solve problems. Each problem requires the right architecture and an understanding of the trade-offs involved.
Why study AI agent architecture?
The system design choices you will make will determine how effective and efficient your AI agents are. By mastering classic AI agent architecture you will be able to make confident choices at the system design stage—before problems become costly to fix.
3. Building AI Applications with LangChain
LangChain is a framework that allows for seamless development of AI-driven applications by chaining interoperable components.
Why study LangChain?
Learn how to create agents that can reason. LangChain facilitates the creation of systems where individual pieces—such as language models, databases, and reasoning algorithms—can be interconnected to enhance overall agent functionality.
4. LangGraph
LangGraph sets the foundation of how we can build and scale AI workloads. Use this tool to design agents that reliably handle complex tasks.
Why study LangGraph?
With LangGraph you will be introduced to multi-step agent orchestration. This is where you learn how to add conversational memory to your agent, so it learns to remember, adapt, and grow smarter with every interaction.
5. AI Agents in Practice
Step into the world of AI agents with this practical module on agentic systems. You will gain real-world experience. From prompt design and multi-step reasoning to safety techniques and LangSmith monitoring.
Why study AI Agents in Practice?
Gain the practical skills to build production-ready AI workflows. Take the next step in your AI journey with hands-on projects.
What You Get
- $1,250 AI agent engineering training program
- Active Q&A support
- Essential skills for AI engineering employment
- AI learner community access
- Completion certificate
- Real-world business case solutions for job readiness
We’re excited to help you become an AI Agent Engineer from scratch—offering an unconditional 30-day full money-back guarantee.
With excellent course content and no risk involved, we’re confident you’ll love it.
Why delay? Each day is a lost opportunity. Click the ‘Buy Now’ button and join our AI Agent Engineer program today.
What you’ll learn
- The course provides the entire toolbox you need to become an AI Agent Engineer
- Understand key AI agent concepts and build a solid foundation
- Impress interviewers by showing an understanding of AI agents
- Apply your skills to real-life business cases
- Harness the power of AI agents
- Leverage LangChain for seamless development of AI-driven applications by chaining interoperable components
- Model AI agent workflows with LangGraph
- Evaluate AI agents with LangSmith
- Build single and multi-agent systems
Who this course is for:
- You should take this course if you want to become an AI Agent Engineer or if you want to learn about the field
- This course is for you if you want a great career
- The course is also ideal for beginners, as it starts from the fundamentals and gradually builds up your skills
Table of Contents
Intro to AI Agents Understanding AI agents
1 What Does the Course Cover
2 What Is an AI agent
3 Why AI Agents Are Believed to Be the Next Big Thing
Intro to AI Agents Essential ingredients for building AI agents
4 Intro
5 Environment – The External World That the Agent Perceives and Interacts With
6 Sensors – How the Agent Collects Data About its Surroundings
7 Model – the Agent’s Way of Making Sense of Information
8 Decision making Logic – Rules and Objectives that Guide the Agent’s Actions
9 Actions – How the Agent Shapes the Environment
10 The Updated Environment
Intro to AI Agents Types of AI agents from simple to complex structures
11 Intro
12 Key Characteristics of AI Agents
13 Simple Reflex Agent
14 Model based Reflex Agent
15 Goal based Agent
16 Utility based Agent
17 Learning Agent
Intro to AI Agents Guiding and teaching AI agents
18 Intro
19 Learning from Humans
20 Learning from External Systems
Intro to AI Agents AI agent architecture patterns
21 Intro
22 Distinguishing LLMs vs AI Workflows vs Agents (Agentic vs Non agentic AI)
23 How AI Agents Reason and Act (ReAct)
24 How AI Agents Reason without Observation (ReWoo)
25 Single Agents
26 Multi agents
Intro to AI Agents Implementing AI agents in practice
27 Intro
28 How to Implement AI Agents in Your Business
29 Select a Model
30 External Tools the Agent Can Use
31 Configuring Instructions and Prompt Engineering Best Practices
32 Few shot Prompting
33 Chain of Thought Reasoning
34 Guardrails
35 The Importance of Human Intervention
36 How to Evaluate AI Agents
Practical example n8n Build an agentic automation with n8n
37 Introduction to n8n
38 Node Types in n8n
39 The Project We Will Build
40 Defining Your Agent’s Personality The System Prompt
41 Adding the Brain Making Your Workflow Think
42 Implementing Memory in n8n Building Memory for Your Agent
43 Integrating Tools Google Sheets and Gmail
44 Producing the Final Output
Intro to AI Agents AI agent infrastructure
45 Intro
46 APIs
47 Cloud Services
48 Data and Knowledge Integration
49 Development Frameworks
50 Deployment
Intro to AI Agents AI agents in business
51 The Key Value Proposition of AI Agents
52 AI Agents as Teammates
AI Agents Architecture Module Intro
53 Intro
AI Agents Architecture Module Foundations of Agentic AI
54 Agentic Workflows vs AI Agents
55 Core Building Blocks of an AI agent
56 When (and when not) to Use AI Agents
57 Why Architecture Matters Scaling Reliability & Control
AI Agents Architecture Module Prompting for Agentic Systems
58 Section Introduction
59 General Principles of Prompt Structuring
60 Prompting Frameworks
61 Positive and Negative Prompting
62 Chain of Thought (CoT)
AI Agents Architecture Module Agentic Workflows
63 Section Introduction
64 The Augmented LLM
65 Prompt Chaining
66 Routing
67 Parallelization
68 Orchestrator worker
69 Evaluator optimizer
AI Agents Architecture Module Single Agent Architecture Patterns
70 Section Introduction
71 When to Use a Single Agent Architecture
72 Reflection
73 ReAct (Think Do)
74 Reflexion
AI Agents Architecture Module Planning and Decomposition
75 Section Introduction
76 Task Decomposition
77 The Importance of Planning
78 Plan and Solve
79 ReWOO
80 Tree of Thought
AI Agents Architecture Module Multi Agent Architectures
81 Section Introduction
82 When to Use Single vs Multi agent Systems
83 Vertical vs Horizontal Architectures
84 Challenges with Group Conversations
85 Supervisor
86 Hierarchical Teams
87 Dynamic Teams
AI Agents Architecture Module Execution Performance and Reliability
88 Section Introduction
89 Agents and Asyncronous Task Execution
90 Performance Metrics Latency and Cost
91 Error Handling and Recovery
AI Agents Architecture Module Memory Systems
92 Section Introduction
93 Short term Context Buffer
94 Vector store RAG
95 Entity level Memory
AI Agents Architecture Module Oversight and Control
96 Section Introduction
97 Self reflection
98 Human in the loop
AI Agents Architecture Module Governance and Safety
99 Governance Patterns
100 Guardrails and Policy Enforcement
101 Cost limiter
102 A B Shadow Testing
103 Bias and Fairness Systems
AI Agents Architecture Module Evaluation and Benchmarking
104 Section Introduction
105 How to Measure Agent Performance
106 Offline Benchmarks
107 Online Metrics
LangChain Module Introduction to LangChain
108 Introduction
109 Business Applications of LangChain
110 What Makes LangChain Powerful
111 What Does the Course Cover
LangChain Module Tokens Models and Prices
112 Tokens
113 Models and Prices
LangChain Module Setting Up the Environment
114 Setting Up a Custom Anaconda Environment for Jupyter Integration
115 Obtaining an OpenAI API Key
116 Setting the API Key as an Environment Variable
LangChain Module The OpenAI API
117 First Steps
118 System User and Assistant Roles
119 Creating a Sarcastic Chatbot
120 Temperature Max Tokens and Streaming
LangChain Module Model Inputs
121 The LangChain Framework
122 ChatOpenAI
123 System and Human Messages
124 AI Messages
125 Prompt Templates and Prompt Values
126 Chat Prompt Templates and Chat Prompt Values
127 Few Shot Chat Message Prompt Templates
LangChain Module Output Parsers
128 String Output Parser
129 Comma Separated List Output Parser
130 Datetime Output Parser
LangChain Module LangChain Expression Language (LCEL)
131 Piping a Prompt Model and an Output Parser
132 Batching
133 Streaming
134 The Runnable and RunnableSequence Classes
135 Piping Chains and the RunnablePassthrough Class
136 Graphing Runnables
137 RunnableParallel
138 Piping a RunnableParallel with Other Runnables
139 RunnableLambda
140 The @chain Decorator
LangChain Module Retrieval Augmented Generation (RAG)
141 How to Integrate Custom Data into an LLM
142 Introduction to RAG
143 Introduction to Document Loading and Splitting
144 Introduction to Document Embedding
145 Introduction to Document Storing Retrieval and Generation
146 Indexing Document Loading with PyPDFLoader
147 Indexing Document Loading with Docx2txtLoader
148 Indexing Document Splitting with Character Text Splitter (Theory)
149 Indexing Document Splitting with Character Text Splitter (Code Along)
150 Indexing Document Splitting with Markdown Header Text Splitter
151 Indexing Text Embedding with OpenAI
152 Indexing Creating a Chroma Vector Store
153 Indexing Inspecting and Managing Documents in a Vector Store
154 Retrieval Similarity Search
155 Retrieval Maximal Marginal Relevance Search
156 Retrieval Vector Store Backed Retriever
157 Generation Stuffing Documents
158 Generation Generating a Response
LangGraph Module Introduction
159 Welcome to the LangGraph Module
160 What You Will See Next
161 Model Prerequisites
LangGraph Module Setting Up the Environment
162 Setting Up the Environment
LangGraph Module Graph Components and Implementation
163 States Nodes and Edges
164 First Graph Importing Relevant Classes
165 First Graph Defining a State and a Node
166 First Graph Building the Graph
167 Conditional Edges Defining Nodes and a Routing Function
168 Conditional Edges Building the Graph
LangGraph Module Message Management
169 The Annotated Construct and Reducer Functions
170 Reducer Functions in Action
171 The MessagesState Class
172 The RemoveMessages Class
173 Trimming Messages
174 Summarizing Messages
LangGraph Module Thread Level Persistence
175 Checkpointers and Threads
176 Short Term Memory with the InMemorySaver Class
177 The StateSnapshot Class
178 Long Term Memory with SQLite
LangGraph Module Conclusion
179 Conclusion
Agents in Practice Module Introduction to the Course
180 What does the course cover
Agents in Practice Module Agentic Systems in Practice
181 Agent Development Tools
182 Why LangGraph
183 Anatomy of a LangGraph Project
184 Prompt Techniques Part 1
185 Prompt Techniques Part 2
186 Prompting Tips and Tricks
187 System Input vs User Input
188 Behind Scenes Project Helper Chatbot
Agents in Practice Module Project 1 Job Helper agent (ReAct)
189 Project Job Helper agent (ReAct)
190 ReAct Аrchitecture Recap
191 Adding Funds to Your OpenAI API Account
192 Setting Your OpenAI API Key
193 Setup & Installation
194 Building the Tools File Reader
195 Building the Tools Web Search API
196 Integrating Tools into the Agent
197 Building the Assistant Node
198 Building the Graph
199 Running the Graph
200 Adding Memory
201 Conncecting to LangSmith
Agents in Practice Module Project 2 ReWOO Job Helper agent
202 ReWOO Architecture Overview
203 Defining a ReWOO State and Planner
204 Building the Planner Node
205 Implementing the Executor
206 Implementing the Solver
207 Wiring Up the ReWOO Graph
208 ReAct vs ReWOO
Agents in Practice Module Project 3 Business Idea Evaluator
209 Project Overview
210 Human in the Loop (HITL)
211 Parallelization
212 Initializing the State
213 Building the Human in the loop
214 Creating Pre Made “Advisor” Nodes
215 Collection Node and Building the Graph
216 Finalizing the project
217 Bonus lecture
Resolve the captcha to access the links!
