Contact Us

Intermediate course

Production AI Agents with LangChain + LangGraph [2026]

Master RAG, Multi-Agent Systems, LangGraph and FastAPI -- Build and Deploy Real-World AI Agent Projects in Python

Rating: 4.7178 ratings2,623 students17 total hours155 lectures
Open course in DoJo Back to courses
Production AI Agents with LangChain + LangGraph [2026] Intermediate

Course facts

  • Last updated 05/2026
  • English English [Auto], French [Auto] , 1 more
  • Instructor: Paulo Dichone | Software Engineer, AWS Cloud Practitioner & Instructor
  • AI agents, automation and connected workflows

What you'll learn

Practical outcomes

  • Build composable LLM chains using LangChain v.1's LCEL with structured output, streaming, batch processing, and multi-provider switching
  • Implement production RAG pipelines with intelligent chunking, vector stores, and 4 advanced retrieval patterns: Multi-Query, Contextual Compression, Hybrid Sear
  • Design stateful AI agents with LangGraph state machines, conditional routing, self-correcting loops, and human-in-the-loop approval workflows
  • Orchestrate multi-agent systems using supervisor patterns, agent handoffs, parallel execution, and hierarchical team structures
  • Secure LLM applications against prompt injection, PII leakage, and output manipulation with production-grade defense layers
  • Test and evaluate LLM systems using unit tests, integration tests, and semantic evaluation across correctness, relevance, and coherence
  • Deploy production APIs with FastAPI, rate limiting, response caching, structured logging, metrics, LangSmith tracing, and Docker
  • Build 3 real-world applications: Customer Support Agent, Multi-Agent Research System, and Code Review Agent, each with measurable business ROI

Curriculum

11 sections • 155 lectures • 17h 6m total length

Introduction3 lectures • 7min
  1. Introduction, Prerequisites and What You'll Build02:03
  2. Why LangChain and LangGraph - Rapid Growth01:55
  3. Course Structure02:40
Download Course Source Code1 lecture • 1min
  1. Download Source Code00:06
LangChain Foundations - A Deep Dive27 lectures • 2hr 18min
  1. The LangChain Ecosystem - Overview07:53
  2. Setup Development Environment01:31
  3. API Setup and Verification (OpenAI and Anthropic)07:03
  4. The V 1.0 Architecture (LangChain)02:15
  5. LangChain Core Concepts - LCEL and Runnable Chains - Hands-on06:23
  6. LCEL - Batch Execution Demo03:36
  7. Demo Stream Realtime Output with LCEL02:34
  8. Demo Schema Inspection03:29
  9. Your Turn - Build Your First Chain with LangChain01:15
  10. Solution - Your First Chain01:56
  11. Quick Check in00:55
  12. LCEL - The Pipe Operator Overview00:55
  13. New Model Initiation and Available Models in 202604:33
  14. Why Output Parsers in LangChain00:50
  15. Model Configuration and Cost Optimization Strategies06:30
  16. Working with LLMs in LangChain - Multi Providers Configuration12:53
  17. Your Turn - Exercise - Create a Multi-model Setup01:07
  18. Solution02:01
  19. Prompt Templates and Messages - Deep Dive07:19
  20. Hands-on: Prompt Messages10:41
  21. Hands-on: Prompt Templates Code Run Through and Testing06:15
  22. Hands-on: Why Output Parsers and Structured Outputs06:55
  23. Hands-on: Output Parsers and Structured Outputs09:15
  24. Running the Final Output Parser and Structured Output Script - Demo04:23
  25. Smart Q&A Bot Architecture - Overview01:12
  26. Project 1 - Smart Q&A Bot - Overview01:13
  27. Project 1 - Final Touches23:10
  28. LangChain Foundations - Section 2 Knowledge Check 4 questions
Chain Patterns5 lectures • 34min
  1. Chains, RAG and Memory & Chain Patterns - Overview06:48
  2. Hands-on: Basic and Parallel Chains07:57
  3. Hands-on: Demo Passthrough Runnable07:27
  4. Hands-on: Chain Branching04:57
  5. Hands-on: Debugging06:45
Document Loading, Chunking & Embeddings - Loaders, Splitters, Vector Stores27 lectures • 2hr 4min
  1. LangChain Document Loaders - Overview06:14
  2. Hands-on: TextLoaders03:43
  3. Hands-on: WebLoader02:52
  4. Hands-on: Lazy Loader02:15
  5. Hands-on: Document Structure03:34
  6. Hands-on: Loading PDF Files02:54
  7. Why Chunking Matters and Text Splitting Deep Dive08:19
  8. Hands-on: Text Splitter - RecursiveCharacterTextSplitter05:21
  9. Hands-on: Chunk Comparison03:24
  10. Hands-on: Overlap Importance In Code05:22
  11. Hands-on: Markdown Header Splitter02:57
  12. Hands-on: Code Splitter03:32
  13. PDF Document Splitting03:41
  14. RAG Overview10:12
  15. Vector and Embeddings Full Overview06:29
  16. Hands-on: OpenAI Embedding04:41
  17. Free Embedding Models02:17
  18. Hands-on: Embeddings Deep Dive - Basics - Similarity Search06:37
  19. Hands-on: Embedding Caching04:06
  20. Vector Stores: Architecture and Production Options - Overview05:45
  21. Hands-on: Setting Up Chroma and Running Chroma Basics06:17
  22. Important: Python Version for ChromaDB (Use 3.11 or 3.12)00:56
  23. Hands-on: Similarity Search with Scores03:39
  24. Hands-on: Metadata Filtering02:58
  25. Hands-on: Chroma DB Persistence06:13
  26. Hands-on: Vector Store as a Retriever for Chains06:31
  27. Exercise and Solution: Vector Stores03:38
RAG and Memory - A Comprehensive Dive25 lectures • 2hr 43min
  1. RAG Architecture and Best Practices - Overview06:37
  2. Hands-on: Basic RAG Pipeline08:39
  3. Hands-on: RAG with Resources03:12
  4. Hands-on: RAG with Fallback02:11
  5. Hands-on: RAG with Structured Outputs05:51
  6. Hands-on: RAG Pipeline Exercise03:31
  7. From Basic RAG to Advanced RAG - Overview09:23
  8. Hands-on: Advanced RAG - Multi-Query Retriever06:02
  9. Hands-on: Advanced RAG - Contextual Compression08:13
  10. Hands-on: Advanced RAG - Hybrid Search07:13
  11. Hands-on: Advanced RAG - Parent Document Retriever04:28
  12. Hands-on: Advanced RAG - Combining Multi-Query and Compression Strategies05:07
  13. Memory in LangChain - Full Overview07:25
  14. Hands-on: Conversation Memory - Basics05:45
  15. Hands-on: Multiple Sessions Memory03:30
  16. Hands-on: Message Trimming04:28
  17. Hands-on: Windowed Memory07:38
  18. Hands-on: Summary Memory10:40
  19. Exercise and Solution: Persistent Memory08:57
  20. Project: AI Research Assistant - Overview03:27
  21. Project: AI Research Assistant - Indexing Documents (Part 1)07:56
  22. Project: AI Research Assistant - LLM Prompt and Output Parser (Part 2)09:22
  23. Project: AI Research Assistant - Adding Memory (Part 3)08:42
  24. Project: AI Research Assistant - Multi-Query Implementation (Part 4)07:38
  25. Project: AI Research Assistant - Structured Output - Final Part06:43
  26. Chains, RAG and Memory - Section 3 Knowledge Check 4 questions
LangGraph - A Full Deep Dive19 lectures • 2hr 31min
  1. LangGraph and Its Pillars - Overview10:43
  2. Hands-on: Create Your First Simple Graph08:50
  3. Hands-on: Understanding Reducers and Accumulating State08:39
  4. Hands-on: Message State - The Chat Pattern05:13
  5. Hands-on: Multi-Node Pipelines - Chaining LLM Calls15:17
  6. Exercise: Build Your First Node04:17
  7. Hands-on: Full LangGraph Step-by-Step Workflow05:43
  8. Edges and Conditional Edges Deep Dive04:24
  9. Hands-on: Basic Routing with Literal Routing Types07:33
  10. Hands-on: Conditional Looping04:20
  11. Hands-on: Multipath Routing05:36
  12. Hands-on: Cycles and Loops - Self-Correcting Code Writer08:54
  13. Hands-on: Iterative Research Agent with Loops and Cycles06:23
  14. Human in the Loop - Overview05:39
  15. Hands-on: Human Input - Interrupt for Approval12:09
  16. Full Human in the Loop Workflow10:44
  17. Hands-on: Checkpointing Deep Dive16:05
  18. Checkpoint Internals Deep Dive07:08
  19. LangGraph Summary and Key Takeaways03:32
  20. LangGraph - Section 4 Knowledge Check 5 questions
Multi-Agent Systems with LangGraph and LangChain17 lectures • 2hr 37min
  1. Introduction to Multi-Agents and the ReAct Pattern07:02
  2. Hands-on: Tool Calling Agent12:51
  3. Custom Tool with Error Handling06:15
  4. Hands-on: The Supervisor Agent16:48
  5. Hands-on: Agent Handoffs in LangGraph15:17
  6. Hands-on: Map-Reduce Strategy10:57
  7. How Agents Communicate: Reducers Deep Dive11:55
  8. Hands-on: Message Passing Pattern04:38
  9. Hands-on: Shared Field State05:36
  10. Hands-on: The Blackboard Iterative Refinement10:31
  11. Hierarchical Architecture Deep Dive04:15
  12. Hands-on: Single Department in Isolation04:21
  13. Hands-on: Hierarchical Routing and Full Tracing12:58
  14. Section Project: Multi-Agent Research System Overview05:44
  15. Hands-on: State Schema and Send API Overview12:08
  16. Final Project: Research System from the Ground Up14:06
  17. Multi-Agent Systems: Section Summary01:09
  18. Multi-Agent Systems - Section 5 Knowledge Check 5 questions
Production Deployment - Deploying AI Agents29 lectures • 4hr 9min
  1. Introduction to Observability and Benefits Deep Dive08:48
  2. Setting Up LangSmith and Testing Observability Traces07:56
  3. Production Test Commands File - Get This First00:05
  4. PII, Security Categories, and Prompt Injection Attacks05:20
  5. Hands-on: Defense in Depth - Input Sanitization and PII Detection09:19
  6. Hands-on: The LLM Guard - The Smart Bouncer06:03
  7. Hands-on: Output Validator and Summary10:16
  8. Production Considerations00:43
  9. LLM Testing and Unit Tests08:23
  10. Hands-on: Integration Testing04:00
  11. Hands-on: LLM-as-Judge Evaluation04:12
  12. Hands-on: Regression Testing04:26
  13. Hands-on: LangSmith Datasets - Production Approach09:44
  14. Hands-on: LLM Testing Pyramid01:47
  15. Understanding Error Handling and the Retry Decorator07:46
  16. Hands-on: Circuit Breaker06:48
  17. Hands-on: Fallback Chain04:51
  18. Hands-on: Graph-Based Retry06:28
  19. Hands-on: Cost Reduction - Model Router07:58
  20. Hands-on: Semantic Caching05:30
  21. Hands-on: Token Budgeting07:16
  22. Pillars of Production Visibility - Observability and Monitoring11:34
  23. Project: Production-Ready API - Project Scaffold and the Big Picture18:13
  24. Project: Security Layer - First Line of Defense12:06
  25. Project: Production Cache and Monitoring - Save Money, See Everything08:36
  26. Project: The LangGraph Agent - Brain with Safety Net09:41
  27. Project: FastAPI - Wiring Everything Together22:46
  28. Project: Production LangGraph API - Final Build and Dockerization15:37
  29. Deployment to Render - Your API Goes Live22:46
  30. Production Deployment - Section 6 Knowledge Check 5 questions
Wrap up1 lecture • 4min
  1. Wrap up and Next Steps04:17
Bonus1 lecture • 1min
  1. Bonus00:08

Who it is for

  • Python developers who want to add AI agent skills to their toolkit and build real applications, not just follow along with tutorials
  • Backend or full-stack developers who want to integrate AI agents into existing products and APIs
  • Engineers stuck after basics — you've done LangChain tutorials and can call an LLM, but don't know how to build a system that handles errors, scales, and doesn't break in production
  • Career switchers targeting the AI engineer role — companies are paying 25% premiums for these skills in 2026

Course description

Overview

Stop building AI demos. Start shipping AI agents that handle real workloads in production. Most LangChain and LangGraph tutorials teach you how to call an LLM and leave you on your own when it is time to build something real. This course picks up where they stop. From Lecture 1, you will build production-ready AI agent systems using the same patterns companies are paying $150K salaries for in 2026. This is a project-first, production-first course covering LangChain v0.3, LangGraph 1.0, RAG pipelines, multi-agent orchestration, security, testing, LangSmith observability, FastAPI deployment, and Docker. All code uses the latest stable APIs as of January 2026.

What you will build: Customer Support Agent: RAG-powered knowledge base with Chroma, structured issue classification, automatic ticket escalation. Target: reduce Tier-1 support tickets by 40 percent. Multi-Agent Research System: Specialist agents running in parallel with state management, convergence patterns, and quality loops. Target: cut research time from 4 hours to 20 minutes. Production FastAPI + LangGraph API: Full request pipeline with security middleware, response caching, rate limiting, structured logging, metrics, LangSmith tracing, and Docker deployment to Render What you will learn: LangChain v0.3 Mastery: LCEL chain composition, structured output with Pydantic, multi-provider LLM switching (OpenAI, Anthropic, HuggingFace), streaming, and batch processing Complete RAG Pipelines: Document loading, intelligent text splitting, embeddings, vector stores with Chroma, and 4 advanced retrieval patterns: Multi-Query, Contextual Compression, Hybrid Search, and Parent Document Retriever LangGraph Deep Dive (4 hours): State machines with TypedDict, conditional routing, self-correcting loops, human-in-the-loop workflows with interrupt patterns, and checkpoint persistence Multi-Agent Orchestration: Supervisor pattern, agent handoffs, parallel execution with fan-out and fan-in, inter-agent communication, and hierarchical team structures Production Security: Prompt injection defense with regex patterns, PII detection and masking for emails, SSNs and credit cards, LLM-as-Guard pattern, and output validation LLM Testing and Evaluation: Unit tests with mocks, integration tests, regression tests, AB prompt testing, and semantic scoring across correctness, relevance, coherence, and helpfulness Production Deployment: FastAPI integration, rate limiting, response caching with SHA-256 hashing and TTL, structured JSON logging, metrics collection, LangSmith tracing, Docker, and cloud deployment to Render How this course is different: Most AI courses stop at hello world demos. This course is production-first from day one. Every concept is taught through working, deployable code. Security and testing are dedicated modules, not afterthoughts. You will implement error handling, fallbacks, cost optimization, and monitoring throughout. The final API project wires everything together into a system you can actually ship. This course is for you if: You are a Python developer who wants to add AI agent engineering skills to your toolkit You have done LangChain tutorials and can call an LLM, but do not know how to build something that handles errors, scales, and stays stable in production You are a backend or full-stack developer who wants to integrate AI agents into existing products and APIs You are targeting the AI engineer role and need a portfolio of deployed, real-world projects to show employers Requirements: Python at an intermediate level (functions, classes, decorators, type hints) Basic command line familiarity An OpenAI API key (costs roughly $2 to $5 for the entire course) No prior LangChain or LangGraph experience required About the instructor: Paulo Dichone is an AI engineer and educator with over 340,000 students across 71 courses. Every pattern in this course comes from real production systems. You will get the same battle-tested approaches, shortcuts, and lessons learned from building AI applications that run in the real world.

Instructor

Paulo Dichone | Software Engineer, AWS Cloud Practitioner & Instructor

Paulo Dichone | Software Engineer, AWS Cloud Practitioner & Instructor Android, Flutter, AWS, Best Selling Instructor Hi, I’m Paulo – Your Guide to Mastering Development, Cloud, and AI Engineering With a passion for empowering learners, I’ve had the privilege of teaching over 350,000 students across 175 countries. Whether you’re diving into Android, Java, Flutter, AWS Cloud, or venturing into the world of AI engineering, I’m here to help you unlock your full potential. My Expertise I bring extensive hands-on experience in: AI Engineering Mobile App Development (Android & iOS) Cross-Platform Development (Flutter, Dart, and JavaFX) AWS Cloud Solutions And now, I’m also focused on the AI engineering landscape, helping developers leverage the power of machine learning and automation in their projects. My Mission No matter where you are in your journey—whether you're just starting or looking to sharpen advanced skills—my courses are designed to make you an exceptional developer and AWS Cloud Practitioner, equipped to tackle real-world challenges. Beyond coding, I enjoy spending time with my growing family, playing the guitar and mandolin, and traveling whenever I get the chance. Ready to Get Started? Android Development: The Comprehensive Android Development Masterclass Learn Android from scratch. This beginner-friendly course covers everything you need to build Android apps confidently, no prior experience required. The Complete Intermediate Android Masterclass Master essential Android topics like WorkManager API, ROOM Database, and background operations to level up your mobile development skills. Cross-Platform & Web Development: Flutter & Dart - The Complete App Development Course Develop beautiful iOS and Android apps with a single codebase using Dart and Flutter. AngularDart - Build Dynamic Web Apps with Angular & Dart Learn one of the most powerful web frameworks, Angular, combined with Dart to create interactive web applications. TornadoFX - Build JavaFX Applications with Kotlin Craft amazing desktop apps using Kotlin and JavaFX, taking advantage of Kotlin’s simplicity and expressiveness. AWS Cloud Mastery: Amazon EC2 Master Class (Includes Auto Scaling & Load Balancer) Amazon ECS & Fargate Masterclass Amazon EKS with Kubernetes AWS AppSync & Amplify AWS Lambda and Serverless Framework These courses are designed to make you proficient with cloud technologies, covering key AWS services to help you build scalable and efficient cloud solutions. Master Java: Java Masterclass - Beginner to Expert Guide Learn Java from the ground up and gain the skills to build powerful applications. Java Design Patterns - The Complete Masterclass Develop reliable, maintainable software using proven design patterns that are fundamental to professional Java programming. The Future of Development: AI Engineering I'm passionate about helping students explore the intersection of AI and software development. In my upcoming AI courses, I’ll show you how to integrate AI solutions into mobile apps and cloud systems, empowering you to become a cutting-edge developer with AI capabilities. I look forward to welcoming you to my courses and being part of your journey to becoming the best developer, cloud practitioner, and AI engineer you can be. See you inside?