LangChain & LangGraph

Duration: 3 Days

Description

Wiring an LLM app together from scratch means rebuilding the same plumbing every project needs — prompt management, memory, retrieval, orchestration — and LangChain and LangGraph exist to stop that. This course teaches both frameworks as a pair: LangChain for composing chains and managing the prompt, memory, and retrieval layers, and LangGraph for the stateful, multi-step agent workflows that a simple chain can’t express. Rather than a feature tour, the course builds progressively more capable applications so participants understand which abstraction fits which problem — and just as important, when reaching for the framework adds more complexity than it removes.
Class time is divided between instructor-led explanation (35 percent) and hands-on development (65 percent).

Audience

This course is for developers already building LLM applications or agents who want real command of these two specific frameworks, not a first introduction to AI development. Prior AI development experience — comfort with prompts, API calls, and basic LLM concepts — is assumed.

Objectives

• Explain the core abstractions of LangChain and LangGraph
• Compose chains and manage prompts, memory, and output
• Build retrieval pipelines with the framework’s components
• Orchestrate stateful, multi-step workflows with LangGraph
• Build and debug agents using the frameworks
• Evaluate when a framework helps and when it adds overhead

Prerequisites

Participants should have prior AI development experience. The following will help:

• Working knowledge of Python (see Python Foundations)
• Experience building LLM applications (see Building LLM Applications)
• Familiarity with agent concepts (see Introduction to AI Agents)

Related AI Courses

See the full AI training roadmap and course directory for how this fits into a broader learning path.

New to building LLM applications generally? Start with Building LLM Applications. Comparing orchestration frameworks? See LangChain and LlamaIndex. Ready to go deeper on agent design specifically? See Introduction to AI Agents or Advanced AI Agents.

Course Outline

• Module 1 – Course Introduction
  • Welcome and objectives
  • What LangChain and LangGraph are for
  • Framework versus from-scratch development
• Module 2 – LangChain Fundamentals
  • Core components and abstractions
  • Models, prompts, and output parsers
  • Composing chains
  • Hands-on exercise: build a chain
• Module 3 – Memory and Data
  • Managing memory and state
  • Document loaders and text splitting
  • Embeddings and vector stores
  • Building a retrieval pipeline
• Module 4 – Retrieval-Augmented Generation
  • RAG with LangChain components
  • Retrievers and reranking
  • Grounding and citations
  • Hands-on exercise: a RAG application
• Module 5 – LangGraph for Workflows
  • Why graphs: state and control flow
  • Nodes, edges, and state
  • Branching, loops, and human-in-the-loop
  • Hands-on exercise: a stateful graph
• Module 6 – Agents with LangGraph
  • Building agents as graphs
  • Tool use and routing
  • Reliability and observability
  • Hands-on exercise: a graph-based agent
• Module 7 – Production Considerations
  • Debugging and tracing
  • Evaluation and testing
  • Cost, performance, and maintenance
  • When to use the framework and when not to
• Module 8 – Course Wrap-Up
  • Key takeaways
  • Resources for continued learning
  • Next steps toward advanced agents