AI Agent Frameworks
Build production AI agents with LangChain, LangGraph, and CrewAI. Master stateful workflows, multi-agent delegation, memory systems, and agent testing.
Curriculum
Lesson 1: LangChain — Chains, Runnables & LCEL
Build composable LLM pipelines using LangChain Expression Language (LCEL). Chain prompt templates, LLMs, and output parsers into reusable Runnables with streaming and async support.
Lesson 2: Stateful Agents with LangGraph
Model agent behavior as a state graph: define nodes, edges, and conditional routing. Build a ReAct agent that loops until done — with full control over state at each step.
Lesson 3: Agent Memory & State Management
Differentiate in-context, external, and episodic memory. Implement a vector memory store that lets agents recall past interactions. Understand when each memory type is appropriate.
LangChain Explained in 13 Minutes
Quick introduction to LangChain — chains, agents, tools, and how to build AI applications fast.
Lesson 4: Multi-Agent Workflows with CrewAI
Define specialized Agent personas, assign Tasks, and wire them into a Crew. Build a researcher-writer-reviewer pipeline where agents hand off work and check each other's outputs.
Lesson 5: Agent Communication & Delegation Patterns
Survey the major multi-agent topologies: hierarchical (supervisor + workers), peer-to-peer, and pipeline. Understand how message passing, tool sharing, and shared state affect reliability.
Lesson 6: Human-in-the-Loop Agents
Add approval gates that pause agent execution and wait for human confirmation before irreversible actions. Implement interrupt-and-resume workflows in LangGraph and understand UX patterns for agentic oversight.
Multi-Agent AI Systems
How multiple AI agents collaborate, delegate, and solve complex problems together.
Lesson 7: Testing & Debugging AI Agents
Mock external tools for deterministic testing, trace agent execution step-by-step with LangSmith, and write integration tests that verify the agent reaches the correct goal state.
Lesson 8: Capstone — Build a Research Agent Team
Build a multi-agent research pipeline: a Planner breaks down a research question, a Searcher retrieves web sources, a Writer synthesizes a report, and a Critic reviews it — all orchestrated with LangGraph.
Building Production AI Agents
Patterns for production agent deployment — error handling, human-in-the-loop, and checkpointing.
Course Quiz
5 questions · ~5 min · Pass 4/5 to unlock your badge