AI Agents Tutorials

Master AI agents with 24 visual, step-by-step tutorials. From agent fundamentals to production multi-agent systems — build intelligent agents with LangChain, CrewAI, Claude SDK and more.

24 Tutorials
4 Learning Paths
4 Free Tutorials

Learning Paths

Follow a structured path or jump to any topic. Each path builds on the previous one.

Topic Explorer

What Are AI Agents?

Autonomous systems that perceive, reason, and act using LLMs as their core.

LLMs as Reasoning Engines

How large language models power agent decision-making and planning.

Agent Architectures

Single-agent, multi-agent, and hierarchical architecture patterns.

Prompting for Agents

System prompts, few-shot examples, and instruction design for agents.

Tool Use Fundamentals

Equipping agents with tools to interact with APIs, databases, and services.

Memory & Context

Short-term, long-term, and episodic memory for persistent agents.

ReAct Pattern

Reasoning and acting in an interleaved loop for complex tasks.

Chain of Thought

Step-by-step reasoning, planning, and task decomposition strategies.

Function Calling

Structured tool invocation with typed parameters and return values.

RAG for Agents

Retrieval-augmented generation for knowledge-grounded agent responses.

Structured Outputs

JSON mode, schema validation, and reliable output parsing.

Error Handling

Retry strategies, fallbacks, and graceful degradation for agents.

LangChain Agents

Build agents with LangChain's agent executor and tool ecosystem.

LangGraph

Stateful, multi-step agent workflows with graph-based orchestration.

CrewAI

Multi-agent collaboration with roles, goals, and delegation.

AutoGen

Conversational multi-agent systems with human-in-the-loop.

Claude Agent SDK

Build agents with Anthropic's official agent development kit.

OpenAI Assistants

Assistants API with threads, tools, and file handling.

Multi-Agent Orchestration

Coordinating multiple specialized agents for complex workflows.

Evaluation & Testing

Benchmarks, evals, and systematic testing for agent quality.

Guardrails & Safety

Content filtering, output validation, and responsible agent design.

Deployment & Scaling

Production deployment, monitoring, cost optimization for agents.

Human-in-the-Loop

Approval workflows, escalation, and collaborative agent patterns.

Real-World Agents

End-to-end agent projects: customer service, coding, research.