# Agentic AI with LangGraph

A hands-on curriculum of notebooks for building autonomous, stateful, goal-driven multi-agent systems on LangGraph, progressing from foundational concepts to multi-agent orchestration.

The curriculum is organized around seven interoperable components: autonomous agents with roles, memory, tools and objectives such as a planner, a researcher and an executor; a LangGraph state machine acting as the central orchestrator with conditional routing, concurrency and retries; a structured message layer of messages, threads, steps and runs for tracing reasoning; a memory and context store spanning thread history, agent-specific context and vector databases for retrieval; callable tools and interfaces such as web search and a code interpreter; a task router for planning or delegating subtasks; and observability through LangSmith tracing and structured logging.

The learning path moves from foundational state-machine and workflow-design material through intermediate topics such as advanced routing and error handling, contrasting single-shot generative AI with the iterative, self-correcting behaviour of agentic systems throughout.

Website: https://github.com/mohd-faizy/Agentic_AI_using_LangGraph