AI Agents with LangChain and LangGraph

Meet your instructors and discover the skills you'll need to succeed in this AI agents course.

Explore how AI evolves from basic LLM calls to fully autonomous agents, learn agentic frameworks, applications, and how to design effective agent-driven workflows.

Explore setting up and using the OpenAI SDK with Vocareum keys to build Python applications that leverage LLMs for content creation and business solutions.

Learn to build custom AI agents by abstracting LLMs, defining agent roles, managing responses, and adding memory for multi-turn conversations.

Discover four key agentic design patterns—reflection, tool use, planning, and multi-agent collaboration—to boost LLM performance and reliability in complex tasks.

Learn to enhance AI agents with memory and self-reflection, enabling them to critique, refine, and improve responses iteratively based on conversation history.

Learn how to enable AI agents to detect when to call functions, execute them with arguments, and integrate results into conversational responses using memory and tool abstractions.

Discover the ReAct Agent, which combines reasoning and acting to help AI models plan and execute complex, multi-step tasks using external tools for improved decision-making.

Learn to build a ReAct agent that plans, reasons, uses tools, and iterates until task completion, combining LLM reasoning with function execution using Python and OpenAI APIs.

Discover how multiple AI agents collaborate, communicate, and specialize to solve complex problems efficiently, with applications and key challenges in multi-agent systems.

Learn to implement multi-agent collaboration with specialized agents using function calls, supervision, and memory for coordinated task delegation in Python.

Discover agentic AI frameworks like LangChain, AutoGen, CrewAI, LangGraph, and PydanticAI to accelerate building robust, scalable AI applications with prebuilt tools and best practices.

Learn to build a simple LangChain app: integrate LLMs, manage chat history, use prompt templates, and apply few-shot prompting to create customizable chatbots with memory.

Learn how to use LangChain’s streaming to get AI model responses chunk-by-chunk, enabling real-time, interactive, and responsive experiences in chatbots and AI applications.

Learn to parse and structure LLM outputs in LangChain using output parsers, TypedDict, Pydantic models, and automatic error correction for robust workflows.

Learn to build flexible, multi-step AI workflows in LangChain using Runnables and LCEL for composing, batching, and managing complex chains with ease and scalability.

Discover LangChain RAG: enhance LLMs with external knowledge by retrieving, augmenting, and generating accurate, context-aware responses using structured pipelines and prompt templates.

Learn how to encapsulate Python functions as tools in LangChain, enabling LLMs to call functions, interact with APIs, and handle external computations in AI workflows.

Learn to build a simple LangChain agent that combines LLMs, memory, and tools for automated, multi-step workflows and natural user interactions.

Learn to build dynamic, agent-driven AI workflows using LangGraph, leveraging nodes, edges, and routing for modular, adaptive application control and automation.

Learn to manage agent state in LangGraph using TypedDict for simple schemas or Pydantic for robust validation, supporting reliable, flexible AI workflow state machines.

Learn to implement flexible, reliable AI agents using LangGraph by designing agentic workflows, managing parallel updates with reducers, and customizing behavior via configuration.

Learn to build LangGraph database agents that use AI to convert natural language into SQL queries, enabling users to query databases conversationally without writing SQL.

Learn techniques in LangGraph for efficient message handling—limiting, trimming, summarizing messages, and using multiple state schemas for safe, modular agentic workflows.

Learn how short-term memory in LangGraph uses state, checkpoints, and threads to enable persistent, multi-turn agent workflows that remember conversation context across runs.

Learn how to expand AI agents' knowledge and reliability using APIs, memory, context, and evaluation to build effective, safe, and scalable workflow solutions.

Learn to integrate external APIs as tools in LangChain via LangGraph, enabling agents to fetch real-time data and enrich LLM responses using structured workflows and router logic.

Learn how to persist agent memory in LangGraph using databases like SQLite and enhance long-term AI memory with vector storage via LangMem for robust, session-aware agents.

Explore Agentic RAG: how retrieval-augmented generation pipelines empower AI agents with up-to-date, relevant knowledge using embeddings, vector databases, and semantic search.

Explore single-agent Retrieval-Augmented Generation in LangGraph, adding agentic decision-making for dynamic web search and improved knowledge-grounded AI responses.

Learn to ensure AI agent reliability through clear metrics, evaluation, testing, and ongoing monitoring for trustworthy, consistent, and scalable performance in real-world applications.

Explore human-in-the-loop and observability techniques to monitor, debug, and optimize AI agents, ensuring oversight, transparency, and reliable performance at scale.

Explore how to add human approvals or edits at key points in LangGraph agent workflows, enhancing safety and control with human-in-the-loop techniques.

Learn how to use MLflow with LangGraph and LangChain to trace, log, and inspect each step of agent workflows, enabling better debugging, transparency, and observability.

Learn to build, evaluate, and benchmark RAG pipelines and LangGraph agent workflows using RAGAS and MLflow for quality and correctness assessment.

Learn key security concerns in AI deployments, common threats, and best practices like access control, input validation, explainability, and monitoring to ensure safe, resilient AI systems.

Celebrate your achievement in mastering the core skills to design, build, and optimize advanced AI agentic systems beyond basic LLM use.