Your cart is empty.
Keep shoppingFrom Knowledge Graph Assistant to Agentic AI with LangGraph
New
118 students
From Knowledge Graph Assistant to Agentic AI with LangGraph
Build enterprise-grade multi-agent AI systems using LangGraph, Knowledge Graphs, RAG, Neo4j, Human-in-the-Loop, Memory,
Created bySuchismita Sahu
Last updated 8/2026
English
English [Auto],
What you'll learn
- Build a multi-agent AI Assistant using LangGraph with Planner, Ontology, Retrieval, Insight, and Response agents.
- Integrate Knowledge Graphs, GraphRAG, and LLMs to deliver accurate, explainable, and context-aware AI responses.
- Implement agent orchestration, memory, tool calling, and human-in-the-loop workflows for enterprise AI assistants.
- Monitor, trace, and evaluate AI agents using LangSmith to debug, optimize, and improve production-ready AI systems.
Explore related topics
Course content
5 sections • 24 lectures • 4h 51m total length
Requirements
- Prior knowledge of Semantic Web or Knowledge Graphs is required.
- A willingness to learn Ontology Engineering and Semantic Web technologies based Agentic AI system
- A computer with at least 8 GB RAM (16 GB recommended)
- Advanced programming language in Python.
Description
Artificial Intelligence is rapidly evolving from traditional question-answering systems to intelligent, autonomous agents capable of planning, reasoning, collaborating, and making context-aware decisions. While Knowledge Graph Assistants provide a strong foundation for enterprise AI, modern applications require production-ready Agentic AI systems that can orchestrate specialized agents, maintain memory, enforce security, and generate explainable, trustworthy responses.
In this course, you will transform a Knowledge Graph Assistant into a complete Enterprise Agentic AI system using LangGraph. You will progressively build a multi-agent architecture capable of task planning, enterprise knowledge retrieval, response validation, human-in-the-loop workflows, memory management, and scalable execution.
You will develop an end-to-end enterprise application using LangGraph, Neo4j Knowledge Graphs, Retrieval-Augmented Generation (RAG), hybrid retrieval, vector search, Large Language Models, and modern AI engineering practices. You will also learn how to design and orchestrate specialized agents, including Planner, Ontology, Query, Validation, Execution, Response, Memory, Audit, and Evaluation Agents using stateful graph execution.
The course also covers enterprise AI concepts such as AgentState, graph execution, conditional routing, guardrails, observability, evaluation frameworks, asynchronous execution, streaming responses, Role-Based Access Control (RBAC), multi-tenancy, and cost monitoring. Practical healthcare-inspired examples are used throughout to demonstrate real-world implementation while following sound software engineering principles.
This advanced, project-based course is designed for software engineers, AI engineers, solution architects, knowledge engineers, and developers who want to build enterprise-scale Agentic AI applications. By the end of the course, you will have implemented a production-ready Agentic AI platform and gained practical experience with the architectural patterns used in modern enterprise AI systems.
Who this course is for:
- Enterprise Architects designing semantic data platforms and knowledge management systems.
- AI, Machine Learning, and Generative AI Engineers who want to integrate structured knowledge into intelligent applications.
- Data Engineers and Data Architects working with enterprise data integration.
- Researchers and students in Computer Science, Artificial Intelligence, Healthcare Informatics, and Data Science.
- Software Engineers interested in Knowledge Graphs and Semantic Web technologies.
- Anyone interested in learning RDF, OWL, Protégé, Apache Jena Fuseki, and SPARQL through a real-world healthcare project.