Build reliable AI with Aura Agents
Highlights:
-Knowledge Graph Fundamentals: Explanation of how nodes (people, places, things) and relationships (interactions) create interconnected data.
-The Problem with Standard RAG: Demonstrates how a standard agentic stack fails to accurately count specific talent or analyze distribution from PDF resumes.
-Aura Agent Workflow: Shows how to automate the extraction of entities from resumes into a Neo4j graph model to ground the agent with connected facts.
-Deployment and Tools: Features a low-code UI for drafting, testing, and deploying agents to secure REST and MCP endpoints.
-Graph vs. Relational Databases: A comparison highlighting the performance advantages of multi-hop querying and the flexibility to easily extend schemas without complex join tables
Chapters
- 00:07What is a knowledge graph?
- 00:33Introduction to Aura Agent capabilities
- 01:34HR talent agent use case walkthrough
- 02:40Demonstration of failed results using the standard vector RAG
- 03:04Fixing AI hallucinations using Neo4j and Aura Agent
- 03:39Achieving accurate results with graph-grounded agent tools
- 04:10Advanced multihop pattern matching and extending data models
- 04:42Comparison: Knowledge graphs vs. relational databases
- 06:53Resources for getting started with Aura Agent
Get started: https://neo4j.com/developer/genai-ecosystem/aura-agent/
Related Videos
070 ESG Supply Chain Knowledge Graph – NODES2022 – Dr. Julian Gruemmer
Introducing Workspace — The Fastest Way To Build Your Neo4j Database
