Neo4j
2 use cases using this technology
Fastweb + Vodafone: Transforming Customer Experience with AI Agents using LangGraph and LangSmith
Fastweb + Vodafone
Fastweb + Vodafone, part of the Swisscom Group and one of Europe's leading telecommunications providers serving millions of customers across Italy, built two AI agent systems on LangChain and LangGraph. Super TOBi transforms its existing chatbot TOBi into an agentic system using a Supervisor agent (for routing and guardrails) and specialized Use Case agents following the LLM Compiler pattern to call customer APIs and execute transactional actions like offer activation or payment updates. Currently serving nearly 9.5 million customers through the Customer Companion App and voice channels, Super TOBi achieves a 90% correctness rate, an 82% resolution rate, and a Customer Effort Score of 5.2 out of 7. Super Agent is an internal tool that augments call center consultants with diagnostics and guidance, storing operational knowledge as a graph in Neo4j and using an automated ETL pipeline with LangGraph and LLM agents to convert business-authored procedures into the knowledge graph; it has driven One-Call Resolution rates above 86%. The company uses LangSmith for observability, daily automated evaluation of chatbot responses, and continuous improvement.
How Mapfre Insurance modernized fraud claims with Amazon EMR Serverless
Mapfre Insurance
Mapfre Insurance, the number one auto and home insurer in Massachusetts, modernized fraud detection by combining graph-based features from Neo4j with machine learning models deployed on AWS, using Amazon EMR Serverless, Apache Iceberg tables on Amazon S3, AWS Glue Data Catalog, AWS Lake Formation, and Amazon MWAA for orchestration. Fraud predictions integrate directly with Guidewire Claims via AWS Lambda, automatically creating claim activities showing the top model drivers for adjusters. The initiative, covering Massachusetts Auto insurance and later expanded to Home insurance, has delivered more than $5 million in Net Present Value, with detection accuracy improved 50-135 percent compared to baseline methods.