Fastweb + Vodafone: Transforming Customer Experience with AI Agents using LangGraph and LangSmith

Overview

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.

The challenge

Customer service in telecommunications operates at massive scale with complex, interconnected challenges: customers require immediate assistance with billing inquiries, service activations, roaming questions, and technical support, often expecting resolution within a single interaction. Traditional TOBi struggled with nuanced requests that required contextual understanding, multiple system access, and end-to-end resolution. For call center consultants, the manual process of consulting multiple systems and knowledge bases could benefit from intelligent support to further enhance the speed and consistency of the customer experience.

The solution

Fastweb + Vodafone built two AI agent systems on LangChain and LangGraph. Super TOBi transforms the 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. 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. The company uses LangSmith for observability and runs daily automated evaluation of chatbot responses.

Reported business value

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. The use of generative AI in Super Agent has driven One-Call Resolution rates above 86%.