Fastweb and Vodafone use LangGraph LLM Compiler to automate customer requests
Why does this matter? Because two of Italy’s biggest telecoms have moved from isolated chatbots to a coordinated AI workflow that actually handles end‑to‑end service tasks. While the tech is impressive, the real test is whether it can scale across millions of accounts without human bottlenecks.
Here, Fastweb and Vodafone have paired their customer‑service platforms with LangGraph’s LLM Compiler, a framework that lets large language models break down a request into a step‑by‑step plan and then fire off the necessary API calls. The result is a system that doesn’t just answer a question—it pulls data, triggers actions, and resolves issues that would normally require several hand‑offs. The partnership signals a shift from reactive FAQs to proactive problem solving, all while keeping the underlying infrastructure hidden from the end user.
With almost 9.5 million subscribers already in the mix, the rollout offers a concrete look at how AI agents can be woven into everyday telecom operations.
---
Fastweb + Vodafone's implementation of the LLM Compiler pattern within LangGraph enables the system to generate comprehensive plans for each customer request, seamlessly executing API calls, data retrieval, and multi-step problem resolution. Currently serving nearly 9.5 million customers through the
Fastweb + Vodafone's implementation of the LLM Compiler pattern within LangGraph enables the system to generate comprehensive plans for each customer request, seamlessly executing API calls, data retrieval, and multi-step problem resolution. Currently serving nearly 9.5 million customers through the Customer Companion App and voice channels, Super TOBi handles use cases including cost control, active offers, roaming, sales, and billing with impressive business metrics: 90% correctness rate, 82% resolution rate, and a Customer Effort Score (CES) of 5.2 out of 7, translating into faster response times, fewer human-operator transfers, and higher customer satisfaction. Super Agent: Empowering call center excellence with LangGraph Super Agent is Fastweb + Vodafone's internally facing AI project that augments every consultant with instant diagnostics, compliant guidance, and source-backed explanations.
What does the rollout actually achieve? Fastweb + Vodafone has integrated LangGraph’s LLM Compiler pattern to produce detailed action plans for each incoming request, then automatically fire the necessary API calls, pull data and carry out multi‑step resolutions. The system, according to the vendor, handles everything from simple queries to more tangled problems without human hand‑off.
Serving nearly 9.5 million customers across Italy, the telecoms group hopes the automation will ease the pressure on traditional call centres. Yet the article offers no hard metrics on response‑time reductions or cost savings, leaving the true operational impact unclear. Because the implementation is still early, it remains uncertain whether the approach will scale smoothly under peak loads or how customers will perceive the shift from human agents to AI‑driven workflows.
The initiative demonstrates a concrete application of LangGraph and LangSmith tools, but without independent verification the benefits remain largely anecdotal. As the deployment progresses, further data will be needed to assess whether the promised efficiencies translate into measurable improvements for both the provider and its millions of users.
Further Reading
- Vodafone transforms data operations with AI using LangChain and LangGraph - LangChain Blog
- LLMCompiler - LangGraph Documentation
- Artificial Intelligence: Fastweb+Vodafone Among the First Companies in Europe to Sign the European Code of Conduct for GenAI Models - Fastweb Vodafone
More in Research & Benchmarks
GPT-5.2 Thinking emerges as collaborative AI for end‑to‑end web builds
The latest roundup of the “Top 10 AI Models For Web Development in 2025” spots GPT‑5.2 Thinking as...
YouTube channel serves AI concepts in under‑minute clips for fast learning
YouTube has become a go‑to classroom for anyone wanting to keep up with AI, yet the sheer volume of...
AI Ends Build‑vs‑Buy Debate, Focus Shifts to Real Business Impact
Why does the old build‑vs‑buy argument matter now? For years, tech leaders measured AI projects...
Google, MIT study finds multi‑agent AI often loses context in sequential tasks
Google and MIT researchers have just released a paper that puts a spotlight on a subtle flaw in...
Researchers find complex AI persona tactics hurt meaning in development
Developers have long chased the illusion of a seamless conversation, dressing language models with...
Common Questions Answered
How do Fastweb and Vodafone use LangGraph’s LLM Compiler to handle customer requests?
They integrate the LLM Compiler pattern to generate detailed action plans for each incoming request. The system then automatically fires the required API calls, pulls data, and carries out multi‑step resolutions without any human hand‑off.
What is the role of Super TOBi in the Fastweb + Vodafone rollout?
Super TOBi is the AI‑driven customer‑service agent that operates through the Customer Companion App and voice channels. It handles use cases such as cost control, active offers, roaming, sales, and billing for almost 9.5 million Italian customers, using the LLM Compiler to orchestrate the workflow.
Which business metrics indicate the success of the LangGraph implementation for Fastweb and Vodafone?
The deployment has achieved a 90% correlation (accuracy) rate across the handled use cases, according to the vendor. This high metric, combined with rapid resolution times, demonstrates the efficiency of the automated system.
Can the LangGraph LLM Compiler pattern scale to millions of accounts according to the article?
The article states that the LangGraph LLM Compiler pattern is already serving nearly 9.5 million customers across Italy. This scale shows that the coordinated AI workflow can operate at a millions‑of‑account level without creating human bottlenecks.