customer_support · energy · workflow
Fastweb + Vodafone deploys Super TOBi and Super Agent with LangChain and LangGraph for AI-powered customer service at enterprise scale
Traditional TOBi struggled with nuanced customer requests requiring contextual understanding, multiple system access, and end-to-end resolution, while call center agents had to manually consult multiple systems and knowledge bases for each interaction.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Supervisor filters and routes query
The Supervisor acts as the central entry point for all user queries, applying guardrails and routing each query to the most appropriate Use Case.
Tools used
LangChainLangGraphNeo4jLangSmithReAct Agents
Outcome
Super TOBi serves nearly 9.5 million customers achieving a 90% correctness rate, 82% resolution rate, and a Customer Effort Score of 5.2 out of 7. Super Agent drives One-Call Resolution rates above 86%.
What failed first
Traditional TOBi, the existing chatbot, could not handle nuanced requests requiring contextual understanding, access to multiple systems, or end-to-end resolution.
Results
Volume90%
Grounding & classification
Source type: vendor customer story
37 fields verified against source quotes.
agentic workflowai agentconversational aiknowledge searchmulti agent workflowragknowledge basesupport tickethuman review describedmetric backednamed customerproduction runtime claimedsource backedtools describedvendor confirmedworkflow describedtelecomaccuracy improvementautomation ratecustomer satisfactionresolution time reductionvendor customer storycall center aicustomer supportautonomous resolutionescalation workflowextract classify routerag answering