Customer Service Automation
Vodafone Ireland needed to modernize its TOBi virtual assistant because an older assistant deployment could no longer meet containment goals or take advantage of the newer generative-AI, NLU, and self-learning capabilities available in the latest platform.
Reported impact
Vodafone Ireland improved customer-assistant containment, reduced misinterpretation of user requests, and accelerated the creation of new conversational journeys after redeploying TOBi on the latest assistant platform.
Vodafone Ireland worked with IBM Technology Expert Labs to redeploy its TOBi virtual assistant on the latest IBM watsonx Assistant release. The modernization introduced generative-AI features that use retrieval-augmented generation against Vodafone content so the assistant can provide grounded, conversational answers instead of relying only on legacy dialog design. The new platform also includes a transformer-based natural-language-understanding engine that classifies requests with less training effort, plus self-learning algorithms that improve routing and response quality from prior interactions. During the migration, Vodafone comprehensively rebuilt TOBi's conversational journeys and adjusted its surrounding application infrastructure so the assistant could exploit the upgraded NLU and RAG stack. The result is a more maintainable customer-service architecture that lets teams create new journeys faster while improving containment and reducing misunderstood utterances.
Customer messages enter TOBi, watsonx Assistant retrieves grounded content from Vodafone sources with RAG, its NLU model classifies the request and routes the conversation, and the self-learning mechanisms use prior interactions to improve future responses and journey handling.
3x improvement in the turnaround time for creating new conversational journeys
An 80% reduction in misunderstood customer utterances
The solution also includes a natural language understanding (NLU) engine that uses a new foundation model based on transformer architecture
These new features leverage Large Language Models (LLMs) for retrieval-augmented generation (RAG), designed to generate accurate, conversational answers grounded in Vodafone’s content.
redeploy TOBi on the latest watsonx Assistant, which contains generative AI capabilities.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
IBM Sample May 6, 2024 O2 Czech Republic O2 needed to manage a broad mix of 24x7 customer-service requests more efficiently while still giving customers fast answers across voice, mobile-app and operator-assisted channels. Approximately 30% of O2 customers communicate exclusively by voice with the virtual assistant IBM Cloud · IBM watsonx Assistant IBM Sample Apr 18, 2024 Vodafone Vodafone wanted to use generative AI to speed up how its teams design, test, and improve TOBi conversational journeys because manual journey testing and gap analysis slowed releases and limited how much optimization the… 99% improvement in turnaround time of journey testing IBM Cloud Code Engine · IBM watsonx Assistant · IBM watsonx.ai IBM Sample Apr 3, 2024 WINDTRE WINDTRE needed to automate and accelerate claims handling for telecom service issues because high report volumes, stateful operational complexity, and repetitive service-desk tasks were slowing response times and… 10,000+ reports handled per month with AI and automation IBM Cloud · IBM Consulting · IBM Watson Knowledge Studio 