Use Case Intelligence RSS Search use cases Search
IBM Telecommunications Europe and Africa

Vodafone

Customer Service Automation

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 customer-service organization could do.

Read the original story Explore all use cases
99% improvement in turnaround time of journey testing
approximately 14 different languages
around 6.5 hours to test each new journey
less than five minutes per journey

Reported impact

Business outcome

Vodafone dramatically shortened journey-testing and gap-analysis work for TOBi, created a repeatable way to compare central and local conversational content, and expects the added AI-assisted quality checks to improve customer satisfaction.

  • Customer Experience
  • Productivity Improvement
  • Speed to Market

Solution

Vodafone worked with IBM to build a generative-AI testing and analysis layer around its TOBi virtual assistant. After workshops identified five candidate use cases, the team prioritized journey testing and gap analysis, then completed a five-week build with IBM Client Engineering and IBM Consulting. IBM Cloud Code Engine was used to orchestrate a service that ran multiple test scenarios in Voice Flow, while IBM watsonx.ai simulated customer interactions, analyzed the resulting transcripts, and produced sentiment, emotional, and comparative journey insights. The workflow helped Vodafone compare content between its Central Library and local market journeys and identify where conversations could be improved before deployment. TOBi itself continues to run on IBM watsonx Assistant across roughly 14 languages, and the new AI-assisted test stack shortens validation cycles while improving the quality of journey content before live customer traffic sees it.

Data flow

Journey content from Vodafone's Central Library and market variants is fed into an IBM Cloud Code Engine service that runs test scenarios in Voice Flow, watsonx.ai simulates customer interactions and analyzes transcripts, and the resulting insights help designers improve TOBi before release.

Solution architecture

4 components · 4 layers
  1. Compute
    • IBM watsonx.ai Simulates customer interactions, analyzes transcripts, and performs sentiment, emotional, and gap-analysis tasks for TOBi journeys.
  2. Serving
    • IBM watsonx Assistant Powers Vodafone's TOBi virtual assistant that the team is improving through the new testing workflow.
  3. Orchestration
    • IBM Cloud Code Engine Hosts the orchestration service that executes the automated testing workflow.
  4. Uncategorized
    • Voice Flow Executes multiple TOBi test scenarios that are then analyzed by the IBM AI workflow.

Architecture clues

  • The build phase lasted five weeks and spanned data, design, architecture, and development workstreams.
  • The pilot prioritized two use cases out of five identified in the workshops: journey testing and gap analysis.
  • The solution added sentiment and emotional analysis on top of transcript analysis for TOBi journeys.

Evidence from the source

An orchestration service was built and deployed using IBM Cloud Code Engine, which was responsible for executing multiple test scenarios in Voice Flow.
TOBi, a virtual assistant that is available 24x7 to answer customer questions ... in approximately 14 different languages.
The service relied on IBM watsonx.ai ... to simulate customer interaction with TOBi.
The transcripts generated by these interactions were then analyzed using watsonx.ai.
the team observed a 99% improvement in the turnaround time of journey testing
Transparency Evidence & methodology 100/100 reference value · 89% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value100/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    2 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. IBM

    Vodafone customer story

    First-party
    https://www.ibm.com/case-studies/vodafone-tobi
    Source type
    Vendor-published customer story
    Published
    Apr 18, 2024
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
IBM May 15, 2024 Vodafone Ireland Telecommunications Ireland 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… 3x faster for creating new conversational journeys Customer Service Automation IBM watsonx Assistant IBM May 6, 2024 O2 Czech Republic Telecommunications 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 Customer Service Automation IBM Cloud · IBM watsonx Assistant IBM Apr 3, 2024 WINDTRE Telecommunications Italy 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 Customer Service AutomationIT Operations Automation IBM Cloud · IBM Consulting · IBM Watson Knowledge Studio