Microsoft Telecommunications Europe Company newsroom

Vodafone

Customer Service Automation · Enterprise Knowledge Search

Vodafone wanted to improve customer service by overcoming the limits of traditional chatbots, which could usually answer only simple keyword-based questions and created weaker first-contact resolution and customer experience during complex enquiries.

TOBi is already supporting customers in 13 countries across Europe and Africa
first-time resolution rate increased from 15% to 60%
online net promoter scores improved by 14 points to 64 points
understands 11 different languages

Reported impact

Business outcome

Vodafone reported faster handling of complex enquiries, more personalized customer conversations, automatic escalation to human agents when needed, higher first-time resolution in Portugal, improved online net promoter scores, and reduced repetition for customers handed to agents in Ireland.

  • Customer Experience
  • Productivity Improvement

Solution

Vodafone deployed SuperTOBi as a generative AI virtual assistant for customer service, powered by Microsoft Azure OpenAI and rolled out across European markets. Customer enquiries enter Vodafone’s online chat service, where SuperTOBi interprets full sentences and phrases instead of relying on simple keyword matching, then generates more natural responses for customer-facing journeys such as appointment booking and, increasingly, billing. When the assistant cannot resolve an issue, it automatically transfers the conversation to a human agent. Vodafone paired this with SuperAgent, based on Microsoft Azure OpenAI’s Agent Copilot solution, to support customer care employees: it searches Vodafone’s companywide private knowledge database for reliable answers to complex questions and sends conversation summaries to agents so customers do not need to repeat themselves. SuperSearch extends the same AI-driven search pattern to Vodafone’s public websites.

Data flow

Customers submit questions through Vodafone's online chat, where SuperTOBi processes full-sentence enquiries using Microsoft Azure OpenAI and returns responses for tasks such as appointment booking. If an issue is unresolved, the interaction is handed to a human agent, while SuperAgent uses Agent Copilot to search Vodafone's private knowledge database and pass a conversation summary to the agent. Related answers are also exposed through SuperSearch on Vodafone websites.

Solution architecture

5 components · 3 layers
  1. Compute
    • Microsoft Azure OpenAI Provides the generative AI model capability that powers SuperTOBi and underpins Vodafone's agent-assist workflow.
  2. Serving
    • SuperTOBi Serves as Vodafone's customer-facing generative AI virtual assistant in online chat, handling complex enquiries and customer journeys such as appointment booking.
    • SuperAgent Assists customer care employees by locating answers from Vodafone's private knowledge base and passing conversation summaries to agents.
    • SuperSearch Provides improved AI-supported search on Vodafone's customer-facing websites.
  3. Orchestration
    • Agent Copilot Provides the foundation for SuperAgent to search for answers and assist human agents with complex customer queries.

Architecture clues

  • Rolled out in Italy and Portugal, with Germany and Turkey added from July 2024 and other markets to follow.
  • SuperAgent uses only Vodafone's companywide and private knowledge database rather than public sources.
  • SuperTOBi is the next generation of TOBi, which already supports 13 countries and 11 languages.
  • The program sits within a broader Vodafone customer experience transformation backed by a reallocated investment of €140 million.

Evidence from the source

"As a result, the first-time resolution rate has increased from 15% to 60% and Vodafone’s online net promoter scores ... improved by 14 points to 64 points"
"Based on Microsoft Azure OpenAI’s Agent Copilot solution, SuperAgent helps human agents to quickly search and locate answers to complex queries or multiple questions."
"It also only uses information from Vodafone’s companywide and private knowledge database, ensuring that the information is more reliable than public sources."
"SuperTOBi can interpret entire sentences and phrases, overcoming the limitations of existing chatbot technologies which typically can answer only simple questions based on a few key words."
"SuperTOBi, powered by Microsoft Azure OpenAI, can understand and respond faster to complex customer enquiries better than traditional chatbots."
"it will automatically transfer a question it can’t answer to a person that can."
Transparency Evidence & methodology 100/100 reference value · 94% 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 confidence94%
  • Source authority25/25
    The deployment is described by the adopting organization or a government source.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    6 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. Vodafone

    Vodafone customer story

    First-party
    https://www.vodafone.com/news/newsroom/technology/meet-super-tobi-vodafone-s-new-generative-ai-virtual-assistant-now-serving-customers-in-multiple-countries
    Source type
    Customer-published story
    Published
    Jul 4, 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

  • Published on source page Jul 4, 2024 · Vodafone · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.