Telefônica Brasil (Vivo)
Aura customer-service assistant
Vivo's Aura handled more than 20 million customer interactions monthly by January 2020, Microsoft reported
Problem
Vivo needed to interpret customer questions across many service channels while keeping response times low during peaks in demand.
Approach
Vivo launched Aura in February 2018 and used Microsoft AI services to develop and scale it. Bot Framework supported deployment across channels, while language-understanding services classified customer intent. A team of former call-center agents reviewed interactions to improve the models.
Results
Takeaway
Human agents continued to support the assistant by reviewing ambiguous questions and training its language models. The reported interaction volume did not measure resolution rates.
Categories
- Size
- Large enterprise
- Industry
- Technology and telecom
- Business function
- Customer service
- Innovation type
- Process innovation
- AI technology
- Conversational and voice AI
- Adoption
- Partner co-development
- Evidence
- Vendor case study
Sources
Source summaries
Microsoft described Aura's language-understanding services and its deployment across customer-service channels. It reported more than 20 million monthly interactions and explained how former call-center agents helped train the system.
Full details are in the original sources.