United KingdomPublic sector2025 – ongoingDriver and Vehicle Licensing Agency
Natural-language telephone routing
DVLA reported 50% less time in telephone menus after introducing natural-language routing
Problem
Callers navigated several levels of touchtone menus. The menus required effort and frequently routed inquiries inaccurately.
Approach
DVLA used Google Dialogflow within Content Guru's Storm contact-center platform to interpret callers' stated reasons for calling. Its administrators developed the routing flows. The system selected a programmed response or transferred the caller to an adviser.
Results
Takeaway
The system interpreted the inquiry but could not access customer records. Advisers retained responsibility for inquiries requiring those records.
Categories
- Size
- Large enterprise
- Industry
- Public sector
- Business function
- Customer service
- Innovation type
- Process innovation
- AI technology
- Conversational and voice AI
- Adoption
- Off-the-shelf tool or platform
- Evidence
- Company's own claim
Sources
Source summaries
DVLA documented the telephone system in production and reported a 50% reduction in IVR navigation time. It also reported 20k automated transfers monthly and described the limits on customer-record access.
Full details are in the original sources.