Blip
AI-suggested replies for customer conversations
Brazilian messaging platform Blip raised acceptance of AI reply suggestions from 30% to 80%
Problem
Blip needed to use its data better, ship features faster, scale reliably and keep security tight to hold customer trust.
Approach
Blip uses Azure OpenAI Service to suggest replies based on each customer's conversation history. The platform runs as microservices on Azure Kubernetes Service and is moving from .NET Core to .NET 8.
Results
Takeaway
Blip processes more than 1 billion messages a month. A finance customer's copilot produced twice as many loans as the control group.
Categories
- Industry
- Technology and telecom
- Business function
- Customer service
- Innovation type
- Product and service innovation
- AI technology
- Generative AIConversational and voice AI
- Adoption
- Built in-house
- Evidence
- Vendor's case study
Sources
Source summaries
Microsoft reports that Blip added generative AI reply suggestions and was moving to .NET 8. Acceptance of the suggestions rose to 80%.
Full details are in the original sources.