The Opportunity
NOS aimed to evolve its traditional Interactive Voice Response (IVR) based customer support into a more natural and efficient conversational experience.
High volume of billing and payment contacts
Billing and payment use cases represent a significant share of inbound calls, creating operational pressure and increasing costs, even though many interactions are repetitive and well-suited for automation.
Rigid and limited IVR experience
The existing voice journey relied on static menus and reactive guides, allowing at most two useful conversational turns. This limited resolution capacity, often led to customer frustration, and increased the likelihood of unnecessary escalation to human agents.
Need for a hybrid conversational model
NOS needed a way to introduce conversational AI without disrupting the entire support architecture. The solution had to coexist with legacy static flows, maintain strict control over loops and fallback logic, and preserve a consistent, high-quality experience.
The Solution
We designed and implemented a conversational AI Voice Assistant integrated into NOS’s existing IVR ecosystem, introducing an intelligent intent detection layer capable of routing customers to either static or conversational flows.
The initial MVP focused on billing and payment use cases. A dedicated conversational agent interprets open questions, performs contextual disambiguation when needed, and delivers natural language resolutions using data from the NOS application APIs.
The architecture enforces strict control of conversational turns to avoid loops, includes fallback mechanisms to IVR menus when limits are reached or frustration is detected, and ensures a fluid, less robotized interaction. By combining structured IVR logic with AI-powered conversational resolution, NOS can incrementally transition toward a more scalable and human-like customer support model while preserving operational stability.
The Impact
The implementation of a voice assistant enabled NOS to significantly reduce operational pressure on its customer support teams while improving the overall customer experience.
By automating high-volume billing and payment interactions, the solution reduces unnecessary transfers to human agents and shortens resolution times for common queries. Customers benefit from faster, more natural interactions that feel closer to a guided conversation than a rigid script.
The projected reduction of 10,000 calls per month translates into meaningful cost savings and improved efficiency. Just as importantly, this hybrid conversational model establishes a scalable foundation for expanding AI-driven automation to additional use cases, supporting NOS’s long-term strategy of modernizing and optimizing its customer support operations.
