AI-powered agent cuts analysis time by 80% at One New Zealand
One New Zealand has implemented a new AI agent, termed Network Concierge, aimed at reducing the time needed to analyse and resolve customer network complaints. The agent uses Amazon Bedrock from Amazon Web Services to consolidate information from various systems, streamlining a process that previously required customer service and network teams to manually consult a range of tools.
Process simplification
The Network Concierge agent enables teams to input customer details and automatically retrieves performance data, alarms, and records of past incidents. The system then produces a single summary for customer service representatives, detailing ongoing issues and providing advice on next steps. This automation has resulted in an 80% reduction in analysis time, supporting faster issue resolution for consumers.
Internal efficiencies
Previously, diagnosing network and coverage complaints involved a fragmented toolset and significant manual intervention. The new agentic AI solution changes this approach by serving as a central repository of information that provides actionable guidance to engineers within minutes, instead of the prolonged waits previously experienced by customers and frontline staff.
"Building on the success we've seen with AWS's generative AI in our contact centres, we wanted to apply this technology to speed up diagnosis and resolution when our customers report network and coverage related issues. Our Network Concierge agent pulls everything into one place and gives our engineers clear answers in minutes, which in turn reduces wait times for customers," said Thaigan Govender, GM Mobile Networks, One NZ.
Storm response
One New Zealand has also applied the same AI-driven methodology to its management of network power outages, particularly during storms. During such events, the agent helps engineers prioritise the deployment of mobile generators to sites most in need, using real-time data on backup power levels and network criticality. This approach was used in a recent severe weather event in the South Island, with company teams reportedly able to react more quickly to keep services running.
Strategic automation
One New Zealand is considering further integration of AWS agentic AI tools into its systems, aiming to extend automation across more aspects of incident management and field-force operations. The company states this is part of a broader move towards a model where AI-supported tools handle repetitive data collation and triage, leaving staff free to address more complex customer and operational challenges.
"These new tools let our teams work smarter and much faster. Our goal is to become the world's most AI-enabled telco. Working with companies like AWS helps us get there. By weaving AI into the way we run the network and support customers, we're changing how we respond to outages, solve issues, and deploy people on the ground. AI handles the repetitive, data gathering type work that is time consuming, and our people focus on the tricky and important things. AI-first, human when it matters most," said Govender.
Technology provider perspective
Amazon Web Services sees the collaboration as an example of how advanced AI applications can directly impact telecom operations and customer experience in New Zealand.
"Today, losing network connectivity even for a few minutes can disrupt people's daily activities, and that's why we think One NZ's Network Concierge is so impactful. By reducing analysis time by 80%, it can help Kiwis get back online much faster. Looking ahead, this technology will predict issues before they occur and automate repairs in the background before they turn into major disruptions. One NZ's implementation of Amazon Bedrock and agentic AI demonstrates how leading New Zealand companies are leaning into the latest AI technologies to improve customer experience and operational efficiencies, and we look forward to supporting their AI journey," said Manuel Bohnet, Country Manager, AWS New Zealand.
