Salesforce Telecommunications New Zealand

One New Zealand

Customer Service Automation

A complex prepaid product landscape made it difficult for customers to choose the right plan. One NZ has built a reputation for delivering reliable connectivity — reaching 99% of the population, from major cities to the most remote rural areas.

24/
5 weeks to build prepaid agent
5 weeks to build prepaid agent 24/7 on-demand customer service
7 on-demand customer service

Reported impact

Business outcome

Reported outcomes include 5 weeks to build prepaid agent, 24/, and 7 on-demand customer service.

  • Customer Experience
  • Revenue Growth
  • Scalability

Solution

One NZ set out to simplify their prepaid offerings and migrate hundreds of thousands of customers to seven improved plans. With Agentforce, existing customers can easily understand and pick a new plan on demand. Agentforce provides a self-service path to migrate hundreds of thousands of prepaid customers to better prepaid plans. To bring their vision to life, One NZ is using Agentforce , the agentic layer of the Salesforce Platform , to build a digital assistant that helps customers quickly and seamlessly choose the best mobile plan for their needs. Built in just five weeks, Agentforce streamlines what used to be a multistep, employee-assisted process into a simple, touchless journey from start to finish. For their initial pilot, One NZ has identified a segment of hundreds of thousands of prepaid customers as the best fit to focus on now.

Data flow

Operational, customer, and engagement data is unified in Data 360, Agentforce uses that context to authenticate prepaid subscribers, explain options, and convert mobile plans, and resulting actions and updates are written back to Agentforce so teams and customers work from the same current state.

Solution architecture

5 components · 3 layers
  1. Storage
    • Data 360 Unifies enterprise and behavioral data so teams can authenticate prepaid subscribers, explain options, and convert mobile plans with current context.
  2. Serving
    • Communications Cloud Stores subscriber, plan, and product context that supports authenticate prepaid subscribers, explain options, and convert mobile plans.
    • Experience Cloud Provides the self-service portal through which users access workflows that help teams authenticate prepaid subscribers, explain options, and convert mobile plans.
    • Agentforce Voice Extends agentic support into voice channels used to authenticate prepaid subscribers, explain options, and convert mobile plans.
  3. Orchestration
    • Agentforce Runs the AI agent workflows that authenticate prepaid subscribers, explain options, and convert mobile plans.

Architecture clues

  • A one-time-password step is used to authenticate users before plan changes.
  • SMS is used as part of the customer interaction flow.
  • The solution is designed to provide always-on self-service support.
  • The system operates on live or near-real-time operational data.
  • Vector search is used to retrieve trusted knowledge in real time.
  • Voice support is part of the agentic service experience.

Evidence from the source

24/
5 weeks to build prepaid agent
A complex prepaid product landscape made it difficult for customers to choose the right plan.
More than one million people currently use One NZ’s prepay service, which allows customers to customize their own plans with their unique combo of data, minutes, and texts.
One NZ has built a reputation for delivering reliable connectivity — reaching 99% of the population, from major cities to the most remote rural areas.
“The connectivity we provide is an essential service to so many people both in New Zealand and overseas,” said CEO Jason Paris.
Transparency Evidence & methodology 96/100 reference value · 89% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value96/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity16/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    5 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    6 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Salesforce

    One New Zealand customer story

    First-party
    https://www.salesforce.com/customer-stories/one-nz/
    Source type
    Vendor-published customer story
    Published
    Oct 15, 2025
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Oct 15, 2025 · Salesforce · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.