Countdown (now Woolworths NZ), one of New Zealand's leading supermarket brands, serves over three million customers every week across its 185 stores nationwide. With a team of more than 20,000 members, Countdown offers customers a wide selection of over 22,000 products. The 'Countdown X' division oversees the company's digital and technological aspects, including online shopping, the Onecard loyalty programme, digital marketing, customer personalisation, and customer care. The Countdown brand was part of Woolworths New Zealand, a subsidiary of the publicly-listed Australian company, Woolworths Limited.
The Challenge
As Countdown's online business experienced rapid growth, the company recognised the need to provide customers with self-service options to scale their customer support team effectively. Introducing a digital assistant across multiple channels became a crucial part of their digital strategy. Countdown aimed to deliver quick and efficient service via web chat, interactive voice response (IVR), and integration with virtual assistant platforms like Alexa and Google Assistant. While leveraging the work done by the WooliesX team in Australia, Countdown needed to create a customised version for the New Zealand market.
The Solution
ClearPoint, chosen for their expertise in digital innovation and DevOps practices, began by building a proof of concept virtual assistant in just two days. After validating the prototype, the team set out to build Countdown's digital assistant, Olive, with the goal of going live within three months.
ClearPoint's engineers developed Olive using Google DialogFlow NLU (natural language understanding) integrated with a custom fulfilment service built with NodeJS, which connected to Countdown's backend systems. They implemented fully cloud-based containerised services using Kubernetes and Google Cloud, and created an automated deployment pipeline using Google Cloud Build. This pipeline allows Countdown teams to deploy to test environments in under 10 minutes and promote to production in under 5 minutes. High unit test coverage and automated end-to-end tests ensure fast, safe, and frequent deployments to production.
The Clearpoint team provided technical and thought leadership to ensure we created something helpful for our customers and relevant for our business. They provided a great team who blended well in our Agile Tribe and added to our culture of experimentation.”
— Adam Hatley-Owen, former Head of Digital Experience, Woolworths NZ
The Outcome
Olive went live on a single page within three months of kick-off, answering general questions about store details, opening hours, locations, and FAQs. The team then introduced the ability to handle refund requests, and Olive was subsequently rolled out across the rest of the site, including the main 'Contact Us' page.
The automated deployment pipeline, which included end-to-end tests for each feature, enabled high-quality releases multiple times a day. Olive has already answered thousands of questions from Countdown customers, reducing call volumes to the Customer Support team. Historical conversations are used to prioritise new features and refine training data for the machine learning model, with a goal of achieving 80% conversational success within the first year of operation.
The team at CountdownX really understand Product Management. This starts with setting the desired outcomes and giving teams the space to deliver. Another key aspect is their grasp of how to evolve a product through ongoing evidence-based investment.”
— Marcus Simmons, former Product Manager, ClearPoint
The key objectives for the platform are:
- Fast, safe, and frequent enhancements
- Enable customer self-service delight
- Provide customer insight gold
These objectives are tracked via twelve key results including:
- Cycle Time for New Features
- Deployment Frequency
- Time to Deploy
- Test Coverage
- Change Failure Rate
- Monthly Active Users
- Conversation Success
- Average Session Length
- Fallback Rate
- Team Adoption
- Team Usage
- Insight Value
It’s been awesome working with CountdownX – their engineering practices really align with ours, which means we were able to deliver a digital assistant really quickly, along with a CI/CD pipeline which has been instrumental in our success.”
— Robert Redgwell, Principal Engineer, ClearPoint
By leveraging technologies such as Google DialogFlow, Google Cloud Build, GKE, CI/CD pipelines, NodeJS, Kubernetes, Docker, Helm, and Stackdriver, ClearPoint and Countdown successfully created an AI enhanced digital assistant that enhances customer experience and streamlines support operations.
