For many people with type 2 diabetes, knowing what to do is not the hard part — sticking with it is. Managing the condition demands long-term changes to eating, exercise and medication, but the condition can worsen gradually without obvious immediate consequences, making it easy for good intentions to fade under the pressures of daily life.

Researchers at the Auckland Bioengineering Institute (ABI) at Waipapa Taumata Rau, University of Auckland are developing an AI-powered digital coach called DiNa to help bridge the gap between doctor visits. The system is designed to support people in staying on track with goals they have set alongside their healthcare team, according to a university announcement.

Dr Gonzalo Maso Talou leads the project, which has received more than NZ$4 million in funding from the Ministry of Business Innovation and Employment. DiNa is part of ABI's broader digital twin programme and is currently being tested in a clinical trial involving people with type 2 diabetes.

"DiNa is not about curing diabetes," Maso Talou said. "What we're trying to do is increase people's chances of adhering to the treatment plan they've developed with their clinician."

The need is significant. According to Health New Zealand's Virtual Diabetes Register, more than 365,000 people were living with diabetes in Aotearoa in 2025, a figure that has risen by more than 40 percent since 2011. Diabetes disproportionately affects Māori, Pacific and Indian communities.

The current study will follow 10 participants with type 2 diabetes over three months. Half are using DiNa, while the other half are using an existing diabetes-management tool, allowing researchers to compare outcomes. The team, which includes PhD student Kekayan Nanthakumar, is investigating whether personalised, ongoing support can help people maintain healthy habits more effectively.

DiNa draws information from multiple sources, including meal records, medication tracking, smartphone activity data and continuous glucose monitors (CGMs). Rather than requiring users to carefully log every detail themselves, the system aims to make monitoring as effortless as possible. Users can photograph their meals, and artificial intelligence identifies the foods and estimates calories, carbohydrates, protein and other nutritional information. If details are missing, users can correct or add them using voice commands.

"It removes a lot of the burden of manually keeping food diaries," Maso Talou said. "That's important because traditional tracking is time-consuming and people often forget details or stop recording altogether."

For exercise, DiNa can access information already gathered by smartphones and wearable devices. People can also promptly note if they have taken their prescribed medicines. However, what sets DiNa apart is its conversational nature. Rather than operating like a conventional health application, the platform lets users interact with an AI coach via a voice-only interface. Initial versions featured a talking head on a screen, but participants did not necessarily warm to that approach, Maso Talou said.

"We originally thought a realistic virtual person would make the experience better. What we found was many users preferred just talking by voice. It was less demanding and felt more natural."

This creates a dynamic that resembles a phone chat more than a video meeting. DiNa could assist a person in determining the optimal time for physical activity, pinpoint obstacles hindering their progress, or propose adjustments to schedules when disruptions occur. The platform offers uplifting feedback during successful periods and aids users in troubleshooting when challenges arise.

The digital coach is not designed to replace clinicians. The information it provides comes from curated New Zealand diabetes resources developed with clinical partners, and it directs users back to healthcare professionals whenever clinical advice is needed, according to Maso Talou.

"There can be months between appointments. People often have questions or uncertainties during that time. DiNa can help people better understand their condition and the advice they've already received."

Participants in the study have already responded positively to the technology, the researchers said. "One of the first things people told us was how much easier it made monitoring. Many were already familiar with tracking food and medication. They liked that the system reduced that workload and allowed them to focus on getting on with their lives."

Beyond behaviour change, researchers are working toward a more ambitious goal: personalised digital twins. These are computer models that simulate how an individual's body responds to factors such as food, exercise and medication. Early versions can already model glucose responses using information about carbohydrates, fats and proteins. Eventually, that could allow users to ask highly personalised questions before making decisions — for example, comparing two meal options to see which is more likely to cause a glucose spike, or generating healthy recipes based on glucose levels and ingredients already at home.

"Two people can respond very differently to exactly the same meal," said Maso Talou, who is co-lead on the digital twin project with ABI colleague Dr Finbar Argus. "Factors such as sex, metabolism, activity levels and other physiological differences all play a role. The digital twin helps us move toward truly personalised advice."

Scientists think this innovation may serve as a valuable learning aid, enabling individuals to gain deeper insight into how their bodies react to various actions and giving them the ability to make well-informed decisions. The first three-month investigation marks the initial of three intended test phases, with bigger studies planned for the coming year. Information gathered from those tests will additionally assist scientists in improving the core digital twin technology. Should the outcomes be favorable, the team hopes DiNa could eventually be integrated into healthcare systems and made widely available.

For Maso Talou, the long-term goal is straightforward. "We want to help people make sustainable lifestyle changes and stay engaged with their care. If we can make it easier for people to follow the plans they've already developed with their healthcare team, we have an opportunity to improve health outcomes and quality of life."