Patient with Healthcare Nurse


Chronic disease management often entails self-discipline and long-term support from families and healthcare providers. During the process, the majority of patients experience fear, frustration, and lack of communication with providers. We are making this journey easier, more accessible, and less daunting through a data-centric approach.


Graphic Shapes

Bring the appropriate data to the table

  • Diabetes requires monitoring glucose levels in sync with food and exercise. Silos lead to shooting in the dark.

  • Diabetes also requires clinicians and data experts. Our patented technology brings input from both parties.

Data Processing

Make data collection super easy for every user

  • Automate data collection through smart devices, electronic medical records, and blood reports.

  • Factors like age and socioeconomic status should not affect your ability to use the app.

Healthy Snack

Make changes that stick

  • Translating clinical objectives to relatable outcomes that patients are likely to follow.

  • Keeping users motivated through our proprietary nudging algorithm. Our framework focuses on nudging when the user is primed and is most likely to adopt the recommendation.

  • Personalize the recommendations to fit your lifestyle and habits so that the recommendations are not short-lived.

Construction Signs

Warn and raise red flags but sparingly

  • Raising warnings and red flags for preventing bad outcomes in both the short and the long term.

  • We are conscious of notification fatigue. Hence, we do not overwhelm users with excess inputs. Unless necessary, our recommendations are aggregated over a few data points and they are delivered when in a cadence that is decided based on user profiles and the acuity of the situation.


Account for the error in data collection

  • This is probably the most understated and impactful use of AI in this context - to detect and account for when users' estimates (for food intake and exercise) are far off from reality and take course-corrective measures.

  • By defining objective functions that are independent of subjective observations. One such example is of using glucose levels from continuous glucose monitors / glucometer.

Powered by



Thanks for submitting!