cover image hero.jpg

Medicube - Voice Assisted Medication Dispenser


How might we make medication adherence easier for the elderly patients?



Medication non-adherence is a big problem, specially for the elderly patients in the US Healthcare system. Some of the prime reasons contributing to this problem are - forgetfulness, organizing multiple medication, lack of knowledge and low motivation amongst patients. New pharmacy models like PillPack solve the problem partially by pre-sorting medication according to dosages, but there is nothing which tracks adherence. Mobile apps for medication management are often difficult for the elderly to interact with due to the high cognitive load. This project explores ways to leverage existing innovative solutions and integrate them with new technology to solve this problem.


Medicube is an IOT connected medicine dispenser with a built in voice assistant, which gives personalized reminders to the patient and tracks their compliance. It is an extension of the current service provided by Pill Pack where medication is sorted by timely dosages. If the patient does not take their medication on time, it sends additional voice reminders that are designed to motivate them to follow their regimen. The patient’s medicine habits could be monitored by the caregiver through an app and the system alerts them if the patient needs any assistance.




Research, Ideation, Prototyping, Visual Illustrations, Concept Video, VUI Design


Amik Ahmad, Eric Forman





New user journey

Once the patient is subscribed to PillPack, the pharmacy would send a package with prescribed medicines and the Medicube dispenser in it. Once Medicube is plugged in, the caregiver can set it up by following the easy to understand instructions through its voice interface. They can also customize medicine reminders for their patients through the caregiver facing app.


Next the patient and the caregiver sign a pledge on the app where the patient promises to abide by their medication regime and thee caregiver promises to help them in their journey to recovery. The below illustrated storyboard shows the happy path of the experience.

Happy path

Happy path.jpg

Patient motivations are not always high and will eventually result in situations when they do not want to take their medicines. Illustrated below are some instances of the unhappy path. On detecting non adherence, Medicube tries to tell the patient of the function and benefits of the medication to get them to consume it. Other strategies include reminding them of the promise that they made to the caregiver and offering a credit score like point system where proper adherence gives you a better score that can be redeemed as discount in the co-pays for medicine.


UnHappy path.jpg

The caregiver can also customize the reminders with existing physical or digital habits of the patient to integrate medication as a habit in their lives. The example illustrated below shows how the activity of listening to daily news can be integrated with a medication taking activity.

Integrating with existing habits

Existing Habits.jpg

Medicube also has provisions for emergency situations. If it detects any anomaly by the patient’s response or if the patient requests for additional help, it can send alerts to the caregiver who can then get in touch with their patients and provide help.

emergency situations

Emeregency situations.jpg

The Medicube eco system includes the pre packed medicine roll, the voice UI based smart dispenser and a caregiver facing app. The smart dispenser would also have a light ring (like the echo devices) which would give visual cues to compliment the voice UI.

Medicube ecosystem

Product Package.jpg

Device Light Animation


Persona of Alexa (Medicube)


(1) Modern and New Age

(2) Compassionate and Empathetic

(3) Respectful

(4) Calm under pressure

(5) Facilitator & not decision maker

  • Be Personal by cooperating with the user. Provide the user opportunity to have a natural back and forth dialog, adapting to the user’s preferred way of speaking and changing context.

  • Be Adaptable by solving a problem for users and being careful not to create more of them. Make their lives easier by adapting to the nuances of the user’s intended speech patterns and context.

  • Be Relatable. Respond with information relevant to the user’s intended context, and confirming shared understanding with the user only when necessary.

  • Be Available by remembering and build upon past interactions in order to improve and speed up future ones through increased understanding of and navigation through context.

Guidelines for Voice Interactions


Sample Dialogues (Prototypes)


Next Steps

This is an ongoing project and the content is continuously updated as the project shapes up. Stay tuned!