Kara is a concept for an intelligent conversational agent in ambulances. Emergency medical technicians have clear protocols to stabilize patients. The transportation aspect that causes stress. Kara augments the foresight capabilities of medics through multimodal interactions. It doesn't just give suggestions but arrives at a decision through conversation and builds trust. It shares responsibility for the ambulance and manages shift handovers to facilitate conversations across teams. It shares contextually relevant information to prepare EMTs for any situation. Kara helps EMS personnel to achieve the shared goal of effectively transporting patients to the hospital.

2016, Semester long project with Saumya K, Katherine M and Catherine S


Design a near future product, service, or solution that demonstrates value and differentiation of the Conversational User Interface (CUI) to achieve a symbiotic human-computer experience. This project was sponsored by Microsoft Design Expo 2016.


We started by framing an opportunity and territory for further investigation. We started by talking with engineers working on autonomous vehicles and quickly realized that there was a gap in how engineers perceived humans as part of the relationship of car, sensors, artificial intelligence and transport.  We wanted to explore how conversational user interfaces might make people feel comfortable in a driverless car.

We needed to narrow down the set of potential users. We wrote 12 different scenarios for 12 different user groups and concluded that emergency medical transport was a good place to design for autonomous technology, human-computer symbiosis and conversational user interfaces.


What is the role of CUI in a future with autonomous ambulances?


We met with experienced EMTs and voluntary paramedics to gain a deeper understanding of what happens within an ambulance. We designed a workshop with 5 parts

1. Tour of the ambulance - The EMTs talked about their pain points. Being inside an ambulance and we realized that there was tremendous opportunity in designing the interface between the car and human driver even without it being autonomous. A lot of the human factors problems could be overcome with a smart conversational interface.

2. Make a collage representing your ideal partner - To understand how the symbiosis between human and computer could be designed.

3. Create a journey map of a typical call - What the existing gaps in the process are.

4. Role play your last call and create a flexible model the things you interacted with - We wanted to see if the process always played out as neatly as the journey map expressed.

5. Debrief - This was an informal question and answer session where we brainstormed ideas with the participants



How can we improve the front-of-ambulance transport experience by designing an intelligent conversational user interface? 


We spent 16 hours in ride-alongs inside ambulances with EMTs. We gained a more empathetic understanding of their struggles, stresses and coping mechanisms. Based on this and the themes we had identified previously, we created 12 storyboards for concepts. These were meant as provocations since we wanted to elicit strong responses to the needs we had identified. We found that they didn't want to directly deal with their stress but that we would have to alleviate them through other approaches in our design.


We developed a Wizard of Oz style of prototyping 3 different scenarios with 15 touchpoints to test the relevance and authenticity of the concepts, the forms of multi-modal feedback and how they would use a system like this individually, in pairs and across the larger organization of the EMS. 


We narrowed our design principles to three main ones supported by various heuristics. Kara embodies a symbiotic relationship through co-action. Through shared logic, memory, and responsibility within an ambulance, Kara helps EMS personnel to by managing the unknown risks and stresses they face.


Kara’s unique capability of sharing logic, memory, and responsibility with EMS personnel alleviates unnecessary stresses and prevents worst case outcomes. Through a multi-modal, primarily conversational interface, Kara contributes to emergency transportation task-based problem-solving with real-time contextually relevant information provided through hands-free, eyes-free means.


© 2020 by Shruti Aditya Chowdhury