Transforming Healthcare with Conversational Agents
Innovative design principles for effective healthcare conversational agents and user experience.
Innovating Conversational Agents for Health
At Sensely, we enhance healthcare through extensive research and expert collaboration, developing conversational agents that prioritize user experience and effective evaluation methods for improved well-being.


Our Mission
Our Approach
We conduct expert interviews and trials, utilizing quantitative research methods to refine our designs and ensure our conversational agents meet the needs of diverse users in healthcare settings.
Innovative Conversational Agents
We design and evaluate conversational agents for healthcare through expert collaboration and extensive research.
Expert Interviews
Conducting interviews with medical and AI experts to shape design principles and evaluation indicators.


Prototype Development
Creating a prototype conversational agent and conducting trials with diverse user groups in healthcare settings.
Utilizing quantitative research methods to collect interaction data for effective evaluation and improvement.
Data Collection




Conversational Agents
Researching design principles for healthcare conversational agents and evaluation.


Prototype Development
Creating and testing a conversational agent for healthcare applications.




Expert Interviews
Gathering insights from medical and AI user experience experts.
Expertise and accuracy requirements
The knowledge system in the field of healthcare and welfare is huge and complex, covering many professional contents such as disease diagnosis, treatment plans, drug information, rehabilitation care, etc., and medical knowledge is updated rapidly. Dialogue agents need to accurately grasp the latest medical guidelines and clinical research results, such as new drug information approved by the US Food and Drug Administration (FDA) and disease diagnosis and treatment specifications issued by the World Health Organization (WHO). However, in actual design, it is difficult to ensure that the knowledge acquired and processed by dialogue agents is always accurate. For example, different medical literature may have different diagnostic criteria for the same disease. If the dialogue agent fails to accurately screen and integrate, it may give wrong or misleading suggestions, which directly affect the health of users.