Designing systems and services with AI functionality as part of a care experience presents a range of challenges and opportunities. Limitations with sparse or missing data can make algorithmic training difficult, while the opaqueness of some black box methods muddies the process of interpreting outcomes. Human expertise and knowledge need to be carefully integrated at appropriate stages to inform both the AI approach and the fulfillment of the overall care cycle. Tackling this complex problem space requires a multidimensional and multi-stage approach integrating technical, social, medical, design and HCI knowledge. Based on our work creating therapeutic AI systems for cognitive and physical training, we propose six key system design challenges for consideration.

Personal stories encoding health information are an effective tool for promoting health behavior change. As millions of stories about health are accumulated daily in blogs and in social networks online there is an opportunity to harvest and index a large database of health stories for interventions. We envision such a database increasing user education, engagement, motivation and rapport in our conversational agent-based health intervention systems. In this paper we propose a model of indexing health stories based on health behavior change theory, enhanced demographics and quality metrics.

A long-standing dream of artificial intelligence has been to put commonsense knowledge into computers -- enabling machines to reason about everyday life. However, it is widely assumed that the use of common sense in interactive applications will remain impractical for years, until these collections can be considered sufficiently complete and commonsense reasoning sufficiently robust. Recently, at the Massachusetts Institute of Technology's Media Laboratory, we have had some success in applying commonsense knowledge in a number of intelligent interface agents, despite the admittedly spotty coverage and unreliable inference of today's commonsense knowledge systems.

A long-standing dream of artificial intelligence has been to put commonsense knowledge into computers -- enabling machines to reason about everyday life. Some projects, such as Cyc, have begun to amass large collections of such knowledge. However, it is widely assumed that the use of common sense in interactive applications will remain impractical for years, until these collections can be considered sufficiently complete and commonsense reasoning sufficiently robust. Recently, at the Massachusetts Institute of Technology's Media Laboratory, we have had some success in applying commonsense knowledge in a number of intelligent interface agents, despite the admittedly spotty coverage and unreliable inference of today's commonsense knowledge systems. This article surveys several of these applications and reflects on interface design principles that enable successful use of commonsense knowledge.