Designing for Trust

Trust can be thought of as one of the currencies that humans

use to accept a technology in their everyday lives. One of those

technologies are conversational agents (also known as chatbots)

like digital assistants in our smartphones. To provide a more

personal experience, increasing number of businesses are

developing virtual agents with conversational interfaces by

personifying their products and services through automation.

While some agents are generalists like voice-based personal

assistants, many of them are specialist agents that are designed for

specific tasks in different domains including e-commerce. As user

expectations get more complex each day, a collaboration between

specialist agents is needed. In such a scenario, users’ trust level

may change dynamically due to the agent hand-offs. Additionally,

despite many offered benefits, many people hesitate to trust

conversational agents with complex tasks in certain e-commerce

scenarios such as travel booking.

This design research project explores trust issues with virtual

e-commerce agents in several collaboration scenarios between

generalist and specialist agents and provides design guidelines for

more trustworthy conversational agents.