If Conversational Assistants Could Facilitate Human Conversation
Rich, engaging conversation is a hallmark of meaningful human-to-human interaction. However, factors such as relational closeness, social formalities, and insecurities often hinder unfamiliar individuals from going beyond the surface-level conversation.
Thinkspace is a speculative concept that aims to reinvision the role of conversational agents in discussion-based contexts.
Generative vs. Passive Agents
In our world today, much of the tools we use are passive. They do exactly what we tell them and nothing more. Current conversational agents are no different — we provide a request, and the assistant performs that action. In his TED talk, designer and engineer Maurice Conti challenges society to rebuild the passive (tech) tools we use today into “generative ones” — ones that think and create on their own.
In this project, I wanted to challenge the ‘assistant’ metaphor of voice agents. Though the main intent of CUI’s is still to help accomplish tasks, what if these agents could provide input in a way that we might not even know to ask for? In the proper context, what if human conversation can be enriched through the facilitation of a proactive assistant rather than a reactive one?
Our Mind as an Environment/Container
The visual development of Thinkspace is inspired by the manifestation of human thought as a physical entity. In any given day, people have between 50,000 to 70,000 thoughts per day (Huffington Post). Amidst the chaos, our minds form ideas through the constant rearrangement of independent thoughts. When we revisit “old ideas”, our thought process is in reality no longer the same due to the numerous contextual influences that since then have entered our lives. Following the same logic, the way our thoughts arrange themselves will always be different as time passes. And so —
“How can this conceptual model of the human mind influence us on a social level? More specifically, how can the grouping and regrouping of our thoughts act as an metaphor for the way we should engage with people that have different backgrounds, cultures, and ideas?”
Thinkspace as a product
Thinkspace is an exploration of interaction design, spatial computing, and conversational design. The goal of Thinkspace is to facilitate conversation between two or more individuals in a way that gives the group agency over what the system should do.
To wake the system, an individual invocates through voice. Thinkspace is about conversation, therefore the first point of interaction should reflect that.
From there, users decide the system’s role through a mobile interface via bluetooth connection. Every conversation has a different context and reason for initiation. Thinkspace embraces that, giving users the ability to choose the conversational assistant’s role prior to beginning the actual conversation.
This is called an intent, a user-selected mode that dictates the conversational assistant’s behavior. This system is meant to be modular in that the number of possible roles will increase as the entire Thinkspace system expands.
Though it would be quite convenient for users to verbally invoke in a similar way people say“Hey Siri” or “Alexa”, the purpose of the system is to encourage enhance human-to-human conversation, not human-to-computer conversation. Because of that, Thinkspace is designed so that no verbal exchange occurs between person & computer. And though Thinkspace is designed to live in a physical room which affords for some variation of a projected interface, the learning curve of such a foreign interaction paradigm is unnecessary.
When the group has selected a role for the system and has began conversing, Thinkspace only communicates in visual and audial cues, no spoken dialogue. The goal again is to highlight the human-to-human conversation, therefore the assistant never replies auditorily in words.
Building Prototypes
Though this project is quite conceptually driven, a large part amount of time went into the technical explroaiton of particle engines, speech-to-text dictation, and spatial projection. Using Javascript, I built an interactive voice-input sketch that models after how Thinkspace feels on an interaction level.
Prototype can be found here.
Final Concept
After roughly seven weeks of technical and conceptual exploration, I created this concept video to better communciate the vision of Thinkspace.
Project Takeaways
As time pass, so do people, their way of thinking, and the types of conversation they engage in. As people change, so does the role of Thinkspace. Working on Thinkspace was delightful as it stemmed from a genuine interest in computation, multimodal forms of interaction, and the application of metaphor thinking in design. This project pushed me to challenge the potential applications of conversational agents in foreseeable futures. This project was conducted in Carnegie Mellon School of Design’s Environments II Studio course under the supervision of Jonathan Chapman and Steve Stadelmeier.
