Responsibilities
Product design
Experience design
AI Hardware
LLM integration
Product design
Experience design
AI Hardware
LLM integration
CLIENT
Social events, medical situations, and individuals who want to date more efficiently and learn from their experiences
DURATION
4 months
Social events, medical situations, and individuals who want to date more efficiently and learn from their experiences
DURATION
4 months
AI Conversation Feedback + Reflection Device
Project summary: This tabletop device is a creative research object exploring the imbalance in romantic conversation. It was inspired by common dating app experiences, particularly on Hinge, where people often leave dates feeling as if they spent the evening interviewing someone rather than engaging in an equal exchange. Votive is a physical embodiment of AI, which gives an honest reflection, qualitative and quantitative data, between 2 people, of the conversation in print.
The device listens only to the presence of voices, not their content. At the conclusion, it prints a small receipt showing the total duration of the interaction and the percentage of time each person spoke.
By turning conversational dynamics into a quiet, physical artifact, the project invites reflection on listening, reciprocity, and the distribution of attention during intimate encounters without assigning judgment or scores.
PROTOTYPING
Form 1: Hardware Configuration
Form 1: Hardware Configuration
Hardware design diagram
Prototype #1 components
PROTOTYPING
Receipt Output: Version 1
Receipt Output: Version 2
TESTING
This is a prototype to test initial assumptions about people’s interest in visualizations and AI-generated summaries of human conversations.
Proof of Concept
This is a prototype to test initial assumptions about people’s interest in visualizations and AI-generated summaries of human conversations.
V1 Software diagram
PROTOTYPING
Dynamic states: Lighting
Feedback from the proof of concept indicated an opportunity for real-time data analysis. Different light configurations were designed to represent conversational qualities and tested with users to refine them.
Dynamic states: Lighting
Feedback from the proof of concept indicated an opportunity for real-time data analysis. Different light configurations were designed to represent conversational qualities and tested with users to refine them.
PROTOTYPING
Form 2: Model redesign
Form 2: Model redesign
Hardware redesign diagram
Prototype #2 components
Receipt Information Redesign: Version 3
TESTING
Playtest Demo Day
Purpose: Staging moments for conversation between two people for feedback on the Votive object and experience
Goal: Capture feedback on what works and what doesn’t work to instruct later iterations
Playtest Demo Day
Purpose: Staging moments for conversation between two people for feedback on the Votive object and experience
Goal: Capture feedback on what works and what doesn’t work to instruct later iterations
Revisited: V3 software diagram
ADDITIONAL MATERIALS
1) Printed trifold “Question Menu.”
2) Host role-playing
3) Water service
4) Cocktail height table for Votive to exist on and participants to meet at
5) QR code printed at the end of the receipt for users to share feedback on the experience
1) Printed trifold “Question Menu.”
2) Host role-playing
3) Water service
4) Cocktail height table for Votive to exist on and participants to meet at
5) QR code printed at the end of the receipt for users to share feedback on the experience
FEEDBACK
Visual Observations
Notes were taken of what was questioned, observed, and left behind by users. These notes were separated into the experience as a whole and those directed at the object itself.
Notes were taken of what was questioned, observed, and left behind by users. These notes were separated into the experience as a whole and those directed at the object itself.
Collected participant survey #1
Participants who tested during the Playtest Demo shared their experiences and feedback on Votive and on their interactions with both the object and the other participant.
Participants who tested during the Playtest Demo shared their experiences and feedback on Votive and on their interactions with both the object and the other participant.
FURTHER FEEDBACK: Survey
Q: What about this experience worked well?
![]()
Q: What about the experience could have been better?
![]()
Q: How was the experience with the Votive during the conversation?
![]()
Q: How would you describe the quality of this conversation compared to a typical conversation with this person?
![]()
Q: Upon arrival, what did you make of the object?
![]()
Q: How would you describe the relationship you have with the person you were speaking with?
![]()
Q: Did the Votive's presence affect the conversation?
![]()
Q: Did you say anything during the conversation you would not have said otherwise?
![]()
Q: Who do you think spoke more during this session?
![]()
Q: How did you find the instructions?
![]()
OVERALL FEEDBACK + CHANGES
Improve the responsiveness of the lighting, making it reflect the status of the conversation in real time
︎︎︎
Light, “fire” responds to the conversation in 5-second intervals based on volume, amount of conversation, and which microphone is receiving more inputReceipts are fun to explore, but some of the information is not important to the participants
︎︎︎
Limit quantitative data to how much each person spoke, the number of questions asked, and include overall observations, as well as the AI’s guess to what kind of relationship the participants appear to have
The majority of groups hesitated after pressing the button
The LED of the button turns on after pressing, and the fire dances to signal that the session has started and the AI is recording
︎︎︎
The LED of the button turns on after pressing, and the fire dances to signal that the session has started and the AI is recording
The interaction between the participants and the Votive was limited
︎︎︎
After 2 minutes of conversation, have Votive print a question based on the discussion so far that could help stimulate the interaction
PROTOTYPING
The interaction between the participants and the Votive was previously only retrospective, with a large portion of the receipt dedicated to quantitative data. The interaction with the AI would only occur at the end of the meeting, which some found captured the conversation well in an artifact, but they did not feel the LLM was helping them improve their conversation beyond delivering stats and lights that reflected the meeting's tone.
Interaction with the AI
The interaction between the participants and the Votive was previously only retrospective, with a large portion of the receipt dedicated to quantitative data. The interaction with the AI would only occur at the end of the meeting, which some found captured the conversation well in an artifact, but they did not feel the LLM was helping them improve their conversation beyond delivering stats and lights that reflected the meeting's tone.
Question “slip”
Receipt Information Redesign: Version 4
Revisited: V3 Software diagram
TESTING
Version 3 Evaluation
Purpose: In a real-time test, the final iteration of this form will get feedback from participants about how Votive impacted their conversation and perspective on their relationship
Goal: Test AI interaction assumptions and capture feedback on what does and does not work for later iterations
Version 3 Evaluation
Purpose: In a real-time test, the final iteration of this form will get feedback from participants about how Votive impacted their conversation and perspective on their relationship
Goal: Test AI interaction assumptions and capture feedback on what does and does not work for later iterations
PROTOTYPING
For one test, we ran out of paper, so we moved to “printing” the question slips and receipts on a dedicated browser page that connected to the Raspberry Pi. This was a fast way to convey the changes made to Votive without compromising on the participants’ experience with the data collected.
Additional communication form tests
For one test, we ran out of paper, so we moved to “printing” the question slips and receipts on a dedicated browser page that connected to the Raspberry Pi. This was a fast way to convey the changes made to Votive without compromising on the participants’ experience with the data collected.
Related Projects ︎︎︎
Data Date
Contact for Resume
© RivesMatsonDesign
© RivesMatsonDesign