Users adapt existing workflow patterns to create custom features in an AI email system via conversation, turning the inbox into a user-shaped flexible data layer while managing risks like mis-specified behavior through ongoing oversight.
Title resolution pending
6 Pith papers cite this work, alongside 1,419 external citations. Polarity classification is still indexing.
6
Pith papers citing it
1,419
external citations · external index
citation-role summary
background 3
method 1
citation-polarity summary
fields
cs.HC 6years
2026 6verdicts
UNVERDICTED 6representative citing papers
Mixed-Initiative Context reconceptualizes interaction context as a dynamic, jointly manageable structure that humans and AI can actively organize according to task needs.
Concurrent human-agent interactions occur in 31.8% of turns and follow five action patterns explained by six triggers and four enabling factors, enabled by a context-aware design probe called CLEO.
A preliminary participatory design study identifies design opportunities for proactive mixed reality information support to enhance engagement in in-person small-group conversations.
PSI uses a shared personal-context bus to publish state and write-back affordances, turning isolated AI-generated modules into synchronized, chat-accessible instruments.
Smart glasses expand independent visual access for BLV participants in mixed-vision groups, supporting inclusive collaboration while sighted participants express uncertainty about adapting their helping behaviors.
citing papers explorer
-
Conversational Customization of Productivity Systems: A Design Probe of Malleable AI Interfaces
Users adapt existing workflow patterns to create custom features in an AI email system via conversation, turning the inbox into a user-shaped flexible data layer while managing risks like mis-specified behavior through ongoing oversight.
-
Mixed-Initiative Context: Structuring and Managing Context for Human-AI Collaboration
Mixed-Initiative Context reconceptualizes interaction context as a dynamic, jointly manageable structure that humans and AI can actively organize according to task needs.
-
"When to Hand Off, When to Work Together": Expanding Human-Agent Co-Creative Collaboration through Concurrent Interaction
Concurrent human-agent interactions occur in 31.8% of turns and follow five action patterns explained by six triggers and four enabling factors, enabled by a context-aware design probe called CLEO.
-
Exploring Needs and Design Opportunities for Proactive Information Support in In-Person Small-Group Conversations
A preliminary participatory design study identifies design opportunities for proactive mixed reality information support to enhance engagement in in-person small-group conversations.
-
PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents
PSI uses a shared personal-context bus to publish state and write-back affordances, turning isolated AI-generated modules into synchronized, chat-accessible instruments.
-
Reshaping Inclusive Interpersonal Dynamics through Smart Glasses in Mixed-Vision Social Activities
Smart glasses expand independent visual access for BLV participants in mixed-vision groups, supporting inclusive collaboration while sighted participants express uncertainty about adapting their helping behaviors.