Towards Holistic Prompt Craft
We present an account of an ongoing practice-based Design Research programme that explores real-time AI image generation. Based on three installations, we reflect on the design of PromptJ, a user interface built around the concept of a prompt ‘mixer’. We present a series of strong concepts based on the design and deployment of PromptJ. Later, we cohere and abstract our strong concepts into the notion of Holistic Prompt Craft, which describes the importance of considering all relevant parameters concurrently. Finally, we present PromptTank, a prototype design which exemplifies these principles. Our contributions are articulated as strong concepts or intermediate knowledge, intended to be used generatively by informing and inspiring practitioners and researchers working in this space.
Research Questions / Practical Problems
Question signals indexed for this paper.
- 71%
ProtoAI: Model-Informed Prototyping for AI-Powered Interfaces
IUI '21· Generative AI (Text, Image, Music, Video) +2
- 67%
May AI? Design Ideation with Cooperative Contextual Bandits
CHI '19· Generative AI (Text, Image, Music, Video) +2
- 67%
An Analytic Model for Time Efficient Personal Hierarchies
CHI '19· User Research Methods (Interviews, Surveys, Observation) +1
- 67%
Swap: A Replacement-based Text Revision Technique for Mobile Devices
CHI '20· Context-Aware Computing +1
- 67%
The Image of the Interface: How People Use Landmarks to Develop Spatial Memory of Commands in Graphical Interfaces
CHI '21· Visualization Perception & Cognition +1
- 67%
Misty: UI Prototyping Through Interactive Conceptual Blending
CHI '25· Knowledge Worker Tools & Workflows +1
- 67%
TableCanoniser: Interactive Grammar-Powered Transformation of Messy, Non-Relational Tables to Canonical Tables
CHI '25· Interactive Data Visualization +1
- 67%
Generative AI in User Experience Design and Research: How Do UX Practitioners, Teams, and Companies Use GenAI in Industry?
DIS '24· Generative AI (Text, Image, Music, Video) +2
- 67%
Show of Hands: Leveraging Hand Gestural Cues in Virtual Meetings for Intelligent Impromptu Polling Interactions
IUI '22· Hand Gesture Recognition +1
- 67%
PDFChatAnnotator: A Human-LLM Collaborative Multi-Modal Data Annotation Tool for PDF-Format Catalogs
IUI '24· Human-LLM Collaboration +1
Based on Jaccard similarity of research subtopics & professions (≥60%)