AI-Instruments: Embodying Prompts as Instruments to Abstract &
Reflect Graphical Interface Commands as General-Purpose Tools
Nathalie Henry Riche, Anna Offenwanger, Frederic Gmeiner, David Brown, Hugo Romat, Michel Pahud, Nicolai Marquardt, Kori Inkpen, Ken Hinckley
Chat-based prompts respond with verbose linear-sequential texts,
making it difficult to explore and refine ambiguous intents, back
up and reinterpret, or shift directions in creative AI-assisted design
work. AI-Instruments instead embody “prompts” as interface objects
via three key principles: (1) Reification of user-intent as reusable
direct-manipulation instruments; (2) Reflection of multiple interpre-
tations of ambiguous user-intents (Reflection-in-intent) as well as
the range of AI-model responses (Reflection-in-response) to inform
design "moves" towards a desired result; and (3) Grounding to in-
stantiate an instrument from an example, result, or extrapolation
directly from another instrument. Further, AI-Instruments leverage
LLM’s to suggest, vary, and refine new instruments, enabling a
system that goes beyond hard-coded functionality by generating
its own instrumental controls from content. We demonstrate four
technology probes, applied to image generation, and qualitative
insights from twelve participants, showing how AI-Instruments
address challenges of intent formulation, steering via direct manip-
ulation, and non-linear iterative workflows to reflect and resolve
ambiguous intents.