Design Generative AI for Practitioners: Exploring Interaction Approaches Aligned with Creative Practice

2026-03-03

AI Summary

This work addresses the misalignment between conventional generative AI interaction paradigms—such as prompt-based or global image editing—and the nonlinear, visually driven workflows of designers, which often leads to outputs that deviate from intended design goals. To bridge this gap, the paper introduces three novel human-AI interaction methods—DesignPrompt, FusAIn, and DesignTrace—that distribute control across stages of intent articulation, input construction, and generation, enabling designers to dynamically steer AI behavior. It reconceptualizes AI alignment as a dynamic negotiation process, flexibly assigning the AI an active or passive role based on the creative phase and whether the tool serves instrumental or inspirational purposes. Grounded in HCI design, generative AI, and creative cognition theories, the implemented prototype demonstrates that this distributed control paradigm significantly enhances designers’ agency over generative outcomes and improves creative fluency, thereby facilitating deeper integration of generative AI into professional design workflows.

Technology Category

• Humans and AI: Interaction Techniques and Devices
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Design is a non-linear, reflective process in which practitioners engage with visual, semantic, and other expressive materials to explore, iterate, and refine ideas. As Generative AI (GenAI) becomes integrated into professional design practice, traditional interaction approaches focusing on prompts or whole-image manipulation can misalign AI output with designers' intent, forcing visual thinkers into verbal reasoning or post-hoc adjustments. We present three interaction approaches from DesignPrompt, FusAIn, and DesignTrace that distribute control across intent, input, and process, enabling designers to guide AI alignment at different stages of interaction. We further argue that alignment is a dynamic negotiation, with AI adopting proactive or reactive roles according to designers' instrumental and inspirational needs and the creative stage.

Problem

• Generative AI
• design practice
• human-AI interaction
• creative process
• intent alignment

Innovation

• Generative AI
• design practice
• interaction design
• intent alignment
• creative process