CritiqueCrew: Orchestrating Multi-Perspective Conversational Design Critique
Xiaojiao Chen, Jiahuan Zhou, Yunfeng Shu, Ruihan Wang, Qinghua Liu
Abstract
UI designers face growing cognitive load and cross-functional friction at the intersection of user needs, business goals, and engineering constraints. Existing automated tools often deliver static “problem lists,” lacking actionable repair paths and disrupting creative flow. We introduce CritiqueCrew, a Figma tool that supports designers through conversational critique. CritiqueCrew generates multi-faceted insights by implementing a multi-perspective orchestration of distinct expert roles (UX, PM, Engineer). It translates abstract critiques into concrete actions via in-context feedback and interactive remediation. Across two independent controlled studies (Total N = 48), CritiqueCrew significantly improved both design quality and subjective experience compared to a traditional static checker. Furthermore, our results confirm that the structured orchestration of expert roles—rather than a unified model—is key to fostering trust and creativity support. Our work demonstrates how AI can shift from a “problem auditor” to a “solution co-creator” by integrating multi-perspective dialogue with interactive repair, offering design implications for future creative tools.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext c07ed5fd-f44e-46ab-a3d8-cc8ecfc130ebBuilds on12
- Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
- Generating Automatic Feedback on UI Mockups with Large Language ModelsPeitong Duan, Jeremy Warner, Yang Li, Bjoern HartmannCHI 2024 · 81 citations
- GUIComp: A GUI Design Assistant with Real-Time, Multi-Faceted FeedbackChunggi Lee, Sanghoon Kim, Dongyun Han, Hongjun Yang et al.CHI 2020 · 61 citations
- SimUser: Generating Usability Feedback by Simulating Various Users Interacting with Mobile ApplicationsWei Xiang, Hanfei Zhu, Suqi Lou, Xinli Chen et al.CHI 2024 · 49 citations
- Don't Do That! Hunting Down Visual Design Smells in Complex UIs against Design GuidelinesBo Yang, Zhenchang Xing, Xin Xia, Chunyang Chen et al.ICSE 2021 · 47 citations
Related papers
- Co-Constructed or Constrained? How AI Collaboration Tools Reshape UI Design Practice in a Time-Boxed Design ChallengeCharlotte Kobiella, Lukas Schneider, Albrecht Schmidt, Nada TerzimehicCHI 2026 · 1 citation
- Criticmate: Stagewise Human-AI Co-Critique in Single-Screen UI EvaluationJisu Ko, Jinyoung Choi, Cielo Morales, Dajung Kim et al.CHI 2026 · 1 citation
- Closing the Loop between User Stories and GUI Prototypes: An LLM-Based Assistant for Cross-Functional Integration in Software DevelopmentFelix Kretzer, Kristian Kolthoff, Christian Bartelt, Simone Paolo Ponzetto et al.CHI 2025 · 18 citations
- Cognitive Bridge: AI-Generated Boundary Objects for Cross-Functional CollaborationTamil Selvan Gunasekaran, Sophia Lim, Kunal Gupta, Huidong Bai et al.CHI 2026 · 1 citation
- Understanding Nonlinear Collaboration between Human and AI Agents: A Co-design Framework for Creative DesignJiayi Zhou, Renzhong Li, Junxiu Tang, Tan Tang et al.CHI 2024 · 100 citations
