BeautyGuard: Designing a Multi-Agent Roundtable System for Proactive Beauty Tech Compliance through Stakeholder Collaboration

2025-11-16

AI Summary

To address the lagging, reactive, and fragmented legal, ethical, and reputational compliance review in generative AI applications within the beauty-tech domain, this paper proposes a large language model–based multi-agent “roundtable” system. The system orchestrates role-specialized agents—compliance checker, precedent retriever, legal interpreter, and risk mitigator—to enable proactive, interpretable human-AI collaborative review. Innovatively, it maps organizational structures onto the agent architecture to preserve tacit knowledge, prioritizing information augmentation over decision substitution. Evaluated by domain experts, the prototype achieves a System Usability Scale (SUS) score of 77.5, indicating low cognitive load and significantly enhanced usability and collaborative efficiency. This work establishes a scalable, auditable technical paradigm for AI compliance governance.

Technology Category

• Humans and AI: User Experience and Usability
• Philosophy and Ethics of AI: AI & Law, Justice, Regulation & Governance
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Agentic search

Abstract

As generative AI enters enterprise workflows, ensuring compliance with legal, ethical, and reputational standards becomes a pressing challenge. In beauty tech, where biometric and personal data are central, traditional reviews are often manual, fragmented, and reactive. To examine these challenges, we conducted a formative study with six experts (four IT managers, two legal managers) at a multinational beauty company. The study revealed pain points in rule checking, precedent use, and the lack of proactive guidance. Motivated by these findings, we designed a multi-agent "roundtable" system powered by a large language model. The system assigns role-specialized agents for legal interpretation, checklist review, precedent search, and risk mitigation, synthesizing their perspectives into structured compliance advice. We evaluated the prototype with the same experts using System Usability Scale(SUS), The Official NASA Task Load Index(NASA-TLX), and interviews. Results show exceptional usability (SUS: 77.5/100) and minimal cognitive workload, with three key findings: (1) multi-agent systems can preserve tacit knowledge into standardized workflows, (2) information augmentation achieves higher acceptance than decision automation, and (3) successful enterprise AI should mirror organizational structures. This work contributes design principles for human-AI collaboration in compliance review, with broader implications for regulated industries beyond beauty tech.

Problem

• Ensuring compliance with legal, ethical, and reputational standards in beauty tech
• Addressing manual, fragmented, and reactive traditional compliance review processes
• Designing multi-agent systems for structured compliance advice through stakeholder collaboration

Innovation

• Multi-agent roundtable system using large language model
• Role-specialized agents for legal and compliance tasks
• Synthesizes multiple perspectives into structured compliance advice