MockPanel

Designer with broad interests, Tongji University senior/incoming grad student, exploring Intelligent Products | Industrial Design | Cross-disciplinary studies

This project aims to build a simulated defense multi-agent system for design discipline, helping students discover issues and receive improvement suggestions from different disciplinary perspectives before formal presentations. The system uses multiple AI Agents with clear disciplinary personas (design, engineering, computer science, cross-disciplinary, etc.) to simulate real defense questioning. Different Agents ask targeted questions based on their backgrounds, while a synthesis Agent converges issues, summarizes, and provides structured modification suggestions. Core innovation: Decomposing 'design defense' - a highly contextual, confrontational process - into a collaborative multi-Agent interaction network, enabling students to optimize design logic and expression in a low-cost, iterative environment.

Planning 5-6 Agents, each corresponding to a defense role: 1. Design Committee Agent: Focuses on design logic, user experience and aesthetic expression. 2. Mechanical/Engineering Committee Agent: Focuses on structural rationality and engineering feasibility. 3. Computer/AI Committee Agent: Focuses on algorithms, system architecture and tech choices. 4. Cross-disciplinary Committee Agent: Focuses on system holism and social impact. 5. Troublemaker Agent: Raises extreme or adversarial questions. 6. Synthesis Agent: Summarizes all committee opinions, generates modification suggestions. All Agents connected through OpenAgents Network, messaging in unified channel. System based on openagents.mods.workspace.messaging for multi-Agent communication, using Agent persona, reaction mechanisms and channel messaging for natural defense flow.

Design Committee Agent: Design logic, UX and aesthetic expression. Mechanical/Engineering Committee Agent: Structural rationality and engineering feasibility. Computer/AI Committee Agent: Algorithms, system architecture and tech choices. Cross-disciplinary Committee Agent: System holism and social impact. Troublemaker Agent: Extreme or adversarial questions. Synthesis Agent: Summarizes opinions, generates modification suggestions. All Agents connected via OpenAgents Network for unified channel messaging.