Back to Hackathon Showcase

Third PrizePrize: ¥500#58
KnowledgeFlow Multi-Agent Content Creation Platform
KnowledgeFlow is a multi-agent collaboration system focused on content creation scenarios, solving the full workflow of: information collection, information sedimentation, content creation, and conten...
About the Creator
I'm Dong Hao, AI application development engineer, focusing on multi-Agent systems and content generation applications. Implemented a multi-Agent content creation platform in this Hackathon, exploring Agent collaboration mechanisms and task decomposition methods. Long-term investment in Agent architecture design and AI application engineering practices.
Project Description
KnowledgeFlow is a multi-agent collaboration system focused on content creation scenarios, solving the full workflow of: information collection, information sedimentation, content creation, and content review. 1. Information Collection: RSS Agent captures on schedule or manual Web Scraping Agent collects interesting news, through automated AI processing: Knowledge Summary Agent, Knowledge Classification Agent, knowledge storage, sedimenting into knowledge base. 2. AI Creation: When user inputs a topic, a. Knowledge Linkage: AI Creation Coordinator Agent retrieves similar info from knowledge base, b. Human-Machine Interaction: Outline Writing Agent drafts different directions for user decision, c. AI Creation: Article Writing Agent writes appropriate direction articles, d. AI Review: Three reviewers (AI Flavor Review Agent, Prohibited Words Review Agent, Public Opinion Review Agent) jointly score and iteratively optimize content.
Technical Solution
Created 10 Agents total, including information collection, information processing, content creation, and content review categories. Mods used: messaging, channel, wiki. Driving methods: event-driven, scheduled. Communication methods: agent-human collaboration, agent-agent collaboration, human-human wiki collaboration.
Features
Information Collection Layer: 1. Article Scraping Agent (manual input, event-driven) 2. RSS Collection Agent (scheduled trigger). Information Processing Layer: 1. Content Summary Agent (workflow, event-driven after new knowledge) 2. Content Classification Agent (workflow, event-driven after new knowledge). Agent Collaboration Layer: Creation Commander Agent (chief commander, handles human interaction and agent communication). Content Creation Layer: 1. Outline Writing Agent 2. Content Creation Agent. Content Review Layer: 1. AI Flavor Review Agent 2. Prohibited Words Review Agent 3. Public Opinion Review Agent.
Inspired by this project?
Build your own multi-agent system with OpenAgents. Join the community and start creating today.