I Built a Multi-Agent AI Team to Run My Father's Business — Here's the Architecture

说明与用途

基于开源工具的多智能体 AI 系统自动化小型企业运营，客户查询在 30 秒内完成，仅在关键决策时需要人工干预。

问题

The father’s small business was overwhelmed with repetitive tasks such as answering customer questions, managing social media, updating product listings, tracking orders, and reviewing Google Business Profile comments.

结果

The AI team processes a customer inquiry in under 30 seconds, with live status and task queues visible on a dashboard, and requires human intervention only for escalations or approvals.

工作流

• Detect new customer inquiry
• Friday drafts response
• Kodi assigns Stark to review technical details
• Stark approves and merges PR if needed
• Friday sends response
• Edith logs interaction for follow‑up

证据

I built an AI team that runs my father's business. Not a chatbot, not a single agent, but a team of specialized AI agents that handle operations, content, customer support, code, and analytics.

来源

All coordinated through a central task system. All running on open-source AI.

来源

The system runs on a local server. Here's what it looks like in action: → New customer inquiry detected → Friday picks it up, drafts a response → Kodi assigns Stark to review the technical details → Stark approves, Friday sends the response → Edith logs the interaction for follow-up → All of this happens in under 30 seconds

来源

Agents don't talk to each other directly. They communicate through a shared SQLite database, a single source of truth for: Task assignments and status, Agent availability and current work, Approval workflows, Event history

来源