I built a private AI job-intake assistant for a friend's electrical business

说明与用途

为一家电气服务公司构建了本地 AI 接口助手，使用开源模型处理混乱的客户请求，生成摘要、紧急程度、后续问题和草稿回复，并将所有数据保存在所有者的笔记本电脑上。

问题

Customers send messy requests to an electrical services owner, who must manually parse and respond, leading to inefficiency and risk of missing critical details.

结果

The system reduces manual effort, ensures emergency warnings are flagged, prevents fabricated pricing, and keeps customer data offline.

工作流

• 1. Customer submits request via public form on the showcase site.
• 2. Form forwards the message to the owner’s WhatsApp.
• 3. Owner pastes the message into the local AI intake assistant.
• 4. The assistant runs an open‑weight model (e.g., qwen2.5:1.5b) via Ollama.
• 5. The model generates a one‑line summary, urgency flag, follow‑up questions, and a draft reply.
• 6. Owner reviews and sends the reply to the customer.

证据

Customers message him all day with requests like rewiring damaged buildings, rewinding pump coils, faulty switches, flat wiring, solar and CCTV, burnt wires, urgent equipment repairs, and ATS and contactor prices.

来源

I built a showcase site where a form sends each request to his WhatsApp, plus a private AI intake assistant on his laptop.

来源

Runs an open‑weight model locally with Ollama and turns messy customer messages into a clean job summary, urgency level, follow‑up questions and a draft reply.

来源

Customer names, addresses and phone numbers stay on the owner's computer.

来源