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

Описание и применение

Создано локальное решение на базе открытой модели, которое обрабатывает запросы клиентов электросервисной компании, генерируя сводку, уровень срочности и черновой ответ, сохраняя данные на ноутбуке владельца.

Задача

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

Результат

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

Рабочий процесс

• 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.

Доказательства

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.

Источник

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

Источник

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.

Источник

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

Источник