What it does
A quoting pipeline for a building and interiors contractor. Enquiries from the website and WhatsApp get scope questions and a request for photos and drawings. After the site visit, measured items become a bill of quantities (BOQ). Each line is priced from the contractor's rate library, broken down into material, labour, wastage, overheads and margin, with current material prices. The estimator reviews the BOQ, the quote goes out with terms and a payment schedule, and follow-ups run until the client decides.
The problem
Each quote was built from scratch in Excel, so it took a week, rates differed between estimators, and material price changes ate the margin. Many clients signed with whoever quoted first.
Approach
One rate library holds the contractor's own build-up for each item, so every quote is priced the same way and updates when cement, steel or tile prices change. AI turns site-visit notes into BOQ lines but never sets a price. The estimator approves every quote, and lines outside the usual range are flagged for a second look.
- Input
- AI step
- Rules or code
- Person decides
- Result
Screens
Swipe sideways to see the whole screen.
Client work is shown under confidentiality agreements: no client names, and screens are recreated with sample data.
Stack
- WhatsApp and web forms
- Gemini API
- Rate library and BOQ engine
- PDF quotes
Impact
Typical for systems like this.
