What it does
A deal-tracking product for a property investor. Deals arrive from agents, wholesalers and listing alerts. Each one gets a quick underwriting: rent and value estimates, repair budget, financing costs and the return at the asking price and at a target price. The investor moves deals across the board from new to offer to closed, and every decision keeps its numbers.
The problem
Deals came in by email, text and spreadsheets. Each analysis was a fresh copy of a workbook, so only a few deals a week got looked at properly and good ones were missed.
Approach
One underwriting model with the investor's own assumptions: vacancy, management, repairs, loan terms. Estimates come from comparable rents and sales, and every assumption can be overridden per deal. The investor decides what to offer; the board just makes every deal comparable.
- 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
- Web app
- Gemini API
- Property data and comps
- Underwriting model
Impact
Typical for systems like this.
