What it does
A screening automation for a property management firm. Each applicant gets a checklist link for ID, income proof and references. Documents are read as they arrive, missing or unclear ones are asked for again, and the agreed checks run: income against rent, ID matching the application, references answered. The property manager sees one summary and decides; the lease or a polite decline goes out from there.
The problem
Collecting documents over email and WhatsApp, then checking them by hand, took days per applicant, and good tenants signed elsewhere while the paperwork was chased.
Approach
The checklist is the same for every applicant, which keeps screening fair and consistent. AI reads payslips, bank statements and IDs into fields; rules apply the firm's own criteria. No one is approved or declined automatically: the property manager makes every decision, with the reasons on screen.
- 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
- Document reading (Gemini API)
- Applicant portal
- Rule checks
- E-signature
Impact
Typical for systems like this.
