Bandung Property AI

Pulls real-estate listings from across the Bandung market into one place, drafts Indonesian-language marketing copy automatically, and surfaces direct-from-owner properties that brokers usually bury under their own stock.

Highlights

Direct-from-owner filter surfaces negotiable stock that brokers usually bury
AI marketing copy in Indonesian saves agents hours per listing

Problem

Bandung's residential property market is scattered across multiple listing sites, brokers, and direct-from-owner channels. Buyers and agents waste hours collating listings, and direct-owner inventory buried under broker stock gets missed entirely.

Approach

Automated listing collection across 4 area-specific accounts to gather inventory from the major Bandung property portals without tripping rate limits
Direct-from-owner classifier filters out broker stock so users see negotiable inventory first
AI assistant drafts listing descriptions, price comparables, and buyer outreach in Indonesian — saves agents hours per listing
Admin panel for catalogue browsing, collection control, and AI chatbot

Stack

FastAPIPythonOpenAI GPT-4o-miniPlaywrightSQLiteTailwind

Outcome

Live admin running with active aggregation across the Bandung area
AI chatbot acts as a buyer-side property advisor over the aggregated catalogue