TANVEER HUSSAIN / AI ENGINEER
← All work Experience Certs Get in touch →
Case Study · PropTech Automation

AutoListDR

A multi-portal real estate listing automation platform. It ingests brochures, images, and video, structures them with AI into typed property records, and auto-publishes listings across multiple portals from a single trigger. Built solo, end to end.

Role: Sole Engineer & Architect Client: Real-estate group, Dominican Republic Scope: Ingestion → AI structuring → Auto-publish

[ 01 ] The business problem

The agency listed every property by hand, retyping the same details into portal after portal, each with its own multi-step wizard, login, and quirks. Slow, error-prone, and impossible to scale as inventory grew.

[ 02 ] The technical solution

One system that reads the raw media once, lets AI structure it into clean property records, then drives each portal's full publishing flow automatically. Manual distribution became a single JSON event.

// architecture

How the system works

1

Media ingestion from Nextcloud

Brochures, images, and videos land in Nextcloud and trigger the pipeline automatically, no manual upload step.

Nextcloud IntegrationEvent-DrivenData Ingestion
2

AI extraction & RAG pipeline

Each media type is parsed by the right model: OCR for PDFs, vision for images, transcription for video, then embedded for semantic search.

Mistral OCRGPT-4o VisionWhispern8nRAG
3

Structuring into typed records

An LLM turns messy extracted content into clean, typed property fields, stored once in a proyecto table so extraction never re-runs per portal.

GPT-4o-miniPostgreSQLpgvectorSchema Modeling
4

Durable orchestration

An Inngest-based execution layer coordinates the whole flow with idempotent retries, so a failure resumes cleanly instead of duplicating listings.

InngestDurable ExecutionIdempotencyRetry Logic
5

Multi-portal browser automation

Stagehand + Browserbase drive each portal's full wizard: 15 stages on Corotos, 18 steps on Mercado Libre, and a custom Facebook Marketplace flow, with captcha-tolerant logins and persistent server-side sessions.

StagehandBrowserbasePlaywrightResidential ProxiesAnti-Bot
6

Audit trail & alerts

Every publish is logged with an audit trail, and Telegram alerts report success or failure in real time.

Telegram Bot APIListing Audit TrailMonitoring
{ "event": "publish_property" }

One event, full distribution. A single JSON trigger takes a property from raw media all the way to live listings across every portal, hands-off.

// engineering depth

Hard problems solved

~ anti-bot

Surviving real portals

Residential DR proxies, persistent server-side browser context, and captcha-tolerant logins keep automated sessions alive on sites built to block them.

~ reliability

Idempotent by design

Durable execution with retry logic means a dropped step resumes without ever creating a duplicate listing, safe to re-run.

~ efficiency

Extract once, publish many

Structured data is written once into a shared table instead of re-running costly LLM extraction for every portal.

~ navigation

Per-portal wizard logic

Each portal's multi-stage publishing flow is modeled separately, 15-stage, 18-step, and custom, with image curation per platform.

~ data

Multimodal ingestion

PDFs, images, and video are each routed to the right model and unified into one clean, queryable property record.

~ ownership

Solo, full-stack

Architecture, backend, AI pipeline, browser automation, and ops, designed and shipped end to end by one engineer.

// stack

Built with

AI / LLM
OpenAI APIGPT-4o-miniGPT-4o VisionWhisperMistral OCRRAGEmbeddingspgvectorSemantic SearchPrompt Engineering
Automation / Browser
StagehandPlaywrightBrowserbaseHeadless AutomationWeb ScrapingContext PersistencereCAPTCHA HandlingResidential Proxies
Workflow / Orchestration
n8nInngestDurable ExecutionEvent-Driven ArchitectureIdempotencyRetry LogicWebhooksCron
Backend / Data
TypeScriptNode.jsPostgreSQLpgvectorHonoExpressHTTP API DesignETL PipelinesSSH Tunneling
Infra / Tooling
GitGitHubLinuxDebianDBeaverpsqlPostmanVS Code
Domain
Real Estate TechMarketplace AutomationMulti-Portal PublishingSaaS IntegrationSystem ArchitectureSolo Full-Stack
// outcome

The result

Manual → Auto
Property distribution fully automated
3+
Portals published from one trigger
1
JSON event runs the whole pipeline
100%
Designed & built solo, end to end
// let's build

Have a problem that needs a system?

I turn messy business problems into reliable AI systems, ingestion, agents, RAG, and automation, designed and shipped solo.

Tanveer Hussain · AI Engineer · Building systems that never sleep.