The AI-Powered Classifieds Stack That Posts in Seconds

24ad.info has deployed an AI-powered classifieds stack that processes photo uploads, generates listing details, and posts ads in seconds. The system uses OpenRouter and Gemini 2.5 Flash for vision processing, assigns categories through keyword matching and AI classification, and produces multilingual output with i18n keys. The stack achieves low median ad creation time with parallel AI requests, fallback caching, and subdomain-based location locking.

The AI-Powered Classifieds Stack That Posts in Seconds Users can upload a photo to 24ad.info https://24ad.info . AI assists with the listing details. The ad goes live before any manual steps are complete. Here's how the stack works. The Pipeline 1. Vision Processing OpenRouter + Gemini 2.5 Flash When you upload photos: Key observations: - Processes images quickly - Handles mixed content - Price suggestions draw on available data 2. Category Assignment The system first tries keyword matching. If uncertain, it queries the classification options. Two clever bits: - Dormant category reactivation - Instead of creating duplicate categories, it finds and revives inactive ones - Custom field generation - For categories like Cars, AI suggests relevant fields 3. Multilingual Output Using the same call flow, translations are generated. The response lands in our locales/ directory with i18n keys. The Stack That Makes It Possible Frontend - React 19 + Vite 7 - For the instant form updates - shadcn/ui - Pre-built components with Tailwind - wouter v3 - Lightweight routing no React Router bloat Critical UX details: - File upload starts analysis during selection - Price/category suggestions appear as editable previews - Location auto-fills from browser geolocation or IP Backend - tRPC v11 - Keeps frontend/backend types in sync - Drizzle ORM - For type-safe MySQL queries - Express 4 - Handles the traffic types: - User requests API/SSR - Googlebot HTML injection - Health checks /api/system-health Infrastructure - Caddy v2 - Wildcard subdomains with HSTS - PM2 cluster mode with 4 instances - load-balanced - MariaDB - Heavily indexed for search title, location, price Pain Points We Solved 1. AI Latency Initial versions waited for all AI steps sequentially. Now: - Parallel processing - Fire all AI requests simultaneously - Fallback caching - Common items use template descriptions if needed 2. Location Handling Early users saw unexpected placement. Fixed by: - Subdomain locking - Forces location based on subdomain - Clear labels - Shows target country 3. Spam Protection Current defenses include: - AI content check - Flags suspicious patterns - IP/email blacklist - Shared across country subdomains - Stripe verification - Premium ads require validated payment The Admin Toolkit Moderators get bulk tools plus: - AI banner rotator - Generates event-specific graphics - Health monitor - Checks subsystems including font rendering and upload permissions Performance Median ad creation time is low. Category handling is accurate. Lessons Learned AI isn't magic - Pricing suggestions benefit from additional rules. Condition detection - The AI spots visible details in photos. Speed matters - The entire process must fit within user attention. Try it yourself: 24ad.info https://24ad.info .