Client called at 11 PM: "The workflow is taking 45 SECONDS per PDF. We have 10,000 to process by Monday." Here's how I optimized it to 3 seconds (and saved the weekend): THE EMERGENCY: Law firm acquisition - needed to process 10,000 contracts by Monday morning for due diligence. Current speed: 45 seconds each = 125 hours = impossible THE DIAGNOSIS (1 hour of profiling): Where time was wasted: - PDF download: 2 seconds ✓ (fine) - Generic text extraction: 38 seconds ❌ (disaster) - Table parsing: 4 seconds ⚠️ (could improve) - Database write: 1 second ✓ (fine) The killer: Using basic extraction on 300-page contracts when we only needed 5 pages. THE SURGERY (3 AM - 5 AM): Fix #1: Intelligent Page Detection - Preview first page, find table of contents - Jump directly to signature pages and payment terms - Skip the 280 pages of boilerplate - Time saved: 35 seconds Fix #2: Parallel Processing - Split into 10 parallel n8n workflows - Each handles 1,000 documents - Load balanced across CPU cores - Time saved: 80% overall Fix #3: Better Extraction - Switched from generic to PDF Vector's LLM-enhanced mode - Understands context, not just text patterns - Handles their weird merged cells perfectly - Accuracy actually IMPROVED to 99.4% Fix #4: Caching - MD5 hash of each document - Skip if already processed - 1,100 were duplicates - Time saved: 55 minutes THE RESULT: Saturday 6 AM test run: - 10,000 contracts - Total time: 8 hours 23 minutes - Average per document: 3 seconds - Accuracy: 99.4% - Client reaction: "You're a f***ing wizard" Sunday: I slept for 14 hours THE TOOLS: - n8n with SplitInBatches for parallel processing - Redis for caching - PDF Vector API (handles huge docs without memory issues) - 1 very large coffee Lesson learned: Most "slow" workflows are doing unnecessary work. Find what you actually need and skip everything else. What's your worst performance nightmare? Let's optimize it together ⚡

Project Objective is to build a fully automated, AI-powered n8n Workflow that imports and maintains a catalog of affiliate suit products from the Awin network. This system will seamlessly integrate with Wix CMS, update products weekly, and power a stylish, filterable product discovery experience on the Search for Suits website. ✅ Deliverables 1. Automated Product Import Awin’s affiliate product feed will be processed automatically. Over 3,500+ products will be cleaned, structured, and imported into Wix CMS. 2. Smart Data Cleanup & Enrichment Use of OpenRouter AI to clean titles, descriptions, tags, and format gallery fields. Use of Browse AI to scrape missing product data (gallery images, size variants, fabric care) directly from the merchant product pages (merchant_deep_link). 3. Weekly Auto-Updates Product data (price, stock, size) will be updated every 7 days automatically. Existing products matched by productCode are updated; new ones are added. 4. Wix CMS Frontend Filtering Category pages will be powered by Wix Repeaters + Dataset filters. Users can filter by: ✅ Brand ✅ Price ✅ Fit Type ✅ Material/Tags ✅ Sizes 5. System Testing & Validation Sample products will be tested and verified in the CMS before full import. Logs and manual QA will confirm: Clean formatting Valid image galleries Functional affiliate links Accurate filtering I NEED SOMEONE WHO WILL WORK ALONGSIDE ME AND HELP ME COMPLETE THIS PROJECT. I WILL PAY FOR IT BASED ON YOUR COLLABORATION. THANKS FOR READING THROUGH.

Hi, I am using Make.com for my case, but I am open to using N8n if needed. I am creating a scenario where I will scrape product data using Browse AI from my affiliate partners' websites (my products are Suits from the UK), refine the data according to Wix CMS structure, and list products automatically. I need help structuring the data according to Wix CMS. Need help from experts in Make.com Thank you.