Classify & extract data from floorplans with Mistral AI OCR & JigsawStack

🌊 What it Does

This workflow automatically classifies uploaded files (PDFs or images) as floorplans or non‑floorplans. It filters out junk files, then analyzes valid floorplans to extract room sizes and measurements.

👥 Who it’s For

Built for real estate platforms, property managers, and automation builders who need a trustworthy way to detect invalid uploads while quickly turning true floorplans into structured, reusable data.

⚙️ How it Works

1. User uploads a file (PDF, JPG, PNG, etc.).
2. Workflow routes the file based on type for specialized processing.
3. A two‑layer quality check is applied using heuristics and AI classification.
4. A confidence score determines if the file is a valid floorplan.
5. Valid floorplans are passed to a powerful OCR/AI for deep analysis.
6. Results are returned as JSON and a user-friendly HTML table.

🧠 The Technology Behind the Demo

This MVP is a glimpse into a more advanced commercial system. It runs on a custom n8n workflow that leverages Mistral AI's latest OCR technology. Here’s what makes it powerful:

• Structured Data Extraction: The AI is forced to return data in a clean, predictable JSON Schema. This isn't just text scraping; it’s a reliable data pipeline.
• Intelligent Data Enrichment: The workflow doesn't just extract data—it enriches it. A custom script automatically calculates crucial metrics like wall surface area from the floor dimensions, even using fallback estimates if needed.
• Automated Aggregation: It goes beyond individual rooms by automatically calculating totals per floor level and per room type, providing immediate, actionable insights.

While this demo shows the core classification and measurement (Step 1), the full commercial version includes Step 2 & 3 (Automated Offer Generation), currently in use by a client in the construction industry.

📋 Requirements

• Jigsaw Stack API Key
• n8n Instance
• Webhook Endpoint

🎨 Customization

Adjust thresholds, fine‑tune heuristics, or swap OCR providers to better match your business needs and downstream integrations.