AI for Real Estate: Property Analysis, Cadastre, and Valuation with Junyr
How Junyr Suite's operational real estate module (its 2nd live sector) uses French public data (DVF, DPE, cadastre) to power AI-driven property analysis, valuation, and listing comparison through Junyr Agents.
AI for Real Estate: Property Analysis, Cadastre, and Valuation with Junyr
In short — Junyr Suite ships a dedicated, operational real estate module (its 2nd live sector) that turns French open data (DVF, DPE, cadastre, geocoding) into structured property analysis, valuation, and listing comparison your Junyr Agents can run — exposed at /api/sectors/real_estate/ with a PropertyAnalysisTab in the CRM hub.
The real estate industry generates massive volumes of data: online listings, DVF transactions, energy diagnostics, cadastral records, geolocation data. Junyr Suite offers a dedicated sector module to help real estate professionals harness this data through specialized Junyr Agents.
Why a Dedicated Sector Module for Real Estate?
Generic tools do not understand the specifics of the French property market:
- DPE and GES: Energy performance labels directly influence prices (up to -18% for a G-rated property)
- DVF: The Demandes de Valeurs Foncieres (public property transaction records) are a goldmine, but difficult to exploit manually
- Cadastre: Parcel and municipal data is scattered across multiple APIs
- Multiple portals: SeLoger, Leboncoin, BienIci, PAP -- each portal has its own formats and filters
Junyr centralizes these sources into a unified pipeline, accessible by your AI agents.
Sector Architecture: DDD Isolation
The real estate module is isolated using the Domain-Driven Design pattern:
backend/sectors/real_estate/
__init__.py -- Sector skeleton + get_agent_tools()
services/
analysis_service.py -- Property analysis by URL and images (Gemini Vision)
cadastre_service.py -- DVF, DPE, cadastral data (public APIs)
valuation_service.py -- Price estimation through market comparison
geocoding_service.py -- Geocoding, geographic enrichment
search_url_builder.py -- Multi-portal search URL generation
The real estate code never imports from other sectors. The core ERP runs without the sector loaded. Auto-discovery via sector_registry.py loads the module at startup.
Property Analysis
The AnalysisService extracts structured data from 8 French property portals (SeLoger, Leboncoin, PAP, BienIci, Logic-Immo, FNAIM, Orpi, Century 21).
URL-Based Analysis
- Fetch the listing page via ScrapingBee (JavaScript rendering, premium proxy)
- Extract structured data via Gemini (price, surface area, DPE, amenities)
- Enrich automatically with geographic data (geocoding, neighborhood DVF transactions)
- Save to database for history and comparison
Extracted data includes: property type, price, surface area, rooms, full location, energy performance (DPE/GES), detected amenities, contact information, and a confidence score (0 to 1).
Image-Based Analysis
The visual analysis service uses Gemini Vision to evaluate a property from photos:
- Room identification and condition assessment (score from 1 to 10)
- Amenity detection: flooring, windows, heating, storage
- Renovation estimate: estimated cost and priority repairs
- Market positioning: target buyer profile and selling points
Property Comparison
Compare up to 5 properties with a comparative table, ranking by criteria (value for money, location, potential) and an overall recommendation with confidence score.
Cadastre and Open Data Integration
The CadastreService leverages free French public APIs:
| Source | API | Data |
|---|---|---|
| DVF | api.cquest.org/dvf | Property transactions (price, surface area, date, address) |
| DPE | data.ademe.fr | Energy diagnostics (label, consumption) |
| Cadastre | cadastre.data.gouv.fr | Parcels, municipalities, boundaries |
| Geo API | geo.api.gouv.fr | Municipalities, INSEE codes, population, outlines |
DVF Market Statistics
From DVF transactions, the service computes median price, average price, price per square meter, transaction volume, and min/max range -- over the last 3 years by default.
DPE and Municipal Data
The service queries the ADEME API for DPE/GES labels, energy consumption, and zone statistics (label distribution by postal code). Via the Geo API: INSEE code, population, area, and geographic boundaries.
Price Estimation
The ValuationService produces a well-reasoned estimate in 7 steps: geocoding, DVF retrieval, DPE context, base price calculation (median price per sqm x surface area), adjustments, confidence range, and confidence level.
DPE Label Adjustments
| Label | Adjustment | Impact |
|---|---|---|
| A | +8% | Premium for high performance |
| B | +4% | Moderate premium |
| C | 0% | Baseline reference |
| D | -3% | Slight discount |
| E | -7% | Significant discount |
| F | -12% | Thermal sieve |
| G | -18% | Severe thermal sieve |
Other Factors
| Factor | Examples | Cap |
|---|---|---|
| Property condition | Excellent (+10%), good (0%), fair (-8%), poor (-18%) | N/A |
| Amenities | Pool (+5%), garden (+3%), sea view (+8%), parking (+2%) | +25% max |
| Layout | Studio (+10% per sqm), small rooms (-5%), large rooms (+5%) | N/A |
The service also identifies comparable properties (similarity score based on surface area, distance, and rooms) and computes market trends over 5 years.
Geocoding and Geographic Enrichment
The GeocodingService provides forward and reverse geocoding (Google Maps API), with database caching to reduce costs.
For each property, geographic enrichment analyzes the surrounding area (1 km radius):
| Category | Location Types |
|---|---|
| Schools | Primary schools, universities |
| Transport | Metro, bus, train station, tram |
| Healthcare | Hospitals, pharmacies |
| Shopping | Supermarkets, shopping centers |
| Leisure | Parks, gyms |
An estimated walkability score (0-100) is calculated from the detected amenities.
Search URL Generator
The SearchURLBuilder generates optimized search URLs for Leboncoin, SeLoger, and BienIci with 50+ criteria (outdoor features, view, interior, kitchen, heating, etc.), automatic budget expansion (50% below to 25% above), sort by date, and 45+ major cities pre-configured.
Integration with the Junyr ERP
Pipeline
Listing detected (portal or email)
-> Automatic analysis (URL + images)
-> Prospect created (Commercial module)
-> Valuation generated (DVF + DPE + geo)
-> Project created (Production module)
-> Follow-ups and reminders (Commercial module)
-> Transaction / Invoicing (Finances module)
| ERP Module | Real Estate Usage |
|---|---|
| Commercial | Buyer/seller prospects, follow-ups, sales pipeline |
| Production | Sale projects, rental projects, mandate tracking |
| Finances | Fee invoicing, cash flow tracking |
| HR | Real estate agents (human) and Junyr Agents on the same team |
The Role of Junyr Agents
A Junyr Agent configured for the real estate sector can:
- Receive an email from a prospect ("I'm looking for a 3-bedroom apartment in Lyon, budget 300k, DPE C minimum")
- Generate search URLs on Leboncoin, SeLoger, and BienIci
- Analyze the listings found (structured data extraction)
- Estimate prices (DVF comparison, DPE and amenity adjustments)
- Compare properties and rank by relevance
- Respond to the prospect with a well-reasoned selection
AI Tools
| Tool | Function |
|---|---|
analyze_property_url | Analyze a listing from its URL |
analyze_property_images | Visual evaluation from photos |
get_dvf_transactions | DVF transactions for a given area |
estimate_property_value | Price estimation with detailed methodology |
search_real_estate | Multi-portal search URL generation |
get_nearby_amenities | Nearby amenities and services |
These tools are dynamically injected into the agent context via sector_registry.py, only for companies configured in the immobilier (real estate) sector.
Current Status and Roadmap
What Exists (Backend)
| Service | Status |
|---|---|
AnalysisService | Code complete, powering the live property analysis |
CadastreService | Code complete, APIs connected |
ValuationService | Code complete, algorithm functional |
GeocodingService | Code complete, database caching |
SearchURLBuilder | Code complete, 3 portals |
What Has Shipped
| Component | Status |
|---|---|
| Sector router | Shipped -- endpoints exposed at /api/sectors/real_estate/ |
| LLM tools | Shipped -- agent_tools.py injects the tools into your Junyr Agents |
| Frontend | Shipped -- PropertyAnalysisTab in the CRM hub |
Real estate became Junyr Suite's 2nd operational sector on 23 June 2026.
Roadmap
- Email-to-task automation: automatic analysis of listings received by email, with no manual step
- Continuous enrichment: more portals, search criteria, and valuation factors as field feedback comes in
Early Adopter Program
The real estate module is operational. We help real estate professionals configure their workflows and get the most out of the sector:
- Configure workflows: automated listing analysis, valuation, and mandate tracking
- Calibrate valuations: compare with your local market knowledge
- Connect your accounts: centralize emails, prospects, and documents in the CRM hub
What You Get Today
Alongside the real estate module, Junyr Suite offers professionals an inbox-first, sovereign business suite:
- Full 8-module ERP (commercial, production, finances, HR, and more)
- Junyr Agents to automate emails, tasks, and follow-ups
- Inbox-first workspace with a Morning Briefing and the Ask Junyr assistant to centralize emails, documents, and datasets
- Entity-graph CRM and sales pipeline to track prospects and mandates
- Invoicing with PDF generation and payment tracking
- European data sovereignty — your own local LLM, three confidentiality tiers, and optional On-Prem self-hosting
See the pricing (all-included, no add-ons, billed monthly or annually) for what is bundled by default.
Summary
| Component | Status | Description |
|---|---|---|
| Property analysis | Backend ready | Extraction from 8 portals + visual analysis |
| Cadastre / DVF / DPE | Backend ready | French public APIs integrated |
| Price estimation | Backend ready | Multi-factor algorithm with confidence range |
| Geocoding | Backend ready | Address resolution + geographic enrichment |
| Search URLs | Backend ready | Multi-portal generation, 50+ criteria |
| API router | Operational | /api/sectors/real_estate/ exposed |
| Frontend interface | Operational | PropertyAnalysisTab in the CRM hub |
| LLM tools | Operational | injected into the sector's Junyr Agents |
Junyr Suite's real estate module rests on solid foundations -- five complete backend services representing over 2,600 lines of code -- powered by French public data, now exposed at /api/sectors/real_estate/ and accessible by your Junyr Agents to automate property analysis, valuation, and tracking.
Interested in the early adopter program? Contact us to learn more, or read our real estate agency AI transformation case study.
FAQ
Is the Junyr Suite real estate module available today?
Yes. As of June 2026 the real estate sector is live (Junyr's 2nd operational sector): the sector router (/api/sectors/real_estate/), the Junyr Agent tools, and a PropertyAnalysisTab in the CRM hub are all shipped, on top of the five backend services. AI is gated on your confidentiality tier.
What French data sources does Junyr Suite use for property valuation?
It draws on free French public APIs: DVF (public property transaction records) for comparable sales, ADEME for DPE/GES energy diagnostics, the cadastre for parcels and boundaries, and the Geo API for INSEE codes and municipal data. The valuation algorithm combines median price per square meter with DPE, condition, amenity, and layout adjustments to produce an estimate with a confidence range.
Is my real estate data kept private and sovereign?
Yes. Junyr Suite is a sovereign, European-hosted AI suite. You can route AI on your own bring-your-own local LLM so data stays on your hardware, choose between three confidentiality tiers (Simple, Sécurisée, Totale), and Enterprise customers can self-host On-Prem. Migrating your existing inbox from Gmail or Outlook is supported via the OAuth IMAP Migration Wizard.
How much does Junyr Suite cost?
The Junyr Société plan is all-included with one user, the full 8-module ERP, and 30 GB of storage; additional users (human or Junyr Agent) are billed per seat, and Enterprise is on quote. Annual billing saves 15% and there is no commitment. See the pricing page for current details.
Junyr Team
AI Platform Team
The Junyr team builds AI workforce tools that help European SMEs recruit, train, and manage autonomous AI agents for everyday business tasks.
Related Articles
Industry-Specific AI Solutions: How the Junyr Suite Adapts Its Junyr Agents to Your Business
How the Junyr Suite combines a shared 8-module ERP foundation with strictly-isolated, industry-specific sector modules driven by Junyr Agents — sovereign by design.
Read article →Coming Soon: Creative Studios and Professional Training on the Junyr Suite
A roadmap article: the Creative Studios and Professional Training sectors are still skeletons in the design phase on the Junyr Suite — not yet operational. It explains what is planned, what generic features (8-module ERP, Junyr Agents, sovereign webmail) you can use today, and how to help shape these modules, pointing to the operational Real Estate sector as the shipped example.
Read article →How a Real Estate Agency Saved 40% of Admin Time with AI
A real estate case study: how a 12-person agency deployed three Junyr Agents on the sovereign Junyr Suite in 28 days and freed 40% of its sales team's admin time — without hiring or changing its CRM.
Read article →