An enquiry from Leboncoin that came in on Sunday evening, a listing to write before it goes live, the weekly report to send to every seller, a sale file still missing three documents… Your job happens during viewings, yet a good part of the day is spent behind a screen. At Kreante, we design custom AI solutions for real estate agencies and networks. We first take the time to understand how you work, then we build on top of your transaction software, Apimo, Hektor, Netty or another, to take over what slows your days down. Your negotiators get time back for what really closes deals: viewings, negotiation and the relationship with your clients.
265+ projects delivered in 35 countries · 4.9/5 average rating on Clutch · teams in Paris, Madrid, Miami and Lima
Does this sound like your agency?
Enquiries from SeLoger, Leboncoin or Bien’ici waiting until Monday morning, while the buyer views a property with a competitor
A phone ringing in the middle of a viewing, and messages returned too late
Seller reports written on Friday evening, when they don’t simply fall through the cracks
A well-stocked buyer database, but rarely matched against new listings
Listings to write and check for every new property, without missing a single mandatory disclosure
A spreadsheet called “Buyers_2024_DO_NOT_DELETE.xlsx” that everyone fills in their own way
According to the French Competition Authority, the average commission reached 5.78% of the sale price in 2022[1]. In other words, a buyer called back too late or a seller left without news can weigh on your revenue. Properly connected to your tools, AI can help your teams keep up the pace.
An assistant answers the enquiries that come in through your website, the portals or the phone, pins down the buyer’s project and offers a viewing slot. The next morning, your negotiator finds a complete record, ready to use.
AI prepares the listing from the property record, and from it alone. Your negotiator reviews, adjusts and publishes.
A well-informed seller is a seller who stays. AI prepares their report from the actual activity on their property, and your negotiator only has to adjust it.
Between the offer and the preliminary sale agreement, every document counts. AI keeps the list up to date and follows up with everyone at the right time.
Transaction software, portals, email, phone, e-signature… Your agency already has its tools, and some even include a little AI. The time lost is hidden between those tools, in re-keying, copy-pasting and the follow-ups your negotiators still do by hand.
| The moment | What often happens today | What AI can do |
|---|---|---|
| An enquiry arrives from a portal | It waits in an inbox before being entered into the software | Qualify it, create the record and offer a viewing slot |
| A new listing mandate is signed | The listing is written by hand and the buyer database is not checked | Prepare the listing and identify matching buyers |
| A viewing has taken place | The buyer’s feedback stays in the negotiator’s notebook | Record it and include it in the seller report |
| An offer is accepted | The file’s documents are requested one by one, by email | List the missing documents and follow up at the right time |
Our role is to build what is missing, on top of your tools, without asking your teams to change their habits. And you own the code, with no per-negotiator licence.
For a team of real estate investors based in Miami, we developed DAVCO AI. Every day, the platform:
See the DAVCO AI case studyManually sorting listings and doing the maths in spreadsheets has given way to a clear view, updated automatically.
Your clients entrust you with much more than a property: their ID, their financial situation, sometimes their complete rental application. As you know, every listing, every new client and every prospecting call is also subject to precise rules.
AI-related risks add to these. With today’s tools, one of your staff can build a small app in an afternoon, then share it with the whole agency without anyone checking who can access what. And fraudsters use AI too, to send you fake emails from sellers or notaries that look more real than the real thing, or to find the weaknesses of a poorly protected tool faster. That is why every solution we deliver is reviewed and tested by our senior developers before going live:
Your listings checked before publication, so that no mandatory disclosure is missing, such as fees or the energy rating[2]
Identity checks prepared by AI, but always approved by your teams, as part of your anti-money laundering obligations[3]
Phone follow-ups that comply with the new cold-calling rules, which since 11 August 2026 require the prior consent of private individuals[4]
Clients clearly informed when they are interacting with an AI, as required by the European regulation since 2 August 2026[5]
Callers warned when calls are recorded, with a limited retention period, in line with CNIL recommendations[6]
Your data hosted in Europe, with access rights per agency and per staff member
Before developing anything, we take the time to measure what matters: response time to buyers, reports sent to sellers, viewings arranged. You know exactly what you gain, and you track results week after week.
They keep working in their transaction software, as before. Our solution connects to it and works in the background, with no double entry and no new tool to learn.
Technology prepares, your negotiators decide. The price of a property, an offer, advice to a seller or a delicate follow-up always go through a professional. That is your expertise, and it stays that way.
One agency or twenty, one brand or several: access, rules and dashboards adapt to your organisation. And since you own the code, opening a new agency costs you no extra licence.
Free
30 minutes with an expert
Custom quote
Immersion in your agency, then a costed roadmap
Fixed price, custom quote
Scope and budget approved in writing before we start
The AI consulting engagement is described in detail on its own page.
We get to know your agency. We spend time at the front desk, with your negotiators and in property management, to understand your day-to-day between two viewings.
We take stock. Response time to buyers, seller reports, pending files: we measure your starting point.
We build your first use case. Connected to your transaction software, it is developed by our AI agents, steered and approved by our senior developers.
We test it in the field. First in one agency or with one team, while the negotiators involved are trained, then we roll it out to the rest of the network.
We review together. We compare the results with the initial baseline, and decide with you what comes next.
Challenge
Stack
Performance and payroll management platform for AutoCartel field photographers.
Challenge
The platform ingests property data daily via Zillow scraping, runs AI-driven renovation cost and ARV estimates using OpenAI, and surfaces the highest-potential deals first. Users can review…
Stack
An AI-powered real estate intelligence platform built for a Miami-based investment team. DAVCO AI replaces manual Zillow filtering and spreadsheet-based calculations with an automated map interface that displays estimated profit margins across all active single-family listings in the Miami area.
Challenge
Tango event organizers across Europe were running everything manually — registrations, confirmations, payments, check-in. They needed one purpose-built platform to manage the full event lifecycle,…
Stack
TheFlow is a web platform built for tango event organizers in Europe. Kreante evolved it across multiple phases from a basic registration tool into a complete event management and ticketing product — covering event creation, participant management, waitlists, online payments, QR check-in, automatic invoicing, and an international tango event calendar.
Challenge
Kreante developed a comprehensive platform for Pure Engagement using NoCode technologies. Built with Bubble for the frontend and Xano for the backend, this solution facilitates organizational…
Stack
Pure Engagement needed a platform capable of handling the complexity of organizational transformation, recognizing that success depends not only on structural change but also on people’s psychological and emotional transition.
Challenge
Build an iOS app that turns iPhones plus an audio interface into a complete, professional podcast recording studio, capturing high-quality sound and video across several phones at once and keeping…
Stack
A mobile app that lets creators record, sync, edit, and export podcast audio and video using a dedicated interface and multiple iPhones working together as one studio.
Challenge
Patients leaving clinic checkups with a list of medical recommendations and lab results often had no clear, practical way to turn that information into daily meals, leading to poor adherence and high…
Stack
Kreante built REMI AI, a system that reads a patient's genetic and medical test results and automatically turns them into a personalized nutrition and supplement plan that gradually evolves over several months, with clinic staff reviewing every AI-generated interpretation before it reaches the patient.
Challenge
Stack
In the evolving landscape of web development, choosing the right approach for custom software development is crucial.
Challenge
Stack
In the sustainability-focused retail landscape, product repair and maintenance play a pivotal role in circular economy initiatives. Businesses are increasingly adopting innovative solutions to reduce waste and extend product life cycles.
Challenge
Stack
When Garde-Robe presented their innovative vision to make fashion more social and collaborative, Kreante, a leading LowCode agency, eagerly embraced the challenge.
Challenge
When INSPO approached our LowCode agency with their vision of creating the definitive platform for thought leadership, we knew this project would push the boundaries of what’s possible with…
Stack
In the rapidly evolving landscape of LowCode development, creating sophisticated applications no longer requires months of traditional coding.
Challenge
Stack
Connect with verified construction professionals, find new projects, recruit subcontractors, and grow your business with ShareLeads' trusted B2B platform.
Challenge
The basketball community in Washington D.C. lived on courts and in scattered WhatsApp groups. What was missing: a place to give it visibility, bring more people together, find players at your…
Stack
What we built In 3 months, Kreante delivered all three platforms at once. The mobile app lets you find pickup games within a 10-mile radius, rate players to compete at the right level, track your progress, and meet up to watch games together. Two tiers: a free version and a premium subscription at $39.99/season — proof that the community is willing to pay to play better. For this kind of project, visual identity isn't just a detail — it's what creates the sense of belonging from the very first open. The entire branding was conceived and built by Kreante. The landing page was built to convert: a strong visual world, a clear message, one goal — trigger the download. The e-commerce store pushed the logic even further: unapologetic street style, rooted in DC culture, to rep your colors beyond the court. Launched at a Virginia tournament, HoopSquad is now live across 13 regions in the United States — on the App Store and Google Play.
Challenge
The Meetern team had been connecting students and companies for years, through physical events. Many great encounters and opportunities later, they understood that to create real impact at scale,…
Stack
What we built Kreante designed and developed Meetern: a complete matchmaking platform, with three distinct interfaces for students, companies, and academic institutions. Students build their profile, apply, and track their applications. Companies post opportunities and receive intelligently matched profiles. Academic institutions monitor placements in real time. Across all three: integrated messaging and a matching algorithm that replaces manual introductions. The platform is multilingual, French and English at launch, Dutch on the way. A V1 delivered in 6 months, a V2 launched in March 2026 with extended language support. Today, 50 to 100 active users every day. And a team that no longer runs events, but a platform.
Challenge
Every manager knows a motivated team performs better. But motivation is invisible. And without understanding what truly motivates each person, engagement initiatives remain educated…
Stack
Kreante designed and developed Motives Solutions: a bilingual SaaS platform (FR/EN), from branding to application. Team members answer 3 anonymous questions. The app analyzes responses and generates a detailed report by motivational driver, for each individual, each team, each organization. Two modules: Motives TEAM for team-level insights, Motives ORGA for the full picture. Tracking is longitudinal: engagement evolution over time, visualized. Three questions. A clear picture of what truly moves a team forward. Measuring the invisible, so you can finally act on it.
Challenge
After a decade training thousands of women for tech jobs, Laboratoria saw its graduates stall on the way to leadership: in engineering and product, only 52 women are promoted to management for every…
Stack
Laboratoria+ is the membership platform of Laboratoria, the Latin American organization that has helped more than 14,000 women access quality jobs in tech. Built with Bubble, it brings together live courses and learning circles, 1:1 career mentoring with a network of senior women executives, online and in-person events, and a free plan alongside paid Pro and Plus subscriptions.
Challenge
Stack
Transform your organization with ROC's secure hyperautomation platform. Orchestrate workflows, governance, and access management from a living organizational chart.
Challenge
Class2Class wanted any teacher in the world to find a partner class and run a real project together, but international collaboration in schools depended on personal contacts, scattered tools and…
Stack
Class2Class is a global learning community, based in Denmark, where teachers connect their classrooms to run real-world projects around the UN Sustainable Development Goals. Kreante rebuilt the web platform with Bubble and Xano — teacher profiles, class matching, project creation and collaboration spaces — and delivered the rebranding and landing page. The community now counts more than 25,000 teachers in 190+ countries.
Challenge
In Switzerland as across the world, independent cab drivers face the same reality: ride-hailing platforms that set the rates, impose the rules, and own the client relationship. Olivier Fouvy wanted…
Stack
SmartCab is built on a radical premise: for the end customer, nothing changes. No new app to download, no account to create, no interface to learn. They send a WhatsApp message to their driver, just as they always have. Behind that message, an entire machine kicks into gear: an AI engine processes the request, calculates the route, confirms the booking, and triggers invoicing — automatically. Everything an app does. Without the app. They send a WhatsApp message. The rest happens without them. For drivers, it means freedom regained: customizable pricing, a client relationship that belongs to them, no algorithm to appease to stay visible. For fleet operators, a dispatch module handles ride assignments and real-time driver tracking. Three subscription tiers: Lite, Pro, Premium — built for every profile. What SmartCab proves is that real sophistication doesn't announce itself. It's felt — in a booking that requires zero effort, in a relationship of trust that no one gets to monetize. Available on iOS and Android.
Your teams know better than anyone what takes up their time between two viewings. Let’s start from there, and see together what AI can change for your agency, in a first conversation that is free and without commitment.
The three terms often get mixed up, so let’s take a concrete example for each:
| Tool | What it does | Example in an agency |
|---|---|---|
| Chatbot | It replies when a visitor writes to it | Answering a question about a property from your website |
| Automation | It always runs the same sequence of actions | Creating a contact record for every enquiry received from a portal |
| AI agent | It analyses a situation, sorts, prioritises and suggests an action | Identifying the buyers who match a new listing and preparing the messages |
| Type of tool | Uses in an agency | Examples | Watch out for |
|---|---|---|---|
| AI built into the transaction software | Writing and syndicating listings, tracking enquiries | Depends on your vendor’s features | Limited to the software’s data |
| Valuation tool | Preparing a valuation from recent sales | Public DVF data, specialist tools | Does not replace the visit |
| Image tool | Photo editing, virtual home staging | Specialist editing and staging tools | An edited photo must not mislead the buyer |
| Reception assistant | Answering website and phone enquiries, offering slots | Specialist chatbots and voice agents | Must introduce itself as an AI |
| General-purpose AI | Writing an email, summarising a survey report, preparing a sales pitch | ChatGPT, Claude, Gemini, Mistral | Never client data in the consumer version |
| Custom solution | Connecting your tools and automating the agency’s processes | An agency like Kreante | Requires scoping and data preparation |
The one that relieves you of the task that costs you the most time, without putting your data at risk. Before choosing, ask yourself these four questions:
The simplest way is to follow a listing, from valuation to the preliminary sale agreement.
In lettings management, the logic is the same. AI sorts tenant requests and prepares common replies, and your property managers stay in control of repairs, disputes and unpaid rent.
Yes, and it is particularly useful during viewings or outside opening hours. Connected to your transaction software, the agent finds the property the caller is talking about, answers common questions (floor area, service charges, availability), qualifies the project and offers a slot in the negotiator’s diary. The negotiator receives a summary of the call and calls back already knowing the file.
Three rules govern its use:
Finally, the agent never commits to a price, an offer or a negotiation: it transfers to a negotiator as soon as the request warrants it.
Not like traditional cold calling. Since 11 August 2026, calling a private individual to canvass them requires their prior consent, with some exceptions, notably when a contract is in progress[4]. Calls made by an automated system are also subject to strict consent rules.
AI remains very useful with your existing contacts. It can reply to owners who request an online valuation, identify buyers in your database who also have a property to sell, and follow up with sellers you are already in touch with. You keep active prospecting, within a safe framework.
It can write attractive listings, quickly and in your agency’s style. But it can also forget a mandatory disclosure, or get carried away and turn laminate flooring into solid oak parquet. Compliance therefore remains your responsibility, and it starts with the disclosures a professional listing must include[2]:
At Kreante, we work in three stages. AI writes the listing from the property record, and from it alone, so that nothing is made up. An automatic check then verifies that all mandatory disclosures are present. Finally, the negotiator reviews and approves before publication.
It can help you prepare a valuation, but not set the price for you. Valuation tools rely on past sales, notably the public DVF data (Demandes de valeurs foncières, French property transaction records), published by the tax authorities with some delay. They also take into account the characteristics of the property and its neighbourhood.
| What AI can take into account | What it cannot see |
|---|---|
| Recent comparable sales in the area | The actual condition of the property and the quality of the finishes |
| Floor area, number of rooms, floor level | Natural light, the view and nuisances |
| Nearby shops, schools and transport | Life in the co-ownership building and upcoming works |
| Local market trends | The seller’s circumstances and room for negotiation |
That is where your negotiator makes the difference: they visit the property, talk with the seller, and set a price they will be able to defend.
No. Your negotiators keep their transaction software, their buyer database and their listing syndication feeds. The solution connects to them. If your vendor offers an API, data is exchanged in real time: an enquiry from SeLoger or Leboncoin becomes a contact record within seconds, linked to the right listing.
Otherwise, regular exports are enough to prepare seller reports or match properties with buyers. We check this during the assessment, software by software.
The market brings together vendors of specialist tools, real estate software that includes AI, and agencies that design custom solutions.
| Provider | Type | Positioning |
|---|---|---|
| Kreante | Custom-build agency | AI solutions designed for each agency or network, built on the transaction software and existing tools. 265+ projects delivered in 35 countries, 4.9/5 on Clutch |
| Keyzia | Specialist tools | Conversational assistant, property scoring and preparation of seller appointments |
| Cleemo | Assistant for agencies | AI assistant for everyday sales and lettings tasks, with approval of every message sent |
| Omny | Search platform | Property search through a conversation with an AI, available in ChatGPT, and buyer profiles passed on to agencies |
| Kappn | Agency | AI agents for real estate agencies: seller reporting, enquiry qualification, website and phone reception |
| Product’IA | Agency | Qualification chatbot, listing writing and workflows connected to real estate software |
| Keyweo | Agency | Automation of listings, follow-ups and documents for real estate professionals |
This list is not exhaustive. On Omny, see Journal de l’Agence[7].
It can help you react earlier, which often makes all the difference. Here is how the roles are shared:
No, for several reasons:
At Kreante, every project is priced at a fixed rate on a scope defined in writing, after a free assessment. The budget depends mainly on four factors:
| What changes the budget | Why |
|---|---|
| The number of processes involved | Enquiry handling, listings and seller reports each require their own development |
| The transaction software | Its available connectors determine how easy the integration is |
| The number of agencies and negotiators | More access rights to manage, and more people to train |
| The channels used | Website, portals, phone, email, SMS or WhatsApp |
An AI agency designs and implements artificial intelligence solutions adapted to your business, whereas a software vendor sells the same software to all its clients. There is no “best AI agency” in absolute terms, only one suited to yours. Before committing, ask it these five questions:
A serious agency should be able to answer you precisely from the first conversation.
Some buyers no longer go through a portal’s filters: they describe their project directly to an AI assistant.
Written by Jorge del Carpio, CEO and co-founder of Kreante. Since it was founded in 2020, the agency has delivered 265+ projects in 35 countries.
Published Updated
From the blog
Guides, comparisons and field notes from the projects we deliver.
ToolsPick Lovable to get a hosted, Supabase backed live app fast. Pick Claude Design when engineering teams need code first prototypes and tighter code control.
DevelopmentMost AI automation projects show no measurable result. A Kreante project manager explains the sequence that works, with pricing and a real case study.
DevelopmentPilot AI coaching for one to three teams over 6 to 8 weeks, measure workflow KPIs, and demand embedded deliverables to keep skills in house.
Insights & TipsOutcome first AI playbook for SMBs: use a 5-criteria scoring rubric, run a 4-week before and 4-week after task audit, and pilot in 6–12 weeks to prove ROI.
DevelopmentAn outcomes first AI lifecycle mapping seven stages from prototype to production, covering agents, RAG, evals, guardrails, and a short roadmap.
Insights & TipsExecutive guide to AI consulting with an ROI first approach. Get a roadmap ordered by return, avoid vendor lock in, and secure code ownership.
