For broker pools and advisory firms

Unready leads become signings. With the advisors you already have.

The agents give the lead a plan and hand it back when it is worth calling. The client and the commission stay yours. How many extra signings? A pilot measures it in 30 days.

Prague · Bratislava · Malaga

Built for Europe from day one. The property models were born in Spain, the finance side was proven in the Czech Republic.

PragueBratislavaMalaga
The purchase underwriter

Marb reads the finances and the property.
The advice and the signature stay with you.

But no one reads both sides together. Marb is the purchase underwriter: one verdict on whether the flat is worth the price and what the listing left out. The bank decides the loan.

01 · INTELLIGENCE
A purchase underwriter for every bank
An inspector for every home
A coach for every buyer
02 · MODELS
Mortgage approval-odds models
Six-layer property diligence
500 rules from buying agents
03 · DATA
Case memory across banks
2 million data points on listings
PSD2 + Marb behavioural signals
Anatomy of a verdict

Buying a home is the biggest transaction of a person’s life, and it’s still done blind. Marb assesses the whole purchase and issues a verdict.

One purchase underwriter, four agents. Each covers one moment of the decision.

01 · Find

The Scout

Most people don’t know what they’re actually looking for. The Scout brings their life into it: work, school, budget. It combs the whole market and returns only the flats that fit right away.

→ points of interest + area prices → market match
02 · Calculate

The Analyst

The Analyst reads accounts from every bank and self-employed statements, runs DSTI and a stress test, and builds a budget so the client doesn’t end up living on plain rice. The bank decides the loan.

→ transactions from every bank · DSTI · stress test
03 · Plan

The Navigator

One year, or five? The Navigator breaks it down into months: what to save and when to apply for the mortgage. Then it counts down to the client’s moving day.

→ accounts across banks · your move-in date
04 · Verify

The Inspector

The listing shows pretty photos. The Inspector shows what it left out: condition and repairs from the photos, owners’ association debts, planned construction, floods and noise from official sources. The client knows what they’re getting into before they fall in love.

→ photos · owners’ association · construction · floods · noise
✦ marb agent
I want a flat in Prague, but I don’t know where.
Where do you commute, and what has to be nearby? For your budget, the edge of Prague fits better, say Zbraslav or Řeporyje.
✦ marb agent
Can I afford a CZK 7 million flat?
DSTI comes out tight, and after a stress test at higher rates it no longer holds. You’re comfortable up to CZK 5.8m. The bank decides the loan.
✦ marb agent
When will I live in my own place?
In this situation, mortgage-ready in 11 months. Put aside CZK 8,000 a month and you’re there in May. The bank decides the loan.
✦ marb agent
I entered the address. What should I watch out for?
The owners’ association has a dispute and a debt in the repair fund, and construction is planned 200 m away. Both from the official notice board, not from impressions.
How it fits together

From the whole market and the client’s finances
one verdict in 90 seconds.

The agents run through the market and the client’s data and return one verdict over the API: buy now, or a precise plan to get there.

Market + your data listings · land registry · client finances
Marb calls on inspection and other tools
GET /verdict → “buy now · or a plan for 8 months”
Data & AI

Data no chatbot will show you. Marb runs on it.

Only now can this be computed: PSD2 opens the account, AI reads the home from photos and the land registry, a model holds each bank’s rules. Our own data, not scraped portals.

They see the client across all their banks, not just the one PDF they bring you.

As long as the account stays connected, Marb watches the plan, income drops and the upcoming rate reset. Your meeting prep comes from data, not statements.

listing photos land registry cash flow (PSD2) commute times sales history energy rating condition from photos school quality bank rules supply / demand price vs. real value hidden costs legal risks post-purchase monitoring
Transaction intelligence

Every bank sees the statement.
Marb sees what it means.

With the client’s consent, the agents read money flows across all their banks via PSD2. And turn them into steps that end in a signing with your advisor.

01 · Detection

Spots a probation period and a flat tax paid on time.

From transactions it assembles real income: main, side, loan payments and BNPL. Everything that decides a mortgage, it knows before the client applies.

client K-2481 · income 62,400 · side 8,000 · probation to 3/27 · BNPL 2,490/mo

You know what the bank will see before you send it.

02 · Insights

Finds money the client doesn’t know about.

Food delivery at 4,200 a month is 50 thousand a year toward the down payment. The agents show the client where the money for a home can realistically come from. With numbers, not lectures.

insight · food delivery 4,200/mo → +50,400/yr toward down payment

A client who reaches the down payment sooner signs sooner.

03 · Plan

Blockers become a plan. The plan becomes a date.

The probation ends, the BNPL gets paid off, the down payment grows. The client sees their progress every month. You see the day they will be ready to apply.

recap 6/26 · readiness 58 → 64% · application possible from 2/27

The pipeline fills itself. Every client comes with a date to call.

04 · Triggers

When the verdict is “don’t buy”, the business doesn’t end.

The client won’t buy? The agents see from the photos and finances why, and what makes sense instead: renovating their current home, cutting energy costs, a new provider. You get a trigger for the product that fits.

trigger · own flat: facade + windows → green loan · est. 480,000

Renovation, energy, insurance. Every verdict is a reason to call the client.

Interior photo from a listing, a sample input for photo analysis
Property condition hidden costs ~CZK 550k
Room kitchen · original condition
Photo analysis

The listing: “renovated”.
The photos: kitchen and bathroom original, CZK 550k to fix.

From the photos, Marb identifies every room and its real condition: whether “renovated” means a new bathroom or just repainted walls. And it calculates what the repairs will swallow.

Physical inspection

The agent goes through the photos of every listing. It sends an inspector to the one the client picked.

For the chosen property, with the client’s consent, it books an independent inspection. The condition is verified before the client buys it.

Integration

Deploy agents where
your clients already are.

You keep the front-end, the data and the relationship. We never go to your client directly. It fits into your stack, it does not rebuild it.

POST /verdict
{ "flat": "…", "client": "…" }
200 OK
{ "verdict": "yes",
  "ready_in": "8mo" }
API

Intelligence in your chat

Call the endpoint, get the purchase verdict. Drop it into your advisory portal or CRM, in your design and under your brand.

For advisory firms and broker pools
marb · vaše aplikace
Can I manage this purchase?
In 8 months. Here’s the plan.
UI

Whitelabel app

Don’t want to build a frontend? Deploy our app in your colours and both the broker and their client work in it.

For brokers and their clients
MCP

Marb as a tool in your AI

Connect Marb as an MCP server and work with the client in the AI you are used to. Claude, ChatGPT or your own agent.

For AI-native teams

Enterprise security

Control what matters to your business with built-in guardrails, secure access, and seamless data management. The credit decision never leaves the bank.

For risk, compliance and IT
Cases

What it does
in your office.

Less manual work

The client connects an account or uploads statements. Marb sorts income and spending and calculates what they can reach. For the self-employed it asks for the right documents. The advisor doesn’t start from zero.

→ the advisor handles more clients

Conversion, no acquisition

A paid lead isn’t ready for a mortgage yet. Marb narrows their shortlist to the budget, gives them a plan and sees through the connected account that they’re saving. It hands them back to the advisor prepared.

→ a deferred lead becomes a signing

A client who comes back

The refix date comes from the contract. That the client’s income dropped or that they’re saving for a next flat, Marb spots from the account. And it tells the advisor when to reach out.

→ more business, not just one mortgage

For advisors

Do not raise acquisition.
Raise conversion.

A lead that cannot afford the mortgage yet asks ChatGPT and goes cold. Or you write it off. Marb holds it instead: gives a plan, watches the saving happen and hands it back when it is worth calling.

Of the leads you paid for, this many sign

Without Marb
With Marb
sign on their own Marb pulls the parked ones through

How many exactly? We measure it in a pilot on your data.

A modern new-build apartment block with greenery
A young buyer holding a phone

Book a demo

Please tell us who you are and we will be in touch.

We're a

By submitting, you share your details with Marb so we can respond to your demo request. Processing is governed by our Privacy Policy. You can have your data erased at any time.