Lending infrastructure that evolves with every signal.

Every data point sharpens your loan book. Built with your team, on your data.

Orbii console Live LN-00001 · Falcon Foods LLC · one record · --:--:--
Intake01 / 06

0 documents read

Statements, financials, the trade licence and the bureau report become fields your credit policy can be written against.

Fields extracted0
Statement window0 months
Every field traced toits source page
Orbii Intake →
Origination02 / 06

File assembled

The application is put together and screened against your own credit policy, so what reaches a credit officer is already worth opening.

Policy checks run0
Missing items0
Fields re-keyed by handnone
Intelligent LOS →
Decisioning03 / 06

Band B · PD 0.0%

Your eligibility rules gate the population, your PD model ranks within it, and the weighting between them is yours to set.

DSCR0.00
Days past due0
Recommended limitAED 0
AI Credit Risk Officer →
Labs04 / 06

Champion v1

The model doing the scoring was built on your own book, with your team in the studio, and it stays yours.

Gini0.00
Backtested on0 loans
Challenger in testv5
AI Credit Model Builder →
Servicing05 / 06

0 payments scheduled

Schedules, restructures and a full audit trail. Every repayment becomes a labelled example, so the book you are running teaches the model that writes the next one.

Term0 months
Labelled examples added0
Audit trailcomplete
Intelligent LMS →
Portfolio06 / 06

AED 0.0M book

Canvases you build, not reports you request. The book is watched continuously rather than quarterly, and what it finds loops back into the next decision.

Active loans0
Watchedcontinuously
Portfolio Intelligence →
One record, end to end. Adopt one surface, or run them all.
Live with lenders across UAE, Saudi Arabia, Oman and Jordan
Control

Orbii recommends.
You decide.

Approve. Decline. Price, with human in the loop. The model ranks inside the population, and it shows its working every time. Nothing runs live until your team promotes it.

How decisioning works
01Logged Every field, every rule, every override.
02Explainable A band, a score, and the drivers that produced them, in the order they mattered.
03Yours Your eligibility rules gate the population. Your model ranks within it. You set the weighting, and the model is built on your data.
Five surfaces

One record, five surfaces

01Intake
02Origination
03Decisioning
04Servicing
05Portfolio
Intake

Orbii Intake

Reads the paperwork. Statements, financials, bureau reports and invoices become fields your credit policy can be written against, each one traceable back to the page it came from.

Origination

Intelligent LOS

Assembles the application and screens it against your own credit policy, so what reaches a credit officer is already worth opening.

Decisioning

Decisioning and Labs

A band, a score, and the reasoning behind both. Your eligibility rules gate the population, your PD model ranks within it, and the weighting is yours to set.

Servicing

Intelligent LMS

Schedules, restructures and a full audit trail. Every repayment becomes a labelled example, so the book you are running teaches the model that writes the next one.

Portfolio

Portfolio Intelligence

Canvases you build, not reports you request. The book is watched continuously rather than quarterly, and what it finds loops back into the next decision.

The Orbii stack

Five surfaces, one stack

Adopt one surface or run them all. They sit on the same record, so nothing is re-keyed between them and every repayment loops back into the decision that writes the next loan.

01 / 05
Intake

Orbii Intake

Reads the paperwork, and every field traces back to the page it came from.

Origination

Intelligent LOS

Assembles the application and screens it against your own credit policy.

Decisioning

Decisioning and Labs

A band, a score, and the reasoning behind both.

Servicing

Intelligent LMS

Schedules, restructures and a full audit trail, feeding the next model.

Portfolio

Portfolio Intelligence

Canvases you build, watching the book continuously rather than quarterly.

One stack. Every business model.

Underwrite more files without adding underwriters. Your policy gates the population, your model ranks within it, and every decision carries the reasoning that produced it.

  • Reads statements, financials and bureau reports in any format
  • A band, a score, and the drivers behind both
  • Your officer approves it, Orbii never does
For fintech lenders
Decision LN-00001
Revenue, 12mo AED 4,820,400
Banked credits AED 4,312,700
Band B · PD 4.1%
Top driver DSCR 1.42
Second driver 0 days past due
Recommended to AED 900K. Your officer approves it.

Launch a lending product against your own credit policy, with every rule checked and logged before a file reaches committee.

  • Policy encoded once, then checked on every file
  • Exceptions surfaced at the top, not buried in an annex
  • A full audit trail from intake through to sign-off
For banks and neobanks
Policy check SME term loan
Falcon Foods LLC
AED 900K · 24 month
5/6PASS
DSCR at or above 1.251.42
30 day arrears at zeroYes
Trade licence currentYes
Operating tenure 24mo8.2 yr
Margin at or above 8%14.6%
! Buyer concentration under 50% 61%
One exception, raised for the credit officer, not applied silently.

Embed financing in your product without building a credit function. The limit, the pricing and the reasoning come back over the same API.

  • Merchant and working capital limits from transaction behaviour
  • Offers that move as the merchant's book moves
  • One record from the offer through to servicing
For platforms and marketplaces
Embedded offer MR-4471
Settled volume, 6mo AED 1,940,200
Trend+11% QoQ
SEPFEB
Offer AED 240,000 · 90 day
Recalculated every settlement cycle, not once at onboarding.
Salary Advance
Merchant Financing
Working Capital
Embedded Lending
BNPL
Salary Advance
Merchant Financing
Working Capital
Embedded Lending
BNPL

How Foodics Lender boosted loan approvals by 30% using Orbii’s AI engine.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut et massa mi.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut et massa mi.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut et massa mi.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut et massa mi.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut et massa mi.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut et massa mi.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut et massa mi.

Designed for developers

One record, one API.

A single API and one webhook stream across intake, decisioning, servicing and portfolio. Every field traces to its source, every decision is logged.

LN-00001
POST /v1/applications
{
  "borrower": "Falcon Foods LLC",
  "documents": [ 4 files ],
  "policy": "sme_v3"
}
// 201 Created
{
  "loan_id": "LN-00001",
  "status": "parsing",
  "events": "webhook"
}
documents.parsed 312 fields from 4 documents09:41:02
application.assembled screened against sme_v309:41:04
decision.issued Band B, PD 4.1%09:41:06
loan.disbursed on approval
repayment.posted on each instalment
portfolio.updated continuously
policy.applied sme_v3, by rules engine09:41:04
model.scored champion v4, Gini 0.6209:41:06
reason.recorded DSCR 1.42, zero days past due09:41:06
field.traced every value back to its source page09:41:06
reviewer.assigned credit officer, queue sme09:41:07
Every event carries the same loan id. Nothing is re-keyed between surfaces.

See Orbii in action

Adopt one surface, or run all five. The record is the same either way, and every loan your book writes makes the next decision better.

Five surfaces, one loop, one record

Intake, origination, decisioning, servicing, portfolio

Every decision explainable, every action logged

Trusted by lenders across UAE, KSA, Oman and Jordan

Over $350M processed in 2025

Your team works alongside ours