Disclaimer: Independent product concept by Kaushal Khodifad. Not a live commercial product.return to portfolio
Disclaimer: Independent product concept by Kaushal Khodifad.
The working product

US Commercial Lending (Commercial Real Estate + C&I business loans)

The live prototype first - the market and the spec are below.

Arbiter AnalystLive prototype ↓
Live prototype · multi-agent

How the agents work together

One file, the whole fleet - a safeguard on every handoff.

Watch one credit deal flow through the fleet
spread-ready evidence
cited memo + exceptions
Guardrail
PII redaction + tamper check
Measured
extraction F1 99.2%
Human checkpoint
None - runs autonomously here

Reads the financial package and provenance-tags every statement line.

Always on · across every stage
Policy-as-code governs every stepImmutable, replayable audit trailConfidence signal gates every decisionHuman-in-the-loop below the floorHallucination measured · grounded-or-abstainEvery step recoverable / rollback-safe
Live prototype · agent console

Watch a single agent in depth

Fully instrumented. Run it live.

Arbiter AnalystL1Commercial lendingSynthetic
Illustrative · synthetic - not measured results
11 min
Memo draft
vs ~5 hrs manual
98.2%
Spreading accuracy
100%
Grounded
cite-or-abstain
73%
Committee-ready
of drafted deals
CRE term loan · 12-unit multifamily · Maple Street Holdings LLC
  1. 1INTAKE
  2. 2SPREAD
  3. 3RATIOS
  4. 4COVENANTS
  5. 5MEMO
  6. 6LEDGER

Classify the borrower & deal

Auto

Identified an LLC borrowing against a 12-unit multifamily; loaded 2 years of returns, financial statements, a rent roll and the loan docs.

tool callclassify_entity()
in: package (1120S, FS, rent roll, leases)
out: {entity: LLC, dealType: CRE-term, guarantors: 2}
PII redaction
Confidence signal98%
INTAKE-OK
How it works

The market, from zero

No finance background needed - tap any step.

01Origination / Sourcing

Days to several weeks, depending on how fast the borrower sends documents

A banker (the relationship manager) finds, or is approached by, a business that wants to borrow. They talk through what the company needs the money for, how much, and roughly what the deal would look like, then collect the first batch of documents.

Who: Relationship Manager (the salesperson-banker) and the borrower

Where we play

Where Arbiter fits

The first workflow to automate - and where a human stays in.

The thin-slice wedgeArbiter Analyst

Automated credit spreading & covenant extraction before committee

30-60 min
to spread one return by hand
4-8 hrs
per credit memo, by hand
1.25x
minimum DSCR to clear

Spreading is the slow, error-prone front step whose mistakes poison every downstream ratio.

What the agent decides
  • Map each statement line to the template
  • Compute DSCR, LTV, debt yield, cash flow
  • Extract covenants and existing debt
Where a human stays in
  • Analyst reviews low-confidence flagged cells
  • Committee keeps the lend-or-decline vote
Build-ready

The PRD

Tap any section to expand it.

Arbiter Analyst
From thin slice to governed digital worker
One high-leverage workflow, scoped tight enough for an engineer to build.
1Scope
2Build
3Govern
4Ship
The cast

Who's involved

Who touches the deal, and what each does.

Relationship Manager (RM)
Salesperson-banker who owns the client relationship

The face of the bank to the business. They bring in the deal, figure out what the client needs, and shepherd it through the bank, but they don't usually do the number-crunching themselves. Think of them as the account owner who sells and negotiates.

Credit Analyst
The number-cruncher who builds the case

The person who does the grunt work: re-types the financial statements into the bank's template (spreading), calculates the ratios, and drafts the credit memo. Most of the manual hours on a deal are theirs.

Credit Officer / Credit Committee
The decision-maker(s) who approve or decline

A senior banker (or a panel of them) who reads the credit memo and votes yes or no. They are the gatekeepers protecting the bank from bad loans; bigger or riskier loans need more senior or more people to sign off.

Appraiser
Independent valuer of the property

An outside expert hired to give a professional, unbiased estimate of what a building is worth. The bank needs this to know how big a loan is safe versus the value of the collateral.

Attorney
Lawyer who drafts and closes the loan

Writes the binding legal contract, including the covenants (rules the borrower must follow), makes sure the bank's claim on the collateral is legally airtight, and handles the closing.

Borrower / Guarantor
The business taking the loan and the owners backing it

The company that wants the money, plus the owners who personally promise to repay if the business can't (the guarantors). Their tax returns and financials are the raw material the whole process runs on.

The paperwork

Every document, decoded

Tap a document - what it is, why it matters, an example.

Business tax returns

The tax forms the company files with the IRS, showing its income and expenses. Banks use these because they're hard to fake and give a few years of history.

Why it matters

They are the most trusted source of a company's real earnings and are the starting point for spreading and cash-flow analysis.

Example

A 3-year stack of Form 1120-S returns for 'Maple Street Diner LLC' showing $1.2M revenue and $180K net profit in the most recent year, used to confirm the business earns enough to cover a new $500K equipment loan.

The money

What it costs

Who pays for what - illustrative figures.

Commercial appraisal
Borrower (paid to an independent appraiser)
~$2,000-$10,000+

More for large or complex properties; a common cause of delay as well as cost.

Environmental report (Phase I)
Borrower
~$2,000-$5,000

Checks the property for contamination risk; often required on CRE deals.

Loan origination fee
Borrower (paid to the bank)
~0.5%-1% of the loan amount

The bank's upfront charge for making the loan.

Legal / documentation fees
Borrower
Few thousand to tens of thousands

Lawyers drafting and closing the loan; scales with deal complexity.

Analyst time per deal (bank's internal cost)
Bank
~4-8 hours just to write the credit memo, plus spreading time

The labor the AI wedge targets; spreading one entity's return alone is ~30-60 minutes.

Scoreboard

Hero metrics

The numbers the worker has to move.

Writing the memo alone commonly takes 4-8 hours; total spreading-plus-underwriting time runs from hours to a few days
Analyst hours per deal

How much human time an analyst spends to take one loan from raw documents to a committee-ready memo. Lower is better and means cheaper, faster lending.

Underwriting commonly runs 3-10 business days for smaller loans; longer for complex deals
Time-to-credit-memo

How long from receiving the borrower's documents until the finished memo is ready for a decision.

Best-in-class AI extraction claims up to ~98% capture accuracy, implying manual error rates of a few percent or more
Spreading error rate

How often a number gets mistyped or mis-mapped when financials are copied into the bank's template. Errors here poison every downstream ratio and decision.

A workflow-quality target; higher is better and means less rework
% deals committee-ready

The share of memos that reach the committee complete and correct the first time, without being bounced back for missing data or mistakes.

Lenders commonly require a minimum of about 1.25x
DSCR (debt-service-coverage ratio)

Cash the business or property generates divided by the loan payments. Above 1.0 means it earns more than enough to pay; banks want a cushion.

Commonly capped at 75%-80%
LTV (loan-to-value)

Loan amount divided by the appraised value of what backs it. Lower means the bank has more cushion if it has to sell the collateral.

The field

Who else is here

10 players already serving this vertical, and the gap each leaves.

Zest AImoat 4/5
Underwriting / Decisioning-AI

Builds client-tailored ML credit underwriting models (600+ live models, 50+ patents) plus fraud detection. Optimizes policies/cut-offs to auto-decis…

Gap: Sells the decision engine but not the system of record, so depends on LOS partners for distribution; concentrated in c…

Ocrolusmoat 3/5
Document-AI / Extraction & Fraud

Document-AI platform that extracts and structures data from 100s of document types (bank statements, pay stubs, tax forms) at 99%+ accuracy with hum…

Gap: Sits below the decision - it verifies and feeds data but does not make the credit decision, so it is a component vulne…

nCinomoat 4/5
System-of-Record / LOS

Cloud bank operating system (on Salesforce) spanning onboarding, account opening, loan origination, credit analysis, and portfolio management. nIQ D…

Gap: AI is largely an assistive copilot/data-recognition layer, not autonomous decisioning - bankers still drive credit dec…

Numeratedmoat 4/5
System-of-Record / LOS

AI-driven business-lending origination platform automating the SMB/commercial lending workflow from application to decision to closing (incl. SBA au…

Gap: Decisioning still largely supports human credit approval rather than fully automating it; SMB/commercial credit is het…

Moody's CreditLensmoat 4/5
Underwriting / Decisioning-AI

Commercial-lending credit platform for consistent financial spreading, dual risk-rating models (or bank-configured policies), benchmarking, and BPMN…

Gap: Primarily a spreading/risk-rating and workflow tool that informs human credit committees rather than auto-deciding; co…

Abrigomoat 3/5
System-of-Record / LOS

Compliance, credit-risk and lending platform for 2,400+ community banks/CUs: loan origination, Sageworks credit analysis/spreading, CECL/ALM modelin…

Gap: AI is assistive (narratives, extraction, review acceleration) rather than autonomous decisioning; serves smaller insti…

Guidewiremoat 5/5
Insurance Core & Claims/Underwriting-AI

Dominant P&C insurance core suite (InsuranceSuite: PolicyCenter, ClaimCenter, BillingCenter, plus UnderwritingCenter) on Guidewire Cloud. Adding an …

Gap: Core-platform conservatism and human-in-the-loop governance cap autonomy; AI is largely an orchestration/assist layer …

Duck Creekmoat 4/5
Insurance Core & Claims/Underwriting-AI

End-to-end P&C core SaaS (Duck Creek OnDemand: policy, billing, claims) and the main challenger to Guidewire. Launched an insurance-native Agentic A…

Gap: Smaller installed base than Guidewire; agentic apps are newly launched and unproven at scale; like all core suites it …

Akur8moat 4/5
Insurance Core & Claims/Underwriting-AI

Actuarial AI platform that automates insurance pricing and reserving using proprietary Transparent Machine Learning (TML) on GLM/GAM structures - bu…

Gap: Automates model-building, not the bind/decision - actuaries retain control and regulators approve rates, so it acceler…

Sixfoldmoat 3/5
Insurance Core & Claims/Underwriting-AI

Generative-AI underwriting solution that ingests an insurer's own guidelines/risk appetite, then assesses submissions (SOVs, applications, loss runs…

Gap: Early-stage and venture-funded vs. entrenched cores; produces a risk assessment/score that supports the underwriter ra…

Cheat sheet

Jargon, decoded

Every term on this page - search it.

Spreading

Re-typing a borrower's tax returns and financial statements line-by-line into the bank's standardized template so every borrower can be compared the same way.

e.g. An analyst enters each line of 'Maple Street Diner's' 3 years of tax returns into the bank's credit software to build a clean, comparable financial picture.

Credit memo

The structured write-up that summarizes the analysis, ratios, risks, and a recommendation, and is the document the decision-makers actually read.

e.g. A 12-page memo concluding 'recommend approval of a $500K equipment loan to Maple Street Diner with a 1.40x debt-service coverage and a personal guaranty.'

Credit committee

A panel of senior bankers who read the memo and vote to approve or decline larger or riskier loans.

e.g. On Thursday the committee reviews five memos and approves the diner loan with a condition that the owners keep $100K in reserves.

DSCR (debt-service-coverage ratio)

The cash available to pay debt divided by the debt payments owed; it answers 'can they comfortably afford this?'

e.g. A property with $125,000 of net operating income and $100,000 of annual loan payments has a DSCR of 1.25x.

LTV (loan-to-value)

The loan amount divided by the appraised value of the collateral; it answers 'how much skin does the borrower have versus the bank?'

e.g. A $750,000 loan on a building appraised at $1,000,000 is a 75% LTV.

Debt yield

The property's annual net income divided by the loan amount, showing the bank's plain cash return if it had to take the property over, independent of interest rates or appraised value.

e.g. A property earning $100,000 net income with a $1,000,000 loan has a 10% debt yield.

Global cash flow

A combined view of all the income and expenses of both the business and its owners (guarantors), to see the total ability to repay.

e.g. A property that barely covers its own loan still qualifies because the owner's separate $200,000 salary is added in to show total repayment capacity.

Net operating income (NOI)

For a property, the rent collected minus the cost of running the building, before any loan payments.

e.g. An apartment building collecting $360,000 of rent with $135,000 of operating costs has an NOI of $225,000.

Covenant

A rule written into the loan contract that the borrower must keep following, acting as an early-warning tripwire for the bank.

e.g. A covenant requiring the borrower to keep total debt below 3x annual earnings; exceeding it is a breach the bank can act on.

Borrowing base

The dollar limit on a revolving credit line, set by the value of the borrower's invoices and inventory and recalculated regularly.

e.g. With $2M of eligible invoices at an 80% advance rate, the borrowing base allows up to $1.6M to be drawn that month.

Guarantor

A person (usually a business owner) who personally promises to repay the loan if the business cannot.

e.g. The two 50% owners of the diner each sign a personal guaranty, putting their own assets on the line for the $500K loan.

C&I loan

A commercial-and-industrial loan to an operating business for working capital, equipment, or growth, repaid from the company's profits.

e.g. A $250K revolving line of credit a manufacturer draws on to buy raw materials and repays as customers pay their invoices.

CRE loan

A commercial real estate loan to buy, build, or refinance an income-producing property, repaid from the rent the property earns.

e.g. A $3M loan to purchase a strip mall, repaid from the rent its tenants pay.

↑ Independent product concept by Kaushal Khodifad. Arbiter is an independent product concept by Kaushal Khodifad; it is not a real company or a commercial product. It explores the adjudication infrastructure for regulated lending & insurance space. Not a live commercial product. Data is illustrative.

Return to portfolioOpen the live demo