BankingFinance
Loan underwriting. Reviewed against policy, not guessed.
Reviews every loan file against underwriting policy and credit guidelines, calculates exceptions, and generates the risk memo — before it reaches a credit committee. Built for lenders processing hundreds of loan files a month.
16 cited fields per file. Built on Sphere AI Foundry.
loan_underwriting — file #LN-61042LIVE
00:00Ingest → borrower application + financials, file #LN-61042read
00:03DTI check → debt-to-income 38%, within policypassed
00:06Collateral check → LTV 82%, exceeds 80% policy thresholdflagged
00:08Credit history → 2 late payments in 24 months, within tolerancepassed
00:09Disposition → Route to underwriter, 1 exceptionrouted
review time 10sfields cited 16/16underwriter sign-off required
Organizations around the world trust us
Built on Sphere AI Foundry·Policy-matched by design·21 years, 300+ clients
Manual underwriting doesn't scale with loan volume
A single loan file review means an underwriter checking income, debt ratios, collateral value, and credit history against the bank's underwriting policy line by line, then writing up any exceptions for committee. At low volume that's manageable. Across hundreds of files a month, it's the reason approvals queue up and inconsistent exception-handling creates real credit risk.
85%
faster first-pass file review vs. manual underwriting
16
fields extracted & cited per file
100%
of exceptions traceable to the specific policy threshold
File in, cited memo out
Four steps, every one logged and citable back to the underwriting policy.
01
Ingest
Reads the loan file directly from your systems
Application, income documentation, credit report, and collateral appraisal — read from your loan origination system or document repository. No separate upload step.
Source document
LN-61042 — borrower application
02
Match against policy
Every ratio checked against underwriting policy
Debt-to-income, loan-to-value, and credit history — each checked against the specific policy threshold in effect, not a generic guideline.
Example query
"Does the loan-to-value ratio meet the policy threshold for this loan type?"
03
Cite every exception
No exception without a citation
Each exception links back to the exact policy section and threshold — the citation travels with the finding, not as a separate lookup.
Cited finding
Loan-to-value ratio of 82% exceeds the 80% policy threshold for this property type.
cited to Underwriting Policy §5.2, LTV threshold04
Classify & route
One disposition, one consolidated risk memo
The agent returns Approve, Approve-with-exception, or Decline, with a consolidated exception list routed to the underwriter for sign-off before committee.
Disposition
ApproveApprove-with-exception ✓Decline
16 fields, every one cited
What the agent extracts from every file it reviews.
Underwriting summary & disposition
Borrower & income verification
Debt-to-income calculation
Loan-to-value & collateral check
Credit history & score review
Policy exception list with citations
Prior loan history with this borrower
Stipulation & condition checklist
Consolidated risk memo
Underwriter review checklist
Typical inputs
What the agent reads, and what it connects to.
Documents
- Loan application and income documentation
- Credit report
- Collateral appraisal or valuation
- Bank's underwriting policy and credit guidelines
Systems
- Loan origination system (LOS)
- Credit bureau integration
- Document repository or imaging system
Is this the right fit?
Built for volume — not a one-off loan.
✓ Works best for
- Lenders processing 100+ loan files a month
- Institutions standardizing underwriting against a fixed policy
- Credit risk wanting every exception traceable to policy
Too small for
- A single VIP loan an underwriter can review faster than configuring the match
- Replacing underwriter judgment on a final approve/decline decision
- Loan types with no codified underwriting policy to check against
Grounded in policy, not a black box
Compliance-first, the same standard every Sphere agent is held to.
The agent requires the complete loan file and current underwriting policy before it will return a disposition, and every review sits between application and committee — never past it. An underwriter confirms every exception before a file reaches committee.
Exceptions reference the specific policy section and threshold directly — the same audit-trail standard every Sphere agent on the Foundry is held to.
Prerequisites complete file
The complete loan file and current underwriting policy are required before a disposition is returned.
Human review required
An underwriter confirms every exception before a file reaches committee — never fully autonomous.
Regulatory grounding policy-cited
Exceptions reference the specific policy section and threshold directly in every review.
Foundation Sphere AI Foundry
Access controls and audit trail configured here carry forward to every other agent you deploy.
Frequently asked
Does the Loan Underwriting & Risk Review Agent replace an underwriter?
No. It replaces the manual line-by-line check against underwriting policy. An underwriter still confirms every exception and signs off before a file reaches committee.
What loan types does it support?
Consumer, mortgage, and commercial loans out of the box. Additional loan types and policy sets can be added during onboarding.
How does it integrate with our loan origination system?
It reads directly from your LOS or document repository — no separate upload step required. Integration scope is confirmed during deployment planning.
Is every exception traceable to the underwriting policy?
Yes. Every exception cites the specific policy section and threshold it came from — there is no finding without a citation back to the policy.
How is this different from a generic loan origination system?
It's built specifically around matching a file against your underwriting policy and generating a cited risk memo, not managing the loan pipeline end to end. It runs on Sphere AI Foundry, so the access controls and audit trail configured here carry forward to other agents you deploy.
Hear from
our clientsHear from our clients
Lee Ebreo
VP of Engineering at Credit Ninja
These things would not have been achievable if we did not build our own in-house system and if we did not partner with Sphere to help us achieve our goals.
Selah Ben-Haim
VP of Engineering at Prominence Advisors
Our experience with Sphere and their team has been and continues to be fantastic. We keep throwing new projects at them, and they keep knocking them out of the park (including the rescue of a project that was previously bungled by another vendor).
Ben Crawford
Senior Product Manager at Enova Financial
I would expect to be delighted. It's been a really positive experience, working with Sphere, and I would expect you to have the same.
Mark Friedgan
CEO at CreditNinja
Sphere consistently prioritizes the needs of their clients, demonstrating both agility and teamwork. As an offshore team, they have been an integral part of our organization and we plan to continue growing with them.
René Pfitzner
Co-Founder at Experify
Sphere provided excellent full-stack development manpower to augment our team and help push our product forward. They are easy to work with, tech-savvy and proactive.
Bruce Burdick
Chief Information Officer at Integra Credit
We've been working with Sphere and its excellent consultants since our founding. I've found that they are true partners in the success of our business.
Jemal Swoboda
CEO at Dabble
The resources and developers that Sphere Software provides are skilled and have the required technical expertise, but more importantly, they have helped us build a culture of excellence within our team.
Arthur Tretyak
Founder and CEO at IntegraCredit
With Sphere, we were able to migrate in half the time it would take to train an additional FTE… and for a fraction of the cost. Our experience with Sphere has been exceptional.
Lee Ebreo
VP of Engineering at Credit Ninja
These things would not have been achievable if we did not build our own in-house system and if we did not partner with Sphere to help us achieve our goals.
Selah Ben-Haim
VP of Engineering at Prominence Advisors
Our experience with Sphere and their team has been and continues to be fantastic. We keep throwing new projects at them, and they keep knocking them out of the park (including the rescue of a project that was previously bungled by another vendor).
TOP AI CODE GENERATION COMPANY UNITED STATES 2025
TOP AI TEXT GENERATION COMPANY FLORIDA 2025
TOP APP DEVELOPMENT COMPANY MANUFACTURING 2025
TOP ARTIFICIAL INTELLIGENCE COMPANY UNITED STATES 2025
TOP CHATBOT COMPANY UNITED STATES 2025
TOP RECOMMENDATION SYSTEMS COMPANY UNITED STATES 2025
GLOBAL RECOGNITION AWARDS 2026
BEST IN AI FOR DOCUMENTATION VALIDATION 2026
BEST IN AI POWERED INVOICE AUDITING 2026
GLOBAL TECH WINNER 2026
MOST INNOVATIVE TECHNOLOGY CONSULTING FIRM 2026
GLOBAL GENERATIVE AI AWARD 2026 WINNER
Start here
See it on your own loan files
Bring three real loan files to the demo. We'll show the underwriting review live — exceptions, citations, and the risk memo, on your own documents.
Looking for a different workflow? Browse the full Agent Catalog.
Talk to a solutions architect
Direct to a senior architect — never a sales queue. Replies within one business day.
By submitting, you agree to be contacted about this request. We never share your details.