Every rule a loan has to pass before it funds, and how Sei checks it

• 01

  Pre-close

  Eligibility and the closing package: whether this loan, on these terms, with these documents, can close.

  • Every borrower signed the initial application, and nobody signed it who will not be on the Note
  • The purchase contract is complete, signed by the buyers on the 1003, and agrees with the loan on price, credits and parties
  • Title names the lender with its successors-and-assigns clause, vests in the borrower on a refinance, and puts the new loan in the right lien position
  • Hazard and flood policies cover the subject address, the mortgagee clause and the closing date
• 02

  Underwriting

  The decision behind the approval: the AUS run, every condition on it, and the credit file it was scored on.

  • The latest AUS submission matches the final 1003, the 1008 and the Closing Disclosure
  • The credit report reference number matches the AUS run it was scored on
  • Every AUS condition is cleared by a document in the file, named
  • Waiting periods after a bankruptcy, foreclosure, short sale or deed-in-lieu are met from the right date
• 03

  Income

  Each qualifying figure, recalculated from source and documented to the rules for its own income type.

  • Two years of history for base, overtime, bonus and commission, and the averaging method the guide sets
  • Self-employed income from the returns and transcripts, with year-over-year decline tested
  • Rental income from the Schedule E or the lease and market rent, at the guide’s vacancy factor
  • Non-taxable income grossed up only as far as the program allows
• 04

  Assets

  Twenty-one sources of funds, each with its own documentation rules, tested for ownership, age, seasoning and sufficiency.

  • Bank, brokerage and retirement statements: account holder, every page, statement age and period covered
  • Gifts, gifts of equity, grants, down payment assistance and employer assistance: donor eligibility and transfer evidence
  • Borrowed funds, bridge loans and the sale of personal or real property: the debt in the ratios, the proceeds evidenced
  • Earnest money, large deposits, virtual currency, cash on hand and credit-card rewards, each under its own rule
• 05

  Appraisal

  The collateral and the report that values it, including the property standards each government program adds.

  • The right report for the property type, signed, and submitted through the agency portal with a successful status
  • Comparables, adjustments, zoning and highest and best use, as the appraiser supported them
  • A report made subject to completion or repairs has the completion certificate behind it
  • Condo and PUD project review complete for the review type used

Further reading on QC and underwriting

• Pre-Funding QC With an AI Agent: The Fannie D1-2 Review, the Defects You Catch Before the Wire, and the Reverifications the Rule Still Wants a Human to Judge

  Post-closing QC tells you how many defective loans you already sold. Pre-funding QC is the only review that changes the outcome, because it happens before the money moves. An AI agent can run the full-file pre-funding review at 100 percent of the pipeline instead of a sample, catch the income-calculation error and the data-integrity break before closing, and drive the reverifications the rule requires. What the agent computes, what stays human, and how the defect taxonomy has to be built so the review is defensible.

  7 min read

• Mortgage QC at 100% Coverage: What Changes When AI Reviews Every Loan Instead of a 10% Sample

  GSE quality control rules were written around sampling because full review was impossible by hand. AI removes that constraint. What a full-population pre-funding and post-close QC program looks like, and where the Fannie and Freddie requirements still bind.

  6 min read

• Reading the AUS Findings: Where an AI Underwriting Agent Adds Value, Where SR 11-7 Draws the Line, and Why the Model That Touches Credit Is Governed Differently

  The automated underwriting system already returned Approve/Eligible. The work that follows, clearing the findings, reconciling the conditions against the file, and deciding what the AUS could not see, is where cycle time and defects live. Where an AI agent operates on DU and LPA findings, why an agent that influences a credit decision falls under model risk management, and the governance we run so the agent is a documented, tested model and not a black box in the underwriting path.

  7 min read

• The Large Deposit Question: Verifying Assets With an AI Agent Under Fannie Mae B3-4.2-02, and Where Asset Sourcing Meets the Bank Secrecy Act

  Asset verification looks like adding up account balances and is actually a sourcing investigation. The 50 percent large-deposit rule, funds that have to be the borrower's own, gift documentation, and the point where an unexplained deposit stops being an underwriting condition and becomes a source-of-funds question a regulated lender cannot ignore. Where an AI agent reads bank statements, what it flags, and the line between an eligibility problem and an AML problem.

  7 min read

• Whose Money Is It, and Can You Prove It: Verifying Gift Funds and Down-Payment Assistance With an AI Agent Under Fannie B3-4.3-04

  A gift toward the down payment is the one place in asset verification where the paper trail and the relationship both have to hold, and where the sourcing question quietly becomes a Bank Secrecy Act question. How we build an agent that documents the donor, the transfer, and the availability of funds, tells a personal gift apart from a gift of equity and a DPA second, and knows the exact point at which it stops verifying and escalates to a human.

  6 min read

• The Credit Pull Is Not One Event: Undisclosed-Debt Monitoring, the Pre-Closing Refresh, and the Permissible-Purpose Line an AI Agent Cannot Cross

  A mortgage credit file is pulled at application and again before the note signs, and the gap between those two pulls is where a borrower opens a car loan the underwriter never saw. An AI agent that watches that gap touches FCRA permissible purpose, the Fannie Mae age-of-documents rule, and the re-underwrite decision. Where the agent monitors, what it is allowed to pull, and why it never gets to re-decide the loan on its own.

  7 min read

• The Condo Questionnaire Is Where a Clean File Stalls: Project Warrantability With an AI Agent After the Post-Surfside Rules

  A warrantable borrower in an unwarrantable project is a denied loan, and the project review is the slowest, least-staffed part of mortgage underwriting. How an AI agent assembles condo project eligibility against Fannie Mae SEL-2023-06, the critical-repairs and special-assessment rules effective September 2023, and where the agent has to stop and hand the warrantability call to a human.

  7 min read

• Rental Income Is Three Different Numbers and Only One of Them Qualifies the Borrower: AI on the Investment-Property Calculation

  A lease says one number, the appraiser's Form 1007 says another, and Schedule E says a third, and an underwriter has to pick the right one under rules that change by occupancy and by how long the borrower has owned the property. How an AI agent produces an auditable rental-income figure under Fannie Mae B3-3.1-08, where the 75 percent factor applies, and the reasonableness call the underwriter still owns.

  6 min read

• The Guide Changed on Tuesday and You Have 4,000 Loans in Flight: Version-Controlling the Rules an AI Mortgage Agent Reasons Against

  Fannie and Freddie update their selling guides constantly, often with several effective dates inside a single announcement, and a loan in your pipeline is governed by the rule that was in force when its application was dated, not the rule in force today. Most AI mortgage tools hardcode the rules and silently drift out of date. A technical account of how we version-control the rulebook, apply the right rule by effective date, and re-plan in-flight loans when the guide moves underneath them.

  6 min read