Skip to content
Sei
All Posts

AI Agents

21 articles in this category
AI Agents

Maker, Checker, Threshold: Why a Mortgage AI Agent Gets Three Independent Chances to Say No Before It Writes to the LOS

Mortgage operations already run on maker-checker: the underwriter decides, QC re-checks, a manager signs the exception. An AI agent that writes to the system of record should be held to the same separation, and a single model with a self-reported confidence score is not that. A technical account of how our three verification layers are built, what the checker is and is not allowed to see, why disagreements are never settled by a vote, and how the auto-clear threshold gets set.

7 min read
Read more
AI Agents

Agent Optimization: How Mortgage Lenders and Banks Get Onto a Personal Agent's Shortlist

If personal agents decide which lenders and banks a consumer even considers, being findable stops meaning ranking on a search page and starts meaning being legible to software that compares. What that asks of rate sheets, fee disclosures and product pages, where Regulation Z and Regulation DD advertising rules still apply when the reader is an agent, and how to measure consideration instead of clicks.

4 min read
Read more
AI Agents

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 Most AI mortgage tools hardcode the rules and silently drift out of date.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
Read more
AI Agents

Scopes, Approvals and Records: Designing Consent for Personal Agents in Mortgage and Banking

A technical walk through the consent layer of the Personal Agent Protocol draft 0.3 — delegated sign-in, scopes and scope hints, operations with terms and expiries, approval records and token lifetimes — and how a mortgage lender or a bank would map its own consequential actions onto it: credit pulls, rate locks, application submission, transfers, payment plans and disputes.

6 min read
Read more
AI Agents

How You Test an Agent That Runs for 30 Days Before It Touches a Live Loan: Golden Files, Backtesting, and the Eval Harness SR 11-7 Actually Wants

A model that scores a loan in 300 milliseconds is easy to validate. An agent that holds a goal across weeks, re-plans as the file changes, and makes dozens of decisions along the way is not, and the usual accuracy-on-a-test-set approach misses most of what can go wrong. A technical account of the eval harness we run, the golden loan files we maintain, the backtest against historical underwriter decisions, and how ongoing monitoring under SR 11-7 and the NIST AI RMF applies to something that behaves more like a colleague than a classifier.

7 min read
Read more
AI Agents

A Copilot Waits to Be Asked: Why the Manual Middle of a Mortgage Needs an Agent That Holds the Goal, and How You Bound What It Does

A copilot's ceiling is the number of hours your staff spend asking it things, which is exactly the resource a mortgage operation is short of. The work that actually clogs a loan runs for days and nobody is sitting there prompting it. What changes when an agent holds the goal instead of answering a question, and the specific controls that keep an autonomous agent inside a boundary an examiner will accept, under SR 11-7 and ECOA.

6 min read
Read more
AI Agents

The First 90 Days of a Mortgage AI Deployment: The Controls We Stand Up Before the Agent Touches a Live File

Most mortgage AI deployments fail at the start, when the agent goes live before the controls that make it safe exist. The first 90 days are a control build, not a rollout. What we run in shadow mode before the agent touches a file, why the go-live gate is set per control instead of globally, and how deploying controls-first is also the posture an examiner expects to see.

6 min read
Read more
AI Agents

AI Agents Inside the LOS: The System-of-Record Boundary, the Write-Back Discipline, and the Audit Trail That Survives an Exam

Most mortgage AI fails not at the model but at the integration. How we run an AI agent against a loan origination system without corrupting the system of record. The propose-then-record pattern, idempotent write-backs, MISMO field mapping, and the change log an examiner will ask for under SR 11-7.

6 min read
Read more
AI Agents

UCC Article 4A and the AI Wire-Verification Architecture: Commercially Reasonable Security Procedures When the Caller Is Verified But the Instruction Is Not

Wire fraud losses are running at multi-billion-dollar annual totals and the legal allocation of those losses runs through UCC Article 4A's commercially-reasonable-security-procedure standard. AI voice authentication of the caller does not, by itself, satisfy the security procedure for a payment instruction. The architecture we run so the bank's Article 4A position holds in court when the instruction was the fraud.

14 min read
Read more
AI Agents

Voice Cloning and the End of Voice Biometrics as a Sole Factor: A Caller-Verification Architecture for Banks

Cheap, high-fidelity voice cloning has collapsed voiceprint and knowledge-based authentication as standalone factors on bank phone channels. The NIST 800-63 level we hold caller authentication to, the phishing-resistant factors that survive a synthetic caller, and the agent-side controls we wire around them.

7 min read
Read more
AI Agents

Prompt Injection Defense for Banking AI Agents: Threat Model, Controls, and a Red-Team Cadence

Prompt injection is the highest-impact attack against an AI agent in a bank because the agent has tools that move money. The threat model, the architectural controls, and the red-team patterns we exercise before every deployment.

7 min read
Read more
AI Agents

Building AI Agents for Open Banking While the 1033 Rule Is Enjoined

Section 1033 was finalized in 2024, enjoined in 2025, and is now under reconsideration. How we architect AI agents for personal financial data sharing so the design survives whichever way the rewrite lands.

6 min read
Read more

You Ain't Seen Nothin' Yet

Book a Demo

Pack up some of your complex historical files — any loan type, any investor. We run them through intake, income and condition clearing, and in 30 minutes you see every condition we created and cleared efficiently for your own team, and why.

  • Any loan type, any agency guideline or custom investor overlays.
  • Every finding cited to the guideline or document it came from

Case study highlight

Loan review fell from 4 hours 50 minutes to 47 minutes per file, and 78% of items now clear at high confidence — so QC touches only the exceptions.

Pre-Close QC Agent · Better Mortgage— read the case study

Please provide your full name so we know how to address you.

Tell us which company you represent so we can personalise our response.

Use your work email. One of our experts will get back to you.

Which desks would you like to discuss?*

Choose the desks you’d like us to cover. Pick “Not sure yet” if you’d rather we worked it out on the call.

Roughly, so we bring the right person to the call.

Complete the verification to submit the form.