AI Disclosure Policy

Margie — Pre-Underwriting Analysis Platform

Effective Date: March 23, 2026

Last Updated: October 24, 2026

Document Classification: Compliance — AI Governance

1. Purpose

This AI Disclosure Policy describes how Margie (“Platform”), operated by Margie (“Company,” “we,” “us”), uses artificial intelligence services in its pre-underwriting analysis of mortgage borrower documents. This policy is intended to provide transparency to mortgage brokerages, their compliance officers, and regulators regarding the role, scope, and limitations of AI within the Platform.

Margie is a pre-underwriting analysis tool designed for licensed Illinois mortgage brokers. It does not originate loans, make credit decisions, or serve as a substitute for professional underwriting judgment.

2. Overview of AI Usage

Margie processes borrower-submitted documents through a six-stage forensic analysis engine. AI is used in two narrowly scoped capacities within this pipeline:

1. Optical Character Recognition (OCR) and Structured Field Extraction — AI reads uploaded documents and extracts discrete data fields (e.g., employer name, gross pay, account balances, tax filing amounts).
2. Narrative Analysis Generation — AI produces human-readable commentary summarizing the findings of each analysis stage for broker review.

AI is not used to make decisions, score borrowers, predict outcomes, or determine loan eligibility. The distinction between AI-assisted processing and deterministic analysis is fundamental to Margie's architecture and is described in detail in Section 5.

3. AI Service Providers

Margie uses AI services from one company, Microsoft, in Margie's own Azure account. Azure Document Intelligence receives every page Margie reads; Azure OpenAI receives each stage's results and text read from the pages. Text sent to Azure OpenAI is masked first, as Section 7.2 describes. Margie does not use Anthropic or Google for any AI service.

3.1 Microsoft Azure Document Intelligence

• Function: OCR and structured field extraction from borrower documents.
• Models Used: Prebuilt extraction models including prebuilt-tax.us.w2, prebuilt-payStub.us, prebuilt-bankStatement.us, prebuilt-idDocument, prebuilt-mortgage.us.1003, and additional prebuilt models as applicable.
• Data Transmitted: Uploaded document images or PDFs, transmitted via TLS 1.2+ encrypted connections.
• Data Retention: Microsoft states that Document Intelligence stores the submitted documents and analysis results for 24 hours after an analysis completes and then deletes both automatically.
• Model Training: Margie uses Microsoft's prebuilt models and trains none of its own. Microsoft processes the documents under its Products and Services Data Protection Addendum, which limits its use of customer data to providing the services and the business operations that addendum describes.

3.2 Microsoft Azure OpenAI (gpt-6-luna; gpt-6-sol on standby)

• Function: Margie's notes on each of the six analysis stages; the stage notes; Stage 6's plain-language “Why?” explanation of the file's File Quality rating; reading the borrowers' names from document headers at intake; and reading a field when the typed models could not.
• Where It Runs: In Margie's own Azure account, in a Data Zone deployment in the United States; Microsoft states that for such a deployment prompts and responses may be processed anywhere within the United States. Every call uses gpt-6-luna. If it is unavailable, Margie may move a call to gpt-6-sol, a second model in the same account under the same terms.
• Data Transmitted: Each stage's results (figures, findings and checks) for its notes and, at Stage 6, the “Why?” explanation; the text read from the documents in each stage for the stage notes (on the final stages, the text of every document on the file); the header text of the documents at intake, for the borrowers' names; and, when a field cannot be read by the typed models, the text read from that document. Social Security numbers, numbers of eight or more digits and labelled dates of birth are masked first. The document files themselves are not sent.
• Data Retention: Microsoft states that the models are stateless and that no prompts or completions are stored in the model. Prompts and completions its abuse monitoring flags may be stored in the geography of Margie's Azure resource, the United States, for review by authorized Microsoft employees; no period is stated.
• Model Training: Microsoft states that prompts and completions are not available to OpenAI, are not used by the models' providers to improve their models or services, and “are NOT used to train any generative AI foundation models without your permission or instruction.”

4. How AI Is Not Used

The following limitations are architectural constraints of the Platform, not merely policy commitments:

• AI does not make credit decisions. The Platform does not approve, deny, or recommend loan applications.
• AI does not access credit reports. No credit bureau data is transmitted to or processed by any AI service. The credit score a broker enters can appear in the figures sent to Azure OpenAI for a stage's notes.
• AI does not determine loan eligibility or pricing.
• AI does not perform automated decision-making as defined under applicable consumer protection law.
• AI does not generate risk scores, creditworthiness assessments, or predictive analytics of any kind.
• No AI model is trained on borrower data submitted through the Platform.

5. AI-Assisted vs. Deterministic Processing

Margie's analysis pipeline maintains a strict separation between AI-assisted processing and deterministic rule-based analysis.

5.1 AI-Assisted Processing

AI is used at two points in the pipeline:

AI-assisted outputs serve as inputs to the deterministic engine or as presentation layers for broker review. They do not independently determine findings.

5.2 Deterministic Analysis Engine

Margie's core underwriting analysis is performed by a deterministic rules-based engine spanning six evaluation stages. This engine executes its checks by predefined rule rather than by model inference, including but not limited to:

• Income calculation verification and year-over-year trending
• Employment tenure and stability assessment
• Asset sufficiency and seasoning validation
• Debt-to-income ratio computation
• Document cross-referencing and consistency checks
• Regulatory compliance flag identification

Every check in this engine follows predefined rules and thresholds. No machine learning, neural networks, or probabilistic AI models are used in the evaluation logic. Results are deterministic: the same inputs will always produce the same outputs.

5.3 Why This Distinction Matters

• AI extraction errors can be caught by deterministic cross-checks
• Analysis findings are reproducible and auditable
• No “black box” model influences compliance-relevant determinations
• Brokers can trace any finding back to specific rules and source data

6. Human Oversight Requirements

Margie is designed as a broker-in-the-loop system. The following human oversight requirements are built into the Platform:

1. All AI-generated narrative content is clearly labeled as AI-generated within the Platform interface and in exported reports.
2. Brokers review all findings before taking any action based on Platform output. The Platform does not transmit results to borrowers, lenders, or third parties.
3. The Platform includes explicit disclaimers stating that its output is not a substitute for professional underwriting judgment.
4. Regulatory disclaimers referencing the Equal Credit Opportunity Act (ECOA), Real Estate Settlement Procedures Act (RESPA), and Gramm-Leach-Bliley Act (GLBA) are displayed on all outputs.
5. Brokers retain full discretion over how (and whether) to act on any finding.

7. Data Handling and Security

7.1 Document Processing

• Borrower documents are processed in memory only during analysis. Documents are not written to persistent storage on Margie's servers.
• Every stored field of an analysis that could identify or describe the borrower is encrypted by Margie (AES-256-GCM); so are the audit log's details; what stays readable is ids, dates, document types and the kind and time of each audit event (see the Privacy Policy, Section 2.1).
• All data in transit is protected by TLS 1.2+ encryption.

7.2 Data Minimization

• Azure receives the documents for OCR.
• Azure OpenAI receives each stage's results for its notes and Stage 6's “Why?”, the header text of the documents at intake for the borrowers' names, a document's text when a field must be read by AI, and the text of the documents in each stage for the stage notes. On the final stages that is the text of every document on the file.
• Before any text is sent, Social Security numbers, numbers of eight or more digits and labelled dates of birth are masked first.

7.3 Infrastructure

• Application: Next.js on Azure App Service
• Database: Azure Cosmos DB (encrypted at rest)
• Billing: Stripe (PCI DSS Level 1 compliant)
• Domain: getmargie.com / app.getmargie.com

For complete information on data handling, refer to Margie's Privacy Policy.

8. Model Training Prohibitions — Summary

Margie does not fine-tune, customize, or contribute to the training of any third-party AI model using borrower data.

9. Accuracy, Limitations, and Disclaimers

9.1 OCR and Extraction Accuracy

• Handwritten text, poor-quality scans, unusual document formats, or non-standard layouts may reduce extraction accuracy.
• Extracted field values should be treated as preliminary until confirmed by the deterministic analysis engine's cross-referencing checks or by broker review.
• The Platform's deterministic checks are specifically designed to catch extraction inconsistencies.

9.2 Narrative Generation Accuracy

• Narratives may occasionally contain imprecise characterizations of findings.
• Narratives are summaries for broker convenience, not authoritative compliance determinations.
• All narrative output is clearly labeled as AI-generated.
• Brokers should verify narrative claims against the underlying extracted data and deterministic findings.

9.3 General Disclaimers

• Margie is a pre-underwriting analysis tool, not a licensed underwriter, lender, or credit decision system.
• Platform output does not constitute a loan approval, denial, pre-qualification, or pre-approval.
• Platform output does not constitute legal, financial, or compliance advice.
• All findings are advisory and require review by a licensed mortgage professional before any action is taken.
• The Platform is designed to operate consistently with applicable provisions of the GLBA, ECOA, and RESPA. Compliance disclaimers are affixed to all outputs. Compliance obligations for a given loan file remain with the licensed originator.

10. Contact Information

Questions regarding this AI Disclosure Policy or Margie's use of AI should be directed to:

Margie
Email: contact@getmargie.com
Website: getmargie.com

11. Policy Updates

This policy may be updated to reflect changes in AI service providers, processing methods, or applicable regulatory guidance. Material changes will be communicated to active subscribers. The “Last Updated” date at the top of this document reflects the most recent revision.

This document is provided for compliance transparency purposes and is intended to be reviewed alongside Margie's Privacy Policy, Terms of Service, and GLBA Compliance Statement. A Data Processing Agreement is available upon request for brokerage partners.