---
title: "Mortgage lending"
description: "Document Processing splits a 500-page loan package into its documents and extracts every figure with a citation, so processors and underwriters start from the facts."
canonical: "https://nace.ai/industries/mortgage-lending"
updated: 2026-11-06
---

# Mortgage lending

> Document Processing splits a 500-page loan package into its documents and extracts every figure with a citation, so processors and underwriters start from the facts.

## The whole loan file, read and cited.

Document Processing splits a 500-page loan package into its documents and extracts every figure with a citation, so processors and underwriters start from the facts.

Runs on: Document Processing (reads).

| Value | Result | Source |
| --- | --- | --- |
| 36 | file types, scanned or digital | [Perception evaluation](https://nace.ai/perception) |
| #1 | on grounding in Nace's Perception evaluation | [Perception evaluation](https://nace.ai/perception) |
| <½ | the price of the best tool we tested, at the same accuracy | [Perception evaluation](https://nace.ai/perception) |

Trusted by: Mountain America Credit Union, Prosper.

## Processors spend hours finding the page before they can check it.

Loan files arrive as one long scan. Before anyone can verify income or clear a condition, someone has to find the W-2, the pay stub and the appraisal inside it. Document Processing does that part in minutes.

## Where Nace fits

Document Processing does the reading. Your team and systems take it from there.

| Workflow | What it does | Model |
| --- | --- | --- |
| Package splitting | A 500-page upload split into the 1003, W-2s, pay stubs, statements and disclosures. | Document Processing |
| Income and assets | Income and balances pulled from stubs, W-2s, returns and statements, each figure cited. | Document Processing |
| Appraisal and title | Value, comparables, liens and exceptions extracted from appraisals and title commitments. | Document Processing |
| LE and CD comparison | Fees and terms from the Loan Estimate and Closing Disclosure, extracted line by line. | Document Processing |
| Document classification | Every new borrower upload labeled against your own document taxonomy. | Document Processing |
| Scans and photos | Scanned and photographed pages read the same way as digital ones. | Document Processing |

## Conditions review, end to end

1. Borrower uploads: New documents for open conditions
2. Document Processing splits: Each document found and labeled
3. Document Processing extracts: Every figure, cited to its page
4. Your processor: Clears conditions from cited facts
5. Drex for Search finds: Any loan file, cited to its page

What it reads: Form 1003, Pay stubs, W-2s, Tax returns, Bank statements, Appraisals, Title commitments, Loan Estimates, Closing Disclosures.

## Runs where your data already lives.

Same models and the same API at every tier. Only the boundary around your data changes.

- Managed Cloud: Our GPUs, our API, a key from Console.
- Dedicated Cloud: Your own cluster in our cloud, reached over private links.
- Your Cloud: Installs in your AWS or Azure account. Data stays inside.
- On-Prem & Air-Gapped: Your datacenter, your hardware, zero outbound.

SOC 2 Type II audited. [Visit the Trust Center](https://trust.nace.ai).

## See it on your own files.

Send us a file and the decision you make on it. We'll show you the result on your own documents.

- [Get started](https://console.nace.ai/?utm_campaign=industries&utm_content=industry-mortgage-lending_md&utm_medium=website&utm_source=nace.ai)
- [Talk to sales](https://nace.ai/contact?source=industry-mortgage-lending)

Related industries: [Banking](https://nace.ai/industries/banking) · [Accounting](https://nace.ai/industries/accounting) · [Legal](https://nace.ai/industries/legal)

## For agents

- [Drex API guide](https://nace.ai/drex.md): the decision model: request shape, question types, benchmarks and deployment, as markdown
- [Decision endpoint](https://console.nace.ai/v1/systemone): POST with model "drex-latest", a state string and typed questions (choice, noul, score); https://console.nace.ai/v1/models lists checkpoints
- [Document endpoints](https://console.nace.ai/v1/documents/{parse|split|classify|extract|ground}): POST a source (a public URL, an uploaded workspace file or a finished parse job) and poll GET https://console.nace.ai/v1/documents/jobs/{id}; the same key and credit as decisions
- [Console](https://console.nace.ai): API keys, the playground, usage and billing; send `Authorization: Bearer $NACE_API_KEY` on every request
- [Console docs](https://console.nace.ai/docs): quickstart, question types, the document routes, errors, limits and pricing
- [Nace Document Processing](https://nace.ai/perception.md): the Perception series: parse, split, classify, extract and ground any file type with a location on every value
- [Drex for Search](https://nace.ai/drex/search.md): Drex for Search: decision-powered retrieval for agents, Drex finds the page, cited search through the CLI, SDKs, MCP and REST, and the public benchmark ranks
- [Industries](https://nace.ai/industries.md): Nace by industry: the files Document Processing reads and the decisions Drex makes for accounting, banking, mortgage, insurance, legal, healthcare, government, construction, logistics and professional services
- [Developers](https://nace.ai/developers.md): The execution layer for agents: Perception, Decision and Search behind one key, the Drex Max frontier, install steps, a scripted agent session and the four deployment boundaries
- [Site index](https://nace.ai/llms.txt): every page on nace.ai; append `.md` to any page URL or send `Accept: text/markdown` for the markdown version