---
title: "Affidavit Mapp: Court-ready bank statements, days to minutes. 99.7% data integrity."
description: "Family-law firms drown in bank statements. We built a secure OCR + LLM pipeline that turns raw PDFs into court-admissible reports in minutes, not days. It uses strict grounding, full chain-of-custody, and hits 99.7% data integrity measured against ground truth."
source: "https://www.kensink.com/cases/affidavit-mapp/"
---
LEGALTECH · DOCUMENT AI Affidavit Mapp (US) · US

# Affidavit Mapp.  
Court-ready bank statements, days to minutes.

99.7% data integrity.

99.7%

Data integrity vs. ground truth

OCR + LLM PIPELINE LEGALTECH · DOCUMENT AI

## Affidavit Mapp: Court-ready bank statements, days to minutes. 99.7% data integrity.

Family-law firms drown in bank statements. We built a secure OCR + LLM pipeline that turns raw PDFs into court-admissible reports in minutes, not days. It uses strict grounding, full chain-of-custody, and hits 99.7% data integrity measured against ground truth.

[View .md](https://www.kensink.com/cases/affidavit-mapp.md)

99.7%

Data integrity vs. ground truth

Days→min

Per-case processing time

100%

Outputs grounded to the source PDF

8 wk

Kickoff → production for first firm

01 · THE PROBLEM

## Where they were stuck.

Family-law analysts were spending entire days per case reading bank statements line by line, building spreadsheets that would later be sworn into court. The variance between analysts was high; the audit trail was a folder of Excel files; and the bottleneck was the analyst, not the law. Existing 'AI document tools' produced confident-looking nonsense: hallucinated transactions, dropped pages, no verifiable source.

02 · OUR APPROACH

## How we built it.

-   01 Layered OCR: open-source OCR engine for structure + a vision-LLM pass to recover degraded scans, falling back to manual review only for low-confidence pages
-   02 Retrieval-Augmented Generation grounded against the source PDF: every extracted transaction carries a page reference + bbox so the answer is verifiable back to the original
-   03 Strict eval suite of 1,200 manually-labeled statements as ground truth, run on every model change; production gated on field-level precision/recall thresholds
-   04 Chain-of-custody: SHA-256 hash of the source PDF, all model outputs signed with extraction timestamp, full audit log per case
-   05 Court-admissibility formatting: output post-processed into the exact report shape that judges accept, with no creative formatting
-   06 Confidentiality boundary: processing inside the firm's tenancy, source documents never leave their cloud

> “When opposing counsel can't poke a hole in your output, that's when you know the system works. We've been through depositions on this data with zero challenges sustained.”

_Research Director

Affidavit Mapp_

\[TECH STACK\]

-   Python
-   OCR engine
-   Object storage
-   Multimodal LLM
-   Postgres
-   Eval framework

\[ENGAGEMENT\]

Duration Multi-engagement advisory (2024)

Client Affidavit Mapp (US)

Shape OCR + LLM PIPELINE

Handoff Full ownership · 90-day warranty

START YOUR OWN PROJECT

## Bring a real problem.  
We’ll bring code on day one.

[Start your own project →](https://www.kensink.com/contact) [Book a 15-min intro](https://www.kensink.com/contact)

[← All cases](https://www.kensink.com/cases) CASE · AFFIDAVIT-MAPP