Published Studies

Published
OCR Quality Extraction Architecture Data Sovereignty Audit Trail

OCR & Extraction Benchmark Framework for Insurance Documents

Five evaluation groups for insurance document intelligence. The first four map to standard dimensions. Group 5 — audit and compliance — is where the field narrows.

Read the framework →
Published
Architecture Sovereignty Tool Selection

The Six-Tier Extraction Stack

Which tool should we use? Wrong question. The right question is which tier the field requires. Tier determines tool, infrastructure, and sovereignty posture.

Read the framework →
Published Premium
WC FNOL Hallucination Analysis Audit Defensibility

The Extraction Intelligence Benchmark

Three architectures on a 7-page NY WC FNOL with a dual-employer layout trap. The approach marketed for its audit trail hallucinated the claimant's name and date of injury. Zero-LLM extracted 19/19 deterministic fields.

Read the case study →

In Progress

In Progress
FNOL Police Reports

Regex vs. LLM on Structured Fields

Head-to-head on Cat 1 fields — VIN, DL#, DOB, policy number — across 200 FNOL and police report documents.

Coming soon
In Progress
Scanned Docs Tables

Scanned Doc Quality: Tesseract vs. Granite-Docling

DPI degradation curve at 300/200/150/75 DPI across 50 scanned insurance documents.

Coming soon

If the problems in these cases
sound familiar, let's talk.

We work with insurers and MGAs who are serious about the architecture — not just the demo. Conversations start with the problem, not the product.