A 2% fee cap and a 31 December 2027 deadline.
RECA claim documentation review checks a uranium worker, downwinder, or onsite-participant file against 28 CFR Part 79, which names the exact pathology and diagnostic evidence each compensable disease requires. We check the file against that list before the claim goes to DOJ, not after it comes back denied for evidence that was missing from the start.
The rulebook is published. So is the referee.
We do not build for a case type until we can name the standard that defines a correct output and the person who grades the file against it. In RECA claims work, both are already in federal statute and regulation — and the 2025 reauthorization means volume is rising fast, with an estimated 30,000–80,000 claims expected in the 29-month filing window.
Three steps between the file and DOJ.
Send the file
Claim intake records, exposure history, and diagnostic files, as they actually arrive, in any format. In the demo case, 342 pages across 2 packets, with a wrong-patient page quarantined before the read starts.
The AI checks it against 28 CFR Part 79, every line cited
Compensable-disease pathology, diagnostic evidence, and exposure site and dates, extracted and matched against the regulation's requirements — page-cited, not summarized from memory.
You file, DOJ decides
The review supports the claim your attorney files, inside the 2% initial-filing fee cap. The DOJ Civil Division issues a written approval or denial that specifies any evidentiary deficiency.
A documentation review that knows it isn't the determination.
We check the file against 28 CFR Part 79 and cite what supports the claim and what's missing. We do not determine eligibility, assign a compensation category, or file the claim — those decisions belong to the DOJ Civil Division, the claimant, and their attorney.
In the demo case, page 140 turned out to belong to a different patient. The review flags it and quarantines it in its own line, instead of folding it silently into the file DOJ receives.
The rules the platform never breaks.
EVERY LINE CITED
HIPAA, under a signed BAA
Every file is handled under our Business Associate Agreement, from the first byte.
Never trains a model
Your records are never used to train any AI model — ours or anyone else's.
Every line cited
If we can't cite it, we don't say it. Every sentence links to its source page.
Deleted after delivery
Files are deleted 30 days after delivery, with a full audit log of every access.
Four capabilities behind every evidence review.
The RECA evidence review is one deliverable of the same platform that reads, sorts, and cites the whole record.
Medical Records OCR
Every exposure record and diagnostic file read in full — PDFs, scans, handwritten clinic notes — nothing skipped, nothing guessed.
Medical Chronology
The exposure and treatment timeline builds itself from the claim file and supplemental records, synced to every source page.
Verifiable AI Citations
If we can't cite it, we don't say it. Every pathology and diagnostic finding links to the page range it was pulled from.
Medical Summary Reports
The evidence review formats straight into the documentation your attorney files with DOJ — your template, your letterhead.
RECA claim documentation review, answered.
Send one file. We'll tell you what we can read.
No obligation. If the case type is buildable we'll scope it; if it isn't, we'll say so.