Project: PriorStatement.com

Tl;dr: An assertion-comparison engine for litigation.

What it does

Most eDiscovery tools index keywords. PriorStatement indexes assertions.

It ingests the entire case file — transcripts, witness statements, police reports, medical notes, expert reports — and builds a profile of every assertion made by or attributed to each witness. Not just what they testified to in deposition, but what they told the police three months earlier. What the medical records say they reported. What third-party witnesses claim they said.

Then it cross-references everything against everything. Same witness, different statements, across time. Same event, different accounts. Every version is anchored to the timeline. Every contradiction, omission, and inconsistency surfaces automatically. It builds a graph (in computer science terms) of the whole evidential base.

What takes a litigation team a week of manual comparison takes an hour with PriorStatement.

Why it matters

Prior inconsistent statements are the most powerful impeachment tool in cross-examination. They’re also the easiest to miss when you’re working across hundreds of documents, multiple witnesses, and years of testimony.

Human review is pattern-matching at scale. Humans get tired. They skim. They focus on the obvious and miss the subtle. An assertion buried in paragraph six of a police report contradicts something said in paragraph twelve of a deposition transcript — and no one catches it until trial prep, if at all.

PriorStatement doesn’t skim. It doesn’t get tired. It maps every assertion to every other assertion and extracts what’s usable.

How it works

Entity resolution. Timeline anchoring. Assertion extraction and comparison across the entire corpus.

The result is not a keyword search. It’s a logical map of who said what, when, to whom, and whether it holds together.

Deployment

PriorStatement runs two ways:

Cloud-based: Standard SaaS deployment for firms comfortable with cloud infrastructure.

Air-gapped: A local inference server and local PriorStatement server deployed entirely on the firm’s closed network. No internet connection. No data leaves the building. Full capability, zero external exposure.

The air-gapped option is designed for work that cannot touch the cloud — government contracts, national security litigation, cases under strict confidentiality obligations. To our knowledge, nothing else in legal AI offers true on-premises inference at this level.

Availability

PriorStatement is currently in private beta with select law firms in London and is not yet publicly available. Enquiries should be directed to luke.cohen@citation.al.

Citational is an AI research and development lab dedicated to law. We build verification infrastructure and specialized models for legal reasoning.