In active build · Early access open

Mass tort.
Coordination at scale.

The same expert, simulated thousands of times across an MDL docket. Each simulation returns a brief (likely opinion, cross-examination weaknesses, methodology challenges, settlement-range implications) in minutes. Build the methodology once. Apply it across every matter the firm coordinates.

Individual simulations are $50 each. Example cases are free on a firm email address, and firms run on credit plans with volume pricing. See pricing.

In active build
Illustrative preview
Causation Toxicologist (every-exposure)
Toxic tort · every-exposure causation, MDL docket
01
Likely opinion
General and specific causation argued via the every-exposure theory.
02
Cross-examination weaknesses
Dose-response gaps; every-exposure rejected in Krik, Bostic, Anderson.
03
Methodology challenges
FRE 702 / Daubert: general acceptance, error rate, peer review.
04
Settlement-range implications
Docket-wide exposure shifts if causation survives Daubert.
The Thesis

Mass tort is methodology compounding at scale. The same expert, the same Daubert weapon, the same brief, across the entire docket.

Frontier AI has compressed the cost of a brief to $50 per simulation. We publish the cost it displaces only where we have measured it, which so far is securities and antitrust; the mass-tort figure is not ours to quote yet. What is already true here is structural: for coordinating counsel the compression is multiplicative rather than per-matter. The "every-exposure" Daubert weapon (Krik v. Exxon, Bostic, Anderson) anchors toxic-tort causation work across asbestos, talc, PFAS, and Roundup dockets. The OB-nursing and ACOG fetal-monitoring methodology anchors birth-injury work. The trucking-safety / FMCSR expert anchors nuclear-verdict trucking practice. Each expert is the same expert pattern across thousands of matters. Build the brief once at MDL coordinating-counsel scale, and the per-matter unit economics of every downstream filing changes.

The Library

The flagship cluster. Building first.

The experts that anchor plaintiff PI and mass-tort practice. Each is a de-identified composite of a class of testifying expert, built from public depositions, trial transcripts and Daubert rulings, and never a named individual. Sequenced for first build.

O-016 · Flagship
Causation Toxicologist (General & Specific)
The "every-exposure" Daubert weapon. Krik v. Exxon Mobil Corp., 870 F.3d 669 (7th Cir. 2017) and Anderson v. Ford Motor Co., 950 F. Supp. 2d 1217 (D. Utah 2013) excluded the theory as expert testimony; Bostic v. Georgia-Pacific Corp., 439 S.W.3d 332 (Tex. 2014) held it legally insufficient on causation. The gold-standard methodology cross across asbestos, talc, silica, and PFAS dockets.
O-017
Industrial Hygienist (Asbestos / Silica)
Exposure modeling, dose reconstruction, OSHA permissible-exposure-limit framework, and historical-exposure attribution under cross.
O-030
Epidemiologist (PFAS / Roundup / Talc)
Bradford Hill criteria, dose-response modeling, confounding-variable analysis, and the relative-risk threshold debate that anchors mass-tort causation.
M-064
OB Nursing / Birth Injury
Electronic fetal monitoring interpretation, ACOG standards, expert-witness qualification scrutiny, and birth-injury causation patterns under Daubert.
M-082
Pharmacology / Pharmacovigilance
Drug-causation analysis, adverse-event signal detection, FDA adverse-event-reporting-system data, label-warning adequacy under failure-to-warn theory.
O-073
Trucking Safety / FMCSR
Federal Motor Carrier Safety Regulations, hours-of-service compliance, negligent-hiring and supervision expert patterns. High-density nuclear-verdict practice.
E-024
Product Defect Engineer
Crashworthiness, design-defect alternative-design analysis, failure-mode-and-effects analysis, and the Restatement (Third) consumer-expectation test.
E-001
Biomechanical Engineer
Shared with the PI cluster. FEA mesh resolution, MADYMO/ATB calibration, HIC/CSDM strain metrics: the foundational biomechanical-engineering standard for the field. Critical for mass-tort matters with traumatic-injury components.
How it works

Matter-first. One brief, grounded in the record.

The deliverable is the Exposure & Settlement Brief: four sections, every supporting quote verified against the public record.

01

Create a matter

Set up the case and upload documents. The file is extracted and available to the analysis.

02

Add experts

Add one or more de-identified experts: the opposing expert, or your own retained expert.

03

Ground it

Ground the analysis in extraction from your uploaded case documents: expert reports, depositions, and filings in the matter.

04

Generate the brief

Produce the Exposure & Settlement Brief: likely opinion, cross-examination weaknesses, methodology challenges (Daubert / FRE 702), and settlement-range implications.

Verbatim citation verification

Every supporting quote is checked verbatim against public-record sources. Quotes that cannot be verified are dropped, not guessed.

Cross-examination practice simulation

Rehearse the exchange against the expert before the deposition: question, answer, follow-up.

Examine the record

Put a question to the case file, the complaint, the opposing report, the brief, and get an answer cited to the page, read as the opposing expert would. When the record is silent, it says so instead of guessing.

Expert-report stress test

Attack an opposing report for its weak points, or red-team your own retained expert's draft before it is served.

Exports built for the file

Export to Word, a Daubert-motion outline, and a cross-examination outline, plus PDF, copy, and email. Deliverable history is retained.

Named-expert overlay

Where warranted, optionally overlay a specific expert's public judicial record. Admin-controlled, not on by default.

Security & Trust

Built for privileged work. Confidentiality is the product.

Matter content is handled as privileged material end to end: where it runs, where it is stored, and what is ever written to a log.

Passwordless sign-in

Magic-link sign-in tied to a named person: a one-time link to a work email. No password to phish or manage.

Firm accounts & admin

Firm accounts with a firm-admin role and self-service team management across multiple devices.

Server-side model

The model runs server-side. The browser never holds an API key.

US-pinned, Zero-Data-Retention

Inference is US-pinned and routed only through Zero-Data-Retention-eligible endpoints. Matter content is not used to train third-party models.

Per-firm US-region isolation

Per-firm data isolation in a US-region database; uploaded documents in a US-region store.

Metadata-only audit; 30-day deletion

Metadata-only audit logging; privileged content is never logged. Deleted matters are removed after a 30-day recovery window.

Pilots add SSO, RBAC, immutable audit logging, and a signed Anthropic data processing addendum (DPA) plus Zero-Data-Retention addendum.

Request early access

Early access on one matter. Shape the build queue.

We're opening early access to a small number of firms: MDL coordinating counsel and senior trial partners at mass-tort firms. One named matter, your choice. Public-record training data only. Direct line to the founding team. Pipeline pull moves the queue; if your matter is in flight, the expert it needs gets prioritized.

Request early access →
What early access looks like
Scope
One named matterYour docket, your expert targets, defense or retained.
Timeline
30 daysExpert build in days one through ten. Live use through day thirty.
Price
$50 a run, one run minimumCredits are bought in the app in any quantity, spendable across any matters by anyone on your firm domain, and they never expire. Example cases are free before you spend any of it. Full pricing.
Data
Public record onlyPACER, RECAP, court transcripts, peer-reviewed publications.
Access
Direct founder lineNo CSM tier. Founding team handles delivery and feedback.