Log in Legacy app
How it works

Six questions in. A defensible number out.

Predict turns a one-minute case description into a confidence-banded gross case value — before attorney fees, case costs, and medical liens — jurisdiction-tuned and cited to a cohort of comparable verdicts. As the case develops and new facts arrive, you re-run it: the number updates and the band tightens, from intake through demand letter and settlement. Here's the version without the math.

Predict your case See it in a demo Free · 60 seconds · no signup to start
  1. 1

    Describe the case

    Six questions: case type, jurisdiction, injury severity, medical specials, property damage, defendant posture. The same facts the senior partner asks for at the intake meeting.

    ≈ 60 seconds · no signup
  2. 2

    We match the cohort

    The model matches a cohort of comparable verdicts and reported settlements — same case type, same county or state, same severity tier. Per-state cohorts run into the hundreds to thousands. The cohort is the methodology.

    Stratified jurisdiction folds · 17 states supported
  3. 3

    You see the band, not just the number

    A median prediction plus a 90% confidence interval. The number is the headline; the band tells you when the cohort is thin and the answer is less certain.

    90–92% median accuracy (MdAPE) on higher-value cases — see the accuracy results →
  4. 4

    Export the demand letter

    Inside the trial, every prediction drafts a full demand letter in your firm's own style and formatting — PDF or Word — with the number, band, cohort, and the facts that moved the prediction.

    Unlocked in the 14-day trial
Inside the product

From six questions to a defensible number — what each screen looks like.

The intake is built around the band — every answer narrows the confidence interval, visibly. When the last question lands, the case-detail view opens to the headline number, the comparable cohort, and the firm's own acceptance threshold. No back-office report. The workspace.

Step 1–3 · Intake
The intake flow with the live preview panel — every answered question narrows the confidence band in real time.
Step 4 · Case detail
Illustrative example. The case-detail view that opens after the prediction lands — number, jurisdiction cohort, acceptance threshold, comparable verdicts, and the demand-letter export, all on one screen.
Illustrative example

What you actually get back.

Illustrative example of the output shape. The structure — number, band, cohort — is real; the figures shown are for illustration, not a named client outcome.

Soft-tissue rear-end, Harris County, Texas. Mid-five-figure med-specials, six months of treatment, moderate severity tier. A low carrier first offer on a case like this is the kind of anchor Predict is built to test.

Predict returns a band in about 60 seconds, sourced to a same-jurisdiction, same-severity cohort of comparable verdicts and reported settlements. That cohort is what you cite in the demand letter.

  • The number is the headline. The median gross case value of comparable cases, before attorney fees, case costs, and medical liens.
  • The band is the methodology. The 90% interval means 9 of 10 similar cases land in the range.
  • The cohort is the proof. Same county, same severity, same case type — openable in the trial.
See how the band is computed →
Illustrative example
$148,000
± $22,000 · 90% CI
TX · HARRIS · MVA
A low first offer sits well below this band. The number is the headline; the band is the methodology, and both are cited to the cohort.
What's in the prediction

Three things Predict puts on the plaintiff's side of the table.

Insurers value cases with data and claim history. An attorney working from gut and a verdict search usually does not have the same footing. Every Predict output ships with the same three load-bearing pieces, and each one answers a question an adjuster, a partner, or a judge will eventually ask.

Confidence-banded predictions

The number is the headline. The band is the methodology.

Every prediction comes with a 90% confidence interval — derived from quantile regression against the comparable cohort, not bolted on. The band widens when the cohort is thin or the severity is catastrophic. It's the part of the output that survives the carrier's "where did you get this number?" — and the part that tells you when to slow down before you take the case.

9 of 10 cases with the same input profile settle inside the published range. The other 10% are the long tail — flagged, not hidden.

See the accuracy results →

Jurisdiction-tuned

Houston isn't Dallas. The model knows.

Injury severity and direct damages drive case value most, with jurisdiction close behind — state and county PI economics vary widely, and a jurisdiction-agnostic model would misprice high-recovery and low-recovery venues alike. Predict supports 17 states for motor vehicle cases and 12 for premises liability; the four densest cohorts — Texas, Florida, California, and New York — have county-level folds for the highest-volume counties (Harris, Los Angeles, Bronx, Miami-Dade, and more) and the tightest bands. Coverage beyond those generalizes with wider confidence bands where verdict density is thinner.

17 states supported for MVA (12 for premises liability) · the four densest cohorts (TX · FL · CA · NY) carry the tightest bands.

See how the cohort is matched →

Cited comparable verdicts

A comparable cohort behind every number.

Inside the trial, every prediction cites the comparable cohort — verdicts and reported settlements from the same jurisdiction, same case type, same severity tier, with the closest comparables surfaced first. The citation includes outcome amount, jurisdiction, severity, and medical specials. The basis you cite in the demand letter when the adjuster asks where the number came from.

Over 20,000 precedent cases and 200,000 data points · plaintiff-side only · no carrier data ever.

See the data behind the model →

A verdict database hands you a list. Predict hands you a number you can defend.

A verdict-search database returns a stack of cases and leaves the math to you, with no way to tell when the comparable set is too thin to lean on. Predict matches the comparable cohort, returns a single calibrated number with a 90% band, and widens the band, or declines to answer, when the comparable set is too thin to defend. The list is the input. The defensible number is the output.

Built around the moments that actually move the case.

Predict isn't a back-office report. It's an instrument designed for three specific moments where the case value gets decided — or fumbled.

At intake

Run the case in 60 seconds before you take it. Triage by number, not by gut.

At the demand letter

Anchor the demand to a defensible band cited to comparable verdicts. The carrier responds to methodology.

At partner review

Same number across the firm. The senior reviews methodology, not math.

Quick answers

The short version of how the model works.

How accurate is the model?

90–92% median accuracy (MdAPE) on the held-out test set for higher-value cases, by case type — 88–92% on motor vehicle accidents, 87–93% on premises liability. Measured on a held-out test set the model never trained on, from the 2018–2025 verdict window. Recalibrated quarterly. See the accuracy results →

What's the training data?

Over 20,000 precedent cases and 200,000 data points — jury verdicts and reported settlements from 2018–2025. Plaintiff-side and publicly-available records only. No claims-side carrier data is used in training, and none will be.

What case types are supported?

Motor vehicle accidents and premises liability. Medical malpractice, mass tort, workers compensation, and family law are out of scope at launch — and the model won't produce a prediction outside its calibrated case types. We'd rather say "not yet" than ship a number we can't defend.

What about my jurisdiction?

The model supports 17 states for motor vehicle cases and 12 for premises liability. Four of them — Texas, Florida, California, and New York — carry the densest verdict cohorts and the tightest bands, with additional county-level folds for the highest-volume counties (Harris, Los Angeles, Bronx, Miami-Dade, Dallas, Bexar, Kings, Queens, and more). Coverage beyond those generalizes with wider confidence bands where verdict density is thinner. We'd rather widen the band than overstate certainty.

What if Predict gets a case wrong?

If a prediction lands outside the 90% confidence band, we recalibrate that jurisdiction and disclose it. Brand commitment, not a marketing line. We publish the recalibration policy and the current model version, and disclose misses rather than bury them.

Does Predict replace my judgment?

No. Predict is a statistical estimate of likely case value — not a legal opinion, not a trial-verdict prediction, not case strategy. The attorney owns the legal judgment; the model owns the math.

No customer logos here yet, on purpose. Predict launched in 2026, so we don't have a wall of attorney numbers to show. Instead we show the work: the held-out test methodology, the 90% confidence interval math, and the quarterly recalibration log are all published in full. Every number on this page traces back to it.

See the accuracy results →

Pricing

One number. One plan. $499 per seat.

A 14-day trial that doesn't ask for a credit card, followed by a simple per-seat monthly price — no tiers, no negotiation, no procurement process.

$0
First prediction · no signup
14 days
Free trial · $0 today
$499/mo
Per seat · unlimited predictions
See full pricing →