A complete demand letter, built to be defended.
Every Predict prediction exports as a full demand letter — drafted in your firm's own style and formatting, PDF or Word — built on the case value, the 90% confidence band, the cited comparable cohort, and the four facts that moved the number. The artifact that turns "we value the case at $148K" into "we value the case at $148K and here's why."
New to Predict? Predict is a case-value model for plaintiff MVA and premises cases, jurisdiction-tuned and shown with confidence bands. You can run a free prediction before you sign up; the demand-letter export ships with the trial.
Comparable cohort
This case value is grounded in hundreds of same-jurisdiction, same-severity rear-end MVA verdicts and settlements from Texas, between 2018 and 2025. The cohort excludes catastrophic-injury outliers and out-of-state cases. The 90% confidence interval reflects the spread of the comparable cohort, not a generic margin.
The four facts that moved the prediction
- Injury severity tier: moderate — soft-tissue, six months of treatment, no surgical intervention. Anchors the case value to the moderate-severity Texas cohort, not the minor-severity cohort. Injury severity is the single largest driver of the number.
- Medical specials: $18,400 across orthopedic and chiropractic providers. Inside the 25th–75th percentile band for the comparable cohort.
- Property damage: $4,200 — low-speed impact. Note: PD is weakly correlated with case value in the moderate-severity cohort; the model deweights it accordingly.
- Commercial vehicle: defendant operating a commercial vehicle, a feature the model weighs directly — commercial-defendant cohorts run materially higher than personal-vehicle comparables.
Methodology & reliance
The case value is produced by Predict (predict.law) using the current model, trained on over 20,000 precedent cases and 200,000 data points — roughly 70% jury verdicts, the rest settlements; held-out MdAPE accuracy (median absolute percentage error against actual case outcomes) on Texas MVA cases runs 88–92%, reaching the top of that range on higher-value cases. The number is gross case value — before attorney fees, case costs, and medical liens. See how the band is built and recalibrated at predict.law/how-it-works.
A full demand letter, built on four defensible foundations.
The number + the band
Predicted case value with the explicit 90% confidence interval. Never a single number — never a range without a median. The pair is the load-bearing claim the letter is built around.
The comparable cohort
The verdicts and reported settlements that informed the case value — same case type, same jurisdiction, same severity tier. With the cohort size, year range, and the filtering criteria used.
The four facts that moved it
Plain-language reasons for the number, computed per case (the model attributions, surfaced as SHAP values): which inputs pushed the value up, which pushed it down, by how much. The "why this number" question, answered in the letter.
Methodology & reliance
Corpus size, MdAPE accuracy on the case-type fold, and a public link to how the model works. The adjuster can't claim "the AI made it up."
See how the band is computed and recalibrated at predict.law/how-it-works.
The same demand letter, on either side of Predict.
The legal arguments and tone stay the attorney's. The valuation — where every demand letter either lands or gets dismissed — is what Predict drafts, in your firm's own language.
"Based on the severity of our client's injuries, the duration of treatment, and comparable cases handled by this office, we value the case at $120,000. We are prepared to litigate."
One number. No band. No cohort. No citation. The adjuster reads this as a negotiating opener and counters low.
"We value the case at $148,000, with a 90% confidence interval of $126,000–$170,000, derived from a cohort of same-jurisdiction, moderate-severity rear-end MVA verdicts and settlements. The full methodology and held-out accuracy figures are public at predict.law/how-it-works."
Number, band, cohort, methodology link — drafted into a complete letter in your firm's style. A cited, banded number gives the adjuster something to respond to on the merits rather than a round opener to discount. We don't claim a specific dollar lift; we show the methodology and let the file speak.
From a prediction to a finished demand letter.
- 1
Start the trial, then run the prediction
Start the free trial, then answer six questions (about 60 seconds). The case value comes back with the band, the cohort, and the four facts already attached.
- 2
Click Export → PDF or Word
Predict drafts a complete demand letter in your firm's own style and formatting — PDF, or a Word document with editable headings — so you can drop it under your letterhead and adjust tone without rebuilding the substance.
- 3
Review, sign, and send
The legal arguments, recovery theory, and tone are the attorney's; the letter is yours to edit. The case value, the band, and the cited methodology are Predict's — and the methodology is in the open.
Quick answers.
Is the export available on the free trial?
Yes — the trial includes the full demand-letter export with the cohort and the feature attributions. The public valuation returns the number and the band, but not the letter.
Does it match my firm's style?
The letter is drafted in your firm's own style and formatting, with editable headings and no fixed letterhead. Drop your firm's letterhead in the document header and edit the language freely; the case value, band, and cited methodology stay intact as the substance of the demand.
How do I cite Predict in the demand letter?
The letter auto-includes a methodology-reliance paragraph with the corpus size, MdAPE accuracy on the case-type fold, and a link to predict.law/how-it-works. Counsel on the other side can read how the model works; the page is public.
What does it cost after the trial?
$499 per seat / month, single tier, with unlimited demand letters on every prediction. The 14-day trial is $0 today — you add a card to start, but it sits on file and isn't charged during the trial, and you can cancel in one click. At day 15 the card on file is charged $499 per seat; before then, nothing. Full pricing and limits are at predict.law/pricing.
Can I edit the number before exporting?
No — and that's a brand commitment. The letter carries the model's case value, not an attorney-adjusted number. You can edit the legal language and tone freely, but editing the model output and presenting it as model output is exactly the failure mode our methodology discipline is built to prevent.
Draft one demand letter on a real case from your docket.
The 14-day trial includes the full demand letter, the cited cohort, and the four-facts attribution on every prediction. $0 today — card on file, cancel anytime; nothing is charged until day 15. The first letter drafts the moment the first prediction completes.