Posts on what we actually think.
Essays on conformal prediction, social inflation, and where generative AI helps and where it doesn't. Written by the team.
The Med-Mal Funnel: Most Claims Pay Nothing
The vast majority of medical malpractice claims close without an indemnity payment. Yet carriers bleed defense dollars treating every file like a nuclear threat.
Module Boundaries: Verdict-Heavy vs Settlement-Anchored Data
Jury verdicts are useful for tail risk, trial severity, and what a jury actually does. They are the wrong target for a settlement value. Mixing the two distributions in one model corrupts the forecast.
Verdicts Are Not Payouts
When a jury awards fifty million dollars, the defense rarely writes a check for fifty million dollars. Building predictive models on raw verdict data guarantees an upward bias that will destroy your reserving strategy.
Stop Anchoring Reserves to Headline Verdicts
A plaintiff attorney attaches a news clipping of an eight-figure verdict to a demand letter, and claims teams instinctively spike the reserve. This reaction traps capital, guarantees over-litigation, and fundamentally misprices risk.
Want to talk to an executive?
Press, partners, investors, candidates — the inbox is monitored. Tell us who you are and we'll route it to the right person within two business days.