CADi · Insurance claims
Fair-settlement and manipulated-claim evidence for insurers, defensible on fairness and on challenge.
Evidence a settlement was fair - and grounds to challenge one that was manipulated.
Seeking build partnersCADi Claim is an open invitation: we are looking for partners to build it with us. If you run insurance claims and want the decision evidenced on both sides, we would like to hear from you.
Get in touchEvery claims decision sits in a tension: settle fairly, and control leakage from claims that were inflated or manipulated. Get it wrong in either direction and the insurer is exposed - to an unfair-treatment complaint, or to a loss it could have challenged.
When a settlement is disputed, or a challenge is questioned, the reasoning is rarely captured in a form anyone can rely on. Defending either the fairness of a payout or the grounds for contesting a claim usually means reconstructing the decision after the fact.
CADi Claim evidences how an insurance claim was governed across the tension between fair settlement and claims leakage. It attests the decision; it does not settle or decline on the insurer's behalf.
It produces a decision-level record showing the policy applied, the rationale, the counterfactual the engine estimates and an immutable trace - so a claims team can defend both the fairness of a settlement and the grounds for challenging a manipulated one. It enters as evidence and is designed to graduate toward governing the settlement decision once the evidence loop is trusted.
A record showing a settlement was reached fairly, under policy - evidence for a complaint or a review, without reconstructing the file.
Where a claim was inflated or manipulated, the evidence and the reasoning to contest it, held to the same standard as a fair payout.
Not just the decision taken, but what the engine estimates a different call would have meant - the tension, made explicit.
Runs alongside the insurer's own process first, attesting how claims were governed; graduates toward governing the settlement as trust builds.
Carriers balancing fair settlement against leakage, who must defend both the payouts they make and the claims they challenge.
The teams accountable for fair customer treatment on claims, who need evidence of how a decision was governed rather than an after-the-fact account.
CADi Claim is one product in the CADi range: the same deterministic causal engine - nine layers, a do-calculus core and a hash-chained audit trail - pointed at the claims decision.
It belongs to the reporting layer: it runs alongside the insurer's own systems, evidencing how a decision was governed rather than making it, and is built to graduate into the decision itself once the evidence loop is trusted - enter on evidence, earn the decision.
CADi is at v0.9 - built and running end-to-end - on nine pending UK patents. CADi Claim evidences how a claim was governed; it does not settle or decline for the insurer, and it never guarantees a regulatory or complaints outcome.
The causal mathematics is rigorous and correctly implemented. Today it runs on an assumed causal graph with heuristic inputs; it is analytical approximation on assumed inputs, not yet statistically validated against live outcomes. We lead with the rigour, and we name the caveat.