CapSeal - Motor insurer scenario

This is an illustrative scenario, not a customer. CapSeal is pre-launch. Every figure below is modelled from published industry data and stated assumptions, which are set out in full further down so you can disagree with them. We will replace these with named, measured references when we have them, and not before.

The situation

Where the organisation starts

A motor insurer handling roughly 40,000 claims a year takes damage photographs through its own app and by email.
Assessors review photographs by eye. Anything that looks wrong goes to the special investigations unit, which has capacity for a fraction of a percent of volume.
Generative editing has made a plausible dent cost nothing to produce. The insurer's own view is that it is paying claims it should not, and cannot say which.

Modelled outcome

What the model produces

62%

of claims auto-payable on sealed evidence

3 min

median time to decision, from days

1.1%

of intake carrying a veto signal

$1.9M

modelled annual leakage addressed

The assumptions behind those numbers

40,000 motor claims a year, average settled value $3,400.
Fraudulent or inflated claims at 3.2% of volume, the mid-point of published industry estimates for motor.
Sealed capture adoption reaching 70% of claims by month six; the remainder route to review exactly as they do today.
Leakage addressed is the portion of fraudulent claims carrying a veto or blocker at intake, not the whole fraud population.
No reduction assumed in assessor headcount; the gain is in cycle time and in claims not paid.

What changes

How the process differs

Evidence is sealed on the phone

The policyholder captures damage through the insurer's app. Integrity signals are measured on the device and bound into the file before it is uploaded.

Intake decides in one call

The claims system posts the sealed capture and receives a verdict with a basis and a proof object. Clean attested captures inside the auto-pay ceiling settle without a human.

The SIU sees the right claims

Vetoes are surfaced at intake with the evidence attached, rather than being found later by sampling. The unit's capacity goes where it is worth spending.

Honest claims get faster, not slower

The policy routes anything uncertain to a human. An old handset, an underground car park, a photograph mailed in - all handled, none penalised.

Honest limits

What this model does not claim

A model is an argument, not evidence. These figures show what follows if the assumptions hold for your organisation, and the point of publishing them in full is so you can check whether they do.

The full model behind these figures, with every input cited to published research, is in the industry brief.

Sealing evidence at capture does not detect every fabrication, does not establish that a truthful-looking document is true, and does not determine intent. The Product Disclosure sets out the boundary precisely.

Model this against your own book.

Send us your claim volume and mix and we will run the same model on your numbers.

Book a pilot Check a file first Motor brief (PDF)