About
Insurance technology that can explain itself
Insurance AI is an AI-powered, multi-tenant life insurance platform built for Pakistani insurers, designed so that every automated step can be justified to an underwriter, an auditor or a customer. It is developed by Rizviz International Impex.
Principles
How we build
Deterministic where it matters
Pricing, requirements and underwriting verdicts are computed by rules that can be read, tested and replayed. Language models stay on the interpretation side of the line.
Humans stay in the loop
Borderline risks, large claims and every data-changing copilot action stop for a person. Automation removes busywork, not accountability.
Everything leaves a trail
One policy state machine, immutable lifecycle events and persisted assessments mean you can answer why something happened months later.
Local from the start
CNIC validation, PKR pricing, takaful as a first-class product type and sanctions screening are part of the core, not an add-on.
Models advise.
Language models read evidence and score risk. Their output is advice, and it is always labelled as advice.
Rules decide.
A deterministic, versioned rule chain chooses the verdict, so the same inputs always give the same outcome.
Audit proves.
Every input, rule and outcome is recorded, so a decision can be replayed months later.
Status
A working prototype, built end to end
Plans, rates and customer data on this site are demo data while we work with early insurers on real catalogues and integrations.
Underwriting pipeline
Medical, financial and fraud scoring, then a rule-based verdict with reasons.
AI copilot
Onboards leads and runs workflows from chat, pausing for confirmation before any change.
Claims journey
Triage, fraud checks, adjudication, payout and recovery, with a human wherever it matters.
Fraud graph
A relationship graph that finds what a single application cannot show.
Group and family workflows
Census upload for employers, nominee shares for families, on the same lifecycle.
Agent mobile app
Lead board, e-application links, the confidential agent report and commissions.
Built to be trusted
AI you can put in front of an auditor.
Insurance AI is a prototype built around the questions a regulated insurer asks first.
Decision traceability
Every status change runs through one state machine and leaves an event behind, so any outcome can be traced back.
Human oversight
Borderline cases go to a person. Human Review and Request Additional Evidence are first-class outcomes.
Explainability
Scores come with reasons, and the rule that produced a verdict is recorded next to it.
Configurable rules
Business rules are versioned data your team can change, not behaviour buried inside a prompt.
Enterprise workflow integration
Multi-tenant and role-aware, with the portal, agent app and copilot working on one set of records.
Want to see it with your own scenarios?
We will walk you through a lead becoming a policy and a claim, with the copilot driving where it helps.