Kyvvu

Insurance

Faster claims, without decisions nobody made.

Agents can read a claim, check the policy and draft the outcome in minutes. Kyvvu makes sure they don't send medical data where it shouldn't go, and that decisions about customers wait for a person.

claims-agent · task 5e72kyvvu engine · in-process
  1. step.messagePOSTsmtp/repairer-externalblock
Blocked: outbound send after personal data was read in this taskTry it: click the highlighted step to take it off the path

The problem

Customer outcomes, decided at machine speed.

  1. 01

    Sensitive data in every claim

    Claims carry medical reports, police reports and bank details. An agent that forwards the wrong attachment has caused a breach.

    health data/special categories

  2. 02

    High-risk pricing and underwriting

    Risk assessment and pricing for life and health insurance is a high-risk use under the AI Act.

    AI Act Annex III

  3. 03

    Decisions customers can challenge

    A rejected claim or a refused policy has real effects. You need to show who decided, and on what basis.

    GDPR Art. 22

In practice

Claims and underwriting, with the right steps in the right order.

A claims agent tries to reject a claim on its own

A claims agent, classified as high risk, assesses a claim and tries to write a rejection to the claims system.

claims-agent · task 5e72kyvvu engine · in-process

Illustrative scenarios. Each one is decided by a single policy from the open policy library, as the engine evaluates it. References to laws and regulations are our reading of them, to show how a policy maps to an obligation. Not legal advice.

How Kyvvu helps

A person on the decisions that matter.

  1. 01

    Judges the whole path

    Every action is checked against everything the agent did earlier in the task, and blocked before it runs if the sequence is dangerous.

    allow/warn/block

  2. 02

    A person on decisions

    Policies can require a handler's approval before a decision about a customer is written, for high-risk agents or for all of them.

    human oversight

  3. 03

    Standard packs to start from

    OWASP agentic, the EU AI Act, GDPR, DORA and MiFID II, healthcare and data exfiltration packs from the open library, next to your own rules.

    open policy library

  4. 04

    A record of every step

    Each task is recorded as an ordered trace of its steps with the verdict on each, hash-chained when it reaches the platform.

    logs/traces

  5. 05

    Hosted or yours

    Use platform.kyvvu.com, or run the platform in your own infrastructure, on-prem or air-gapped, on Enterprise & Public.

    hosted/self-hosted/air-gapped

  6. 06

    Nothing breaks on day one

    Only critical policies block; high, medium and low ones warn. Start a new rule as a warning and make it critical once you trust it.

    shadow/suggest/enforce

Questions

Common questions.

01

Does DORA apply to insurers?

Yes, insurers and reinsurers are in scope of DORA. The DORA and MiFID II pack has policies for financial writes, approvals and loop limits.

02

Can a policy apply only to our high-risk agents?

Yes. A policy can apply to high-risk agents only, such as underwriting and claims decisions, while simpler agents get a lighter set.

03

Where does our claims data go?

Nowhere new. The engine decides inside the agent's process, and traces can be kept on your own machines.

Get started

Every agent has to ASK before it acts.

Start with one agent

See it on your own agents

A 30-minute demo with someone who builds Kyvvu: your agent, your rules, and the policy that decides each step.

The policy pack

The EU AI Act high-risk pack

Human oversight, robustness and documentation duties for high-risk systems, as runtime policies.

Want to see other teams and sectors? All use cases.