UAE · ENBook a demo
Insure AICustomerInvestigator

Policyholder Health Score Agent

Scores policyholder relationships and explains what moved them.

Policyholder Health Score AgentAccount Health Agent · Customer Lifecycle
Industry
Insure AI
Department
Customer
Team
Customer Lifecycle
Kind
Investigator
Approver
Customer Service Manager
Code
CUS-13

It scores each policyholder relationship on servicing signals, such as policies held, recent claims experience, complaints, payment failures and survey sentiment, and explains what moved a score. It flags relationships turning red before renewal so the servicing team can act. **The problem it solves:** Why each customer's relationship score moved: the claims, service, sentiment and payment signals before and after, and which ones drove the change.

How it works

6 steps, and a person signs off before step 6.

  1. 01Looks it up

    Finds the record the request is about in the claims management system: each customer's recent claims with handling time and outcome, and from the policy administration system their policies, complaints and payment failures..

  2. 02Reads the request

    Works out what is being asked and what a complete answer needs.

  3. 03Checks the facts

    Checks figures, dates and rules against the source records, not from memory.

  4. 04Works it through

    Weighs competing explanations against the evidence and shows which one holds up.

  5. 05Asks a person

    Hands the work to Customer Service Manager with its reasoning before anything goes out.

  6. 06Acts

    Once approved, it acts in the policy administration system: it updates each customer's relationship score and flags the red ones for the servicing team. and records what was done.

What it works with

Your knowledge, your systems, your people.

Knows

The relationship health model: signal definitions, weights, thresholds, and how claims experience and complaints affect renewal behaviour.

Reads from

the claims management system: each customer's recent claims with handling time and outcome, and from the policy administration system their policies, complaints and payment failures.

Acts in

the policy administration system: it updates each customer's relationship score and flags the red ones for the servicing team.

Hands back

A list with one entry per customer, each with customer_id, score, band (green, amber or red), change, drivers (a ranked list, each with signal, contribution and evidence) and suggested_action.

Asks a person when

A customer turns red within 60 days of renewal, or the score is driven by an open complaint.

ApproverCustomer Service Manager

Settings

Your limits, set by your managers.

SettingDefaultWhat it controls
Weight of claims experience (%)35How much the last claim's handling time and outcome count.
Weight of complaints and service issues (%)25How much open complaints and service issues count.
Weight of survey sentiment (%)20How much NPS and survey answers count.
Weight of payment behaviour (%)20How much failed premium payments count.
Red below (score)40A score below this is red.
Amber below (score)65A score below this is amber.
Alert on a drop of (points)15A drop this large in a period is explained and flagged.

Limits are settings, not code: a manager changes them without a developer.

Rules it always follows

  • Score with claims 35, service 25, sentiment 20 and payment 20 percent.
  • Below 40 is red, below 65 amber.
  • Explain every drop of 15 points or more by the signals that moved, ranked by contribution.
  • Separate a bad claims experience from a declined claim: a fair decline handled well is not a service failure.
  • Never use health data from claims in the score.

See the Policyholder Health Score Agent agent on your own work.

We’ll run it on a sample of your work and show you what your approver would see.

Policyholder Health Score Agent · Insure AI | Basinwright Industries