Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for insurance actuaries

Mortality and Lapse Assumption Update Agent

Propose supported assumption updates with reserve impact, ready for review.

DecisionsAnalysisFinanceInsurance
See how it worksGet access
Mortality and Lapse Assumption Update Agent: what goes in, what the agent does and what you get

What it does

Each year actuaries refresh the mortality and lapse assumptions behind reserves and pricing, which means weeks of data pulls and comparisons. This agent pulls recent experience, compares it with current assumptions by segment and tests whether the data is credible enough to justify a change. For segments with enough data, it proposes new assumptions, and for the rest, it keeps the current ones or blends them using credibility weights. It then reruns reserves to show the effect of the changes. If a segment fails the credibility test, it widens the study period or merges segments and reruns the analysis. The actuary approves all assumptions.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueYes, continueApprovedNoNo 1 STARTS WHEN Annual study begins 2 USES A TOOL Pull experience data and current assumptions 3 DOES Calculate actual to expected by segment 4 CHECKS THE RESULT Is each segment credible enough to support a change? If not: widen the period or merge segments, thenrecalculate. Back to step 3. 5 DOES Propose new assumptions with credibility weights 6 USES A TOOL Rerun reserves with the new assumptions 7 DOES Compare reserves with the current basis and explainthe change 8 CHECKS THE RESULT Is the reserve change within the expected range? If not: review segments driving the change and test fordata errors. Back to step 5. 9 DOES Draft the assumption memo 10 YOU APPROVE Actuary approves assumptions 11 RESULT Assumption proposal and reserve impact
Read the steps as a list
  1. Annual study begins
  2. Pull experience data and current assumptions
  3. Calculate actual to expected by segment
  4. Is each segment credible enough to support a change?If not: widen the period or merge segments, then recalculate. Back to step 3.
  5. Propose new assumptions with credibility weights
  6. Rerun reserves with the new assumptions
  7. Compare reserves with the current basis and explain the change
  8. Is the reserve change within the expected range?If not: review segments driving the change and test for data errors. Back to step 5.
  9. Draft the assumption memo
  10. Actuary approves assumptionsThe agent waits here for your OK.
  11. Assumption proposal and reserve impact

How it decides

It changes an assumption only where experience is credible, and uses credibility weighting where it is partly credible.

  • Treat a segment as fully credible at 1,082 claims or more
  • Use partial credibility weighting below that
  • Merge segments with fewer than 30 claims
  • Review any reserve change above 2 percent

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Credibility standard
  • Segments
  • Reserve change review limit (default 2 percent)
  • Study period (default 3 years)

What keeps you in control

It always asks you first

  • Actuary approves the new assumptions
  • Chief actuary approves the reserve impact

Hard limits

  • Never changes the production reserve model
  • Shows the data basis for every assumption

It stops when

  • Done: assumptions and memo approved
  • Stop: experience data has unresolved errors

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensFor term life, the 55 to 64 male segment had 410 claims, below full credibility at 1,082. The agent used 62 percent credibility and moved the mortality assumption by 3 percent. Lapse for one small product had 12 claims and failed, so it merged it with a similar product. The reserve rose 1.4 percent, within range, and the actuary approved.

More agents for insurance actuaries

Quality control · Finance

Financial Model Formula Repair Agent

A model that passes all test cases after the repair.

7 steps1 check10 jobs
Quality control · Finance

Rate Filing Exhibit Tie-Out Agent

Deliver a rate filing package where every exhibit and the narrative agree.

11 steps1 check1 job
Risk management · Analysis

Climate Scenario Loss Modeling Agent

Show how climate scenarios hit the actual portfolio and which mitigations work.

11 steps2 checks3 jobs
Quality control · Analysis

Actuarial Model Change Control Agent

Show exactly what a model change does to results before it goes live.

11 steps2 checks2 jobs