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

Annuity Feature Change Pricing Agent

Find feature designs that meet margin and risk targets and explain the options.

DecisionsFinanceInsurance
See how it worksGet access
Annuity Feature Change Pricing Agent: what goes in, what the agent does and what you get

What it does

When product teams want to add a feature to an annuity, such as a higher roll-up rate or a new rider, actuaries rebuild the pricing by hand and guess the margin. This agent takes the proposed feature change and reruns pricing with the new design. It checks margins and risk measures against the targets and compares several design options, such as different fees, caps or rates. If margins fall below target, it adjusts one parameter at a time, such as the rider fee or the cap, and reruns until the target is met or no option works. It then drafts a memo comparing options. The actuary approves the recommendation.

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 Product change proposal arrives 2 USES A TOOL Run the pricing model on the base design 3 DOES Check margin, return and tail risk against targets 4 CHECKS THE RESULT Do the results meet the margin and risk targets? If not: adjust one parameter such as fee, cap or rate,and rerun. Back to step 3. 5 DOES Build two or three alternative designs 6 USES A TOOL Run each alternative 7 DOES Compare options and test sensitivity to keyassumptions 8 CHECKS THE RESULT Does the preferred option still meet targets underthe sensitivity cases? If not: drop or adjust that option. Back to step 5. 9 DOES Draft the recommendation memo 10 YOU APPROVE Actuary approves the recommendation 11 RESULT Approved option memo
Read the steps as a list
  1. Product change proposal arrives
  2. Run the pricing model on the base design
  3. Check margin, return and tail risk against targets
  4. Do the results meet the margin and risk targets?If not: adjust one parameter such as fee, cap or rate, and rerun. Back to step 3.
  5. Build two or three alternative designs
  6. Run each alternative
  7. Compare options and test sensitivity to key assumptions
  8. Does the preferred option still meet targets under the sensitivity cases?If not: drop or adjust that option. Back to step 5.
  9. Draft the recommendation memo
  10. Actuary approves the recommendationThe agent waits here for your OK.
  11. Approved option memo

How it decides

It picks the design that meets margin and risk targets with the smallest change from the product team's proposal.

  • Require a profit margin of at least the target on the base case
  • Change one parameter at a time to see its effect
  • Test interest rates up and down 100 basis points
  • Prefer the option closest to the original proposal

Make it yours

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

  • Margin and risk targets
  • Parameters allowed to change
  • Sensitivity cases
  • Memo template

What keeps you in control

It always asks you first

  • Actuary approves the recommendation
  • Chief actuary approves any price or feature sent to product teams

Hard limits

  • Never releases prices or filings
  • Shows assumptions behind every result

It stops when

  • Done: at least one option meets targets and the memo is approved
  • Stop: no tested design meets the targets

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 happensA proposal raised the roll-up rate from 5 to 6 percent. Base pricing showed margin of 0.4 percent against a 1.0 percent target. The agent raised the rider fee from 1.0 to 1.2 percent, and margin reached 1.1. Under a 100 basis point rate drop it fell to 0.7, failing the stress test. It lowered the cap too and margin held at 1.0. 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
Decisions · Analysis

Mortality and Lapse Assumption Update Agent

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

11 steps2 checks2 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