Predictika · small-group medical quoting: group size, participation, plans, riders, commission and age-rated premium

An AI sales agent's small-group quote, checked before it goes out

An AI sales agent prepares a small-group medical quote for a fictional employer, with the total monthly premium it expects. Before the quote is released for enrollment, the agent sends it to Predictika’s validator, which checks it against group-size, participation, plan, rider and commission rules, compares the total the agent states with the one it computes, and returns a verdict with every reason.

Scope: small-group employer medical quotes in the style of UnitedHealthcare: eligibility, plans and riders, and age-rated premium. See everything this validator covers

This validator models small-group medical quotes for six sample areas and six plans, with dental and vision riders. It handles any combination of group, census, plan, rider and commission choices the model supports, not just the scenarios shown below.

  • Eligibility — Small-group size limits by area, the non-owner employee requirement, the census, participation net of waivers, employer contribution, and the guaranteed-issue window.
  • Plans and riders — HMO and HSA availability, tobacco rating rules, dental PPO and HMO rules and vision.
  • Pricing — Age-rated employee premium, spouses and children, tobacco surcharge, dental and vision, commission load, the employer share, and a check that the total the agent states matches the validator total.

It does not cover large-group or self-funded plans, other carriers’ rules, areas beyond the six modeled, real UnitedHealthcare rates or underwriting decisions, or any real employer.

The AI sales agentBuilds the quote from the conversation and says it is ready.
Predictika validatorChecks the quote against the product and contract rules and returns every finding it has.

7 scenarios in 3 groups · each group runs from the agent’s first attempt to the outcome · click one to switch

What the agent proposes

The AI sales agent says

Illustrative agent statement. The validator receives the structured request below.

Proposing agent: AI sales agent (scripted)

Before sending, the agent must call Recorded run

Predictika validator


      
Waiting for the call.

Where rules-based CPQ gets it wrong

Click to expand

Our assessment of what a typical rules-based CPQ (product rules, price rules and validation rules, as in Salesforce CPQ or Revenue Cloud) does with the same cases. It is a judgment about effort and reliability, not a claim that nothing can be built.

What the validator catchesTypical rules-based CPQPredictika
Eligibility that depends on several choices togetherOnly with workarounds
Group size, participation, contribution, plan and rider rules vary by area, and each combination tends to become a separate rule.
All conditions are evaluated together on every call, whatever order the choices arrive in.
Area limits and minimumsOnly with care
Limits and participation minimums are lookups by area that must be kept complete and read by several rules.
The area row supplies the limit and the minimum, and the same value drives the check and the message.
Age-rated premiumOnly with care
A census by age band, with spouse, child, tobacco, dental and vision factors, is manageable in a price rule but grows with every new band or rider.
Each premium figure is computed once for every check and line item to read.
Participation with waivers and the enrollment windowOnly with workarounds
Net-of-waiver participation and an exception that turns a block into an approval need several coordinated rules.
The participation test, the waiver credit and the window exception are evaluated together and returned with the reason.
Commission as a rate load and an approvalOnly with care
Commission changes the rate, needs an approval above a standard and is blocked above a maximum, which means price rules and validation rules must agree.
The load, the approval and the block come from one commission figure.
The total the agent statesOnly with workarounds
Comparing a stated total with a computed one means a separate rule per quote layout, and price rules rarely run on stated figures.
The stated total is a field in the request and is checked against the computed total.
Every problem returned in one answerOnly with workarounds
Rules tend to fire as the quote is saved, so a rep often fixes one error and meets the next.
All findings come back together, whatever order the choices arrived in.

What this validator catches

Click to expand

Every rule is checked on every call, in whatever order the choices arrive, and one problem never hides another. Blocking findings stop the quote; approval findings need a person to sign off; everything else is computed.

RuleEffectWhat it checks
1blockThe area sets the small-group limit on eligible employees (50 in Texas and Florida, 100 in California, New York and Colorado)
2blockAt least one enrolling employee must not be an owner or owner spouse, and the census must be between 1 and the eligible count
3block, or approvalEnrolling employees, net of valid waivers, must meet the area participation minimum, unless the quote is in the guaranteed-issue window, which needs approval
4blockThe employer must pay at least 50 percent of the employee-only premium, and no more than 100 percent
5blockAn HMO plan needs the HMO network in the area; an HSA needs an HSA-qualified plan
6blockA tobacco surcharge is blocked where tobacco rating is prohibited, and tobacco users cannot exceed enrolling employees plus spouses
7blockDental needs at least 2 enrollees, no more than the medical enrollees, and the dental HMO only where it is offered
8approval, then blockBroker commission above 5 percent needs a compensation override; above 8 percent is blocked
9computedEmployee premium is the area rate times the age-band rating units, with the commission load applied
10computedSpouses and children are rated on their own factors; tobacco, dental and vision are added to the total
11blockThe total monthly premium the agent states must match the validator total within $1

Scenarios and results

Click to expand

The recorded result of the validator for each scenario on this page: the request the AI agent sent, the verdict, and every finding, in the order they appear above.

1. Group size against the small-group limit: 60 eligible employees in Texas

The agent's request. A small-group quote for a Dallas, Texas employer with 60 eligible employees, 45 enrolling, 8 spouses and 10 children, on Choice Plus Gold 1000 with PPO dental for 30 and vision, 60 percent employer contribution. Total monthly premium $54,232.00. Ready to release.

Verdict: Blocked.

  • Group size above the small-group limit. 60 eligible employees exceeds the small-group limit of 50 in Texas Area 7 Dallas; quote large group instead.

2. Group size against the small-group limit: Group of 50 eligible employees

The agent's request. A small-group quote for a Dallas, Texas employer with 50 eligible employees, 45 enrolling, 8 spouses and 10 children, on Choice Plus Gold 1000 with PPO dental for 30 and vision, 60 percent employer contribution. Total monthly premium $54,232.00. Ready to release.

Verdict: Allowed.

3. Participation: 5 of 12 enroll

The agent's request. A small-group quote for a Dallas, Texas employer with 12 eligible employees, 5 enrolling, 2 spouses and 3 children, on Choice Plus Gold 1000 with PPO dental for 4 and vision, 60 percent employer contribution. Total monthly premium $7,362.55. Ready to release.

Verdict: Blocked.

  • Participation below the minimum. 5 of 12 eligible employees (net of 0 valid waivers) enroll, below the 70 percent participation minimum in Texas Area 7 Dallas.

4. Participation: 9 of 12 enroll

The agent's request. A small-group quote for a Dallas, Texas employer with 12 eligible employees, 9 enrolling (8 of them non-owner employees), 2 spouses and 3 children, on Choice Plus Gold 1000 with PPO dental for 4 and vision, 60 percent employer contribution. Total monthly premium $10,201.05. Ready to release.

Verdict: Allowed.

5. The total premium the agent states: Stated total too low

The agent's request. A small-group quote for a Denver, Colorado employer with 10 eligible employees, 8 enrolling, 3 spouses and 4 children, on Choice Plus Bronze HSA 7000 with an HSA, a tobacco surcharge for 2 employees, PPO dental for 6 and vision, 75 percent employer contribution. Total monthly premium $5,512.18. Ready to release.

Verdict: Blocked.

  • Stated total differs from the validator total. The total monthly premium the agent states ($5512.18) differs from the total monthly premium the validator computes ($6890.22).

6. The total premium the agent states: Stated total corrected

The agent's request. A small-group quote for a Denver, Colorado employer with 10 eligible employees, 8 enrolling, 3 spouses and 4 children, on Choice Plus Bronze HSA 7000 with an HSA, a tobacco surcharge for 2 employees, PPO dental for 6 and vision, 75 percent employer contribution. Total monthly premium $6,890.22. Ready to release.

Verdict: Allowed.

7. Approval and release: 7 percent commission, approved

The agent's request. A small-group quote for a Miami, Florida employer with 20 eligible employees and 16 enrolling, on Navigate HMO Gold 1500, 60 percent employer contribution, with a 7 percent broker commission. Compensation override approved. Total monthly premium $13,254.70. Ready to release.

Verdict: Needs approval.

  • Commission needs a compensation override. 7 percent broker commission is above the 5 percent standard and needs a compensation override.

Narration transcript

Click to expand

The text of the narrated walkthrough, step by step.

  1. Welcome to a demo of Predictika's Validator. An AI sales agent prepares a small-group medical quote for a fictional employer, with the total monthly premium it expects. Before the quote is released for enrollment, the agent sends it to Predictika’s validator, which checks it against group-size, participation, plan, rider and commission rules, compares the total the agent states with the one it computes, and returns a verdict with every reason.
  2. I will start with the first request by the agent.
  3. The agent says. A small-group quote for a Dallas, Texas employer with 60 eligible employees, 45 enrolling, 8 spouses and 10 children, on Choice Plus Gold 1000 with PPO dental for 30 and vision. Total monthly premium $54,232.00. The rest of the request is on screen.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with one finding, all in one answer. 60 eligible employees exceeds the small-group limit of 50 in Texas Area 7 Dallas; quote large group instead.
  6. The validator returned one blocking finding in one answer. A check that reads one field at a time would pass most of this; it shows only when the choices in the quote are checked against each other.
  7. What this shows: for area limits and minimums, a rules-based CPQ is error-prone for this.
  8. Now the agent resubmits.
  9. The corrected request. It changes the eligible to 50.
  10. It calls the validator again.
  11. This time the validator clears it.
  12. The validator also returns the line-item quote. It starts with Employee premium (age-rated) and Spouses and children; the other two lines are on screen.
  13. The earlier finding is cleared, and the validator's total, $54,232.00, matches the quote.
  14. One problem caught in one call, fixed in one pass, and a clean quote. That is the value of Predictika's validator: catching mistakes before they reach the customer.