Predictika · sleep therapy devices, masks, payer contracts, pressure, options and contract years

An AI sales agent's sleep therapy equipment quote, checked before it goes out

An AI sales agent prepares a sleep therapy equipment quote for a fictional home medical equipment supplier: a device, a mask, a payer contract, a number of systems, a prescribed pressure, a contract length, telemonitoring and humidifier options and a discount. Before it goes out, the agent sends it to Predictika's validator, which checks it against a declarative model of the product and contract rules and reports every problem it finds, together with the price it computed, in one pass.

Scope: Sleep therapy equipment quotes for four devices (AutoSet CPAP, Bilevel, ASV and Travel CPAP), three masks and three payer contracts, with system counts, prescribed pressure, contract years, telemonitoring and humidifier options, volume and extra discounts and order size. Prices in US dollars are illustrative estimates. See everything this validator covers

This validator checks any quote for these devices, masks and payer contracts, not just the scenarios shown below.

  • Devices and masks — AutoSet, Bilevel, ASV and Travel devices with nasal, pillows and full face masks, including the mask that cannot be used with the ASV device.
  • Pressure — the prescribed pressure against the device range and the mask limit, with a clinical review above 20.
  • Options and payer contracts — telemonitoring and the humidifier by device, and standard, regional and national payer contracts with their system minimums and discounts.
  • Contract and order size — contracts of 1 to 5 years, a finance review above 3 years, a supply capacity review above 1,000 systems, an approval band above 18 percent total discount, a limit at 25 percent, and a deal desk review above USD 2,000,000.
  • The stated total — the net total on the quote is compared with the total the validator computes.

Any quote for these devices, masks and contracts is in scope, not only the scenarios pictured here. Not covered: other products, software subscriptions and accessories, real list prices, payer reimbursement rules, clinical decisions (the pressure review is a quoting check only), tax and other currencies.

The AI sales agentBuilds the sleep therapy quote from the conversation and says it is ready to send.
Predictika validatorChecks every rule at once and returns the verdict, each finding, and the computed figures.

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 this 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 Conga) does with the same cases. It is a judgment about effort and reliability, not a claim that nothing can be built.

What the validator caughtTypical rules-based CPQPredictika
Device and mask compatibilityOnly with workarounds
A pairwise compatibility between two catalogs usually becomes one rule per combination.
Compatibility is a property of the mask and the device, checked on every call.
Pressure against two limitsOnly with care
A number that must fit both a device range and a mask limit spans several validation rules.
Both limits and the review band are evaluated together.
Options by deviceOnly with care
Telemonitoring and humidifier availability differ by device, so option rules multiply.
Each option is checked against the device property directly.
Contract years and order sizeOnly with workarounds
A hard range, a review band and a value threshold are held in separate rules.
The range, the bands and the order value are all evaluated together.
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: findings from its test cases

Click to expand

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

1The system count must be between 1 and 5000.
2The system count must meet the minimum of the payer contract (100 for the national contract).
3The prescribed pressure must be from 4 up to the maximum of the device.
4The prescribed pressure must not be above the limit of the mask (15 for the pillows mask).
5The pillows mask cannot be used with the ASV device.
6Telemonitoring is available only on devices with a modem; the Travel CPAP has none.
7The humidifier is available only on devices that have one; the Travel CPAP has none.
8The contract must be from 1 to 5 years.
9The total discount must not be above 25 percent.
10A prescribed pressure above 20 needs a clinical review.
11A contract longer than 3 years needs finance approval of the price lock.
12More than 1,000 systems need a supply capacity review.
13A total discount above the 18 percent a rep can give needs approval.
14An order value above USD 2,000,000 needs a deal desk review.
15The net total stated on the quote must match the total the validator computes.

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. A contract term that is too long: A 6 year contract on a standard account

The agent's request. AutoSet CPAP with a nasal mask for 20 systems on a standard DME account, pressure 10, for a 6 year contract. Ready to send.

Verdict: Blocked.

  • Contract length. A contract of 6 years is outside the 1 to 5 years allowed.

2. A contract term that is too long: The agent resubmits after fixing the errors

The agent's request. AutoSet CPAP with a nasal mask for 20 systems on a standard DME account, pressure 10, now for a 4 year contract. Ready to send.

Verdict: Needs approval.

  • Long contract. A contract of 4 years is longer than 3 years, so finance must approve the price lock.

3. A contract term that is too long: The agent resubmits after fixing the errors

The agent's request. AutoSet CPAP with a nasal mask for 20 systems on a standard DME account, pressure 10, now for a 1 year contract. Ready to send.

Verdict: Allowed.

4. The wrong mask for an ASV device: An ASV device with the pillows mask

The agent's request. ASV device with a pillows mask for 20 systems on a standard DME account, pressure 10, 1 year. Ready to send.

Verdict: Blocked.

  • Mask compatibility. The pillows mask cannot be used with the ASV device.

5. The wrong mask for an ASV device: The agent resubmits after fixing the errors

The agent's request. ASV device with a nasal mask for 20 systems on a standard DME account, pressure 10, 1 year. Ready to send.

Verdict: Allowed.

6. A stated total that does not match: A quote whose stated total is below the computed total

The agent's request. AutoSet CPAP with a nasal mask for 20 systems on a standard DME account, pressure 10, 1 year, with a net total of USD 16,560. Ready to send.

Verdict: Blocked.

  • Net total mismatch. The quoted net total of USD 16,560 does not match the USD 18,400 the validator computed.

7. A stated total that does not match: The agent resubmits after fixing the errors

The agent's request. AutoSet CPAP with a nasal mask for 20 systems on a standard DME account, pressure 10, 1 year, with a net total of USD 18,400. Ready to send.

Verdict: Allowed.

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 sleep therapy equipment quote for a fictional home medical equipment supplier: a device, a mask, a payer contract, and more. Before it goes out, the agent sends it to Predictika's validator, which checks it against a declarative model of the product and contract rules and reports every problem it finds, together with the price it computed, in one pass.
  2. I will start with the first request by the agent.
  3. The agent says. AutoSet CPAP with a nasal mask for 20 systems on a standard DME account, pressure 10, for a 6 year contract. Ready to send.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with one finding, all in one answer. A contract of 6 years is outside the 1 to 5 years allowed.
  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 contract years and order size, rules-based CPQ can do this only with workarounds.
  8. Now the agent resubmits.
  9. The corrected request. It changes the contract to 4 years.
  10. It calls the validator again.
  11. Not blocked, but held for a person.
  12. The one blocking finding is cleared; one approval remains for a person: long contract.
  13. The agent resubmits once more.
  14. The revised request. It changes the contract to 1 years.
  15. It calls the validator once more.
  16. This time the validator clears it.
  17. The earlier finding is cleared.
  18. One problem caught in one call, fixed in two passes, and a clean quote. That is the value of Predictika's validator: catching mistakes before they reach the customer. Now you can try the other scenarios yourself.