Predictika · Power wheelchairs and rehab seating orders

An AI sales agent's power wheelchair order, checked before it goes out

An AI sales agent prepares an order from a mobility provider: the Corpus power chair model, seat size, power seat functions, controls and accessories, a funding source with the clinical evaluation, and a dealer tier and discount. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the product and ordering rules and returns a verdict, every reason and the figures it computed.

Scope: Permobil Corpus power chair orders: F3 Corpus, F5 Corpus, F5 Corpus VS, M Corpus VS and M300 Corpus HD with seat size, power seat functions, mo-vis controls, accessories and funding rules. See everything this validator covers

This validator models Permobil Corpus power chair orders, not just the scenarios shown below. Items marked with an asterisk are illustrative.

  • Models — F3 Corpus, F5 Corpus (up to 150 kg), F5 Corpus VS and M Corpus VS standing chairs, and M300 Corpus HD (up to 204 kg).
  • Seat and power functions — seat width, depth, seat-to-floor height, backrest height and armrest pad length; power tilt, recline, legrest elevation, ActiveHeight and ActiveReach, which every standing model must carry.
  • Controls and accessories — mo-vis All-round Joystick, Micro Joystick and Scoot Control; BodiLink head support and lateral trunk supports; swing-away knee support for standing models; aggressive tread tires and mud guards on the F5 Corpus; oxygen bottle holder and hand warmer.
  • Funding and dealer terms — Medicare, Medicaid, private insurance, VA and self-pay funding with the clinical seating evaluation; Standard*, Preferred* and Strategic* dealer tiers with discount limits; the stated option count is compared with what the order contains.

Any Permobil Corpus power chair order that touches these rules is in scope — not only the scenarios pictured here. Not covered: prices (funder and dealer pricing is not public, so this validator produces no price build-up or line-item quote), manual chairs, power assist, and non-Corpus seating. Rules and dealer tiers that Permobil has not published are typical for this kind of product; see the fine print at the end of the page.

The AI sales agentBuilds the power chair order from the conversation and says it is ready.
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 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) 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
Weight limits and seat ranges that differ by modelOnly with care
Each model has its own limit and each dimension its own range; a rule per model and dimension works, but every new model or range change is another set of rules to maintain.		Model, user weight and every dimension are in one request and each range is checked against the selected model.
A standing model that carries every power seat functionOnly with workarounds
The requirement links the model on one line with five function lines, so it needs cross-line rules that interact with the rest.		Every choice is in one request, so a missing function is found whichever order the choices arrive in.
Options that exist only on certain models (tread tires, swing-away knee support)Only with care
Each option is a product rule keyed on the model; it works, but every new option or model adds rules.		Model and options are in one request and each pairing is checked together.
Funding rules that need a clinical evaluation on fileOnly with workarounds
Funding documentation usually lives outside the quote, so the order can leave before the evaluation is attached.		The evaluation flag travels with the order and is checked against the funding source and the power functions on every call.
A stated option count that must match the orderOnly with care
A stated figure is a free-entry field; a rule can compare it with a computed total, but someone has to write and maintain that comparison.		The stated figure travels with the order and is compared with the computed total on every call.
Every problem returned in one answerOnly with workarounds
Rules tend to fire as the order is saved or a step is completed, 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 order; approval findings need a person to sign off; everything else is computed.

    
1The user weighs 155 kg and the selected model supports up to 150 kg.
2The user weighs 140 kg and the selected model supports up to 136 kg.
3The user weighs 210 kg and the selected model supports up to 204 kg.
4A seat width of 16 inches is outside the 17 to 23 inch range.
5A seat width of 24 inches is outside the 17 to 23 inch range.
6A seat depth of 13 inches is outside the 14 to 22 inch range.
7Seat-to-floor heights are 17.5, 18.5 and 19.5 inches; the order has 18.0 inches.
8Backrest heights run from 23 to 28 inches in 1 inch steps; the order has 29 inches.
9Armrest pad lengths are 10, 13, 16 and 18 inches; the order has 14 inches.
10A Corpus VS standing model includes all the power seat functions of the Corpus (tilt, recline, legrest, ActiveHeight and ActiveReach), and the order is missing one or more.
11The swing-away knee support is a standing option, and the order has a model without standing.
12Aggressive tread tires and mud guards are options of the F5 Corpus, and the order has a different model.
13Power seat functions or standing on a funded order need a clinical seating evaluation on file, and the order has none.
14Standing functions are generally not covered under Medicare, so the funding route needs to be confirmed before the order is released.
15The order has 0 chairs.
16An order for 10 chairs is a volume commitment that needs commercial sign-off.
17A discount of 18 percent is above the 15 percent that the dealer tier allows without sign-off.
18A discount of 35 percent is deeper than any dealer tier allows.
19The order states 9 options per chair, but the power functions, controls, tires and accessories on it total 7.
20The order states 5 options per chair, but the power functions, controls, tires and accessories on it total 7.

  

  

    
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. Standing chair order: An F5 Corpus VS order with a missing power function, a seat width out of range and no evaluation on file

    
The agent's request. Please quote 3 Permobil F5 Corpus VS power chairs funded by VA for a 100 kg user, with a 24 inch wide by 18 inch deep seat at 18.5 inches from the floor, a 25 inch backrest and 16 inch armrest pads, with power tilt, power recline, power legrest elevation and ActiveHeight, the mo-vis All-round Joystick, lateral trunk supports, a BodiLink head support and the swing-away knee support, on a Preferred-tier dealer agreement with a discount of 10 percent. No clinical seating evaluation is on file. The order states that it contains 8 options per chair. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Seat width not available. A seat width of 24 inches is outside the 17 to 23 inch range.
    • 
      
  • Standing models need every power seat function. A Corpus VS standing model includes all the power seat functions of the Corpus (tilt, recline, legrest, ActiveHeight and ActiveReach), and the order is missing one or more.
    • 
      
  • Clinical evaluation needed for power seating. Power seat functions or standing on a funded order need a clinical seating evaluation on file, and the order has none.
    • 
    

    
2. Standing chair order: The agent resubmits after fixing the errors

    
The agent's request. Please quote 3 Permobil F5 Corpus VS power chairs funded by VA for a 100 kg user, with a 19 inch wide by 18 inch deep seat at 18.5 inches from the floor, a 25 inch backrest and 16 inch armrest pads, with power tilt, power recline, power legrest elevation, ActiveHeight and ActiveReach, the mo-vis All-round Joystick, lateral trunk supports, a BodiLink head support and the swing-away knee support, on a Preferred-tier dealer agreement with a discount of 10 percent. The clinical seating evaluation is on file. The order states that it contains 9 options per chair. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 3 chair(s); the selected model supports up to 136 kg; 9 option(s) per chair.
    • 
    

    
3. Clinic order: An F3 Corpus order with F5 options, a heavier user, a bad armrest pad and no evaluation

    
The agent's request. Please quote 6 Permobil F3 Corpus power chairs funded by Medicaid for a 140 kg user, with a 19 inch wide by 18 inch deep seat at 18.5 inches from the floor, a 25 inch backrest and 14 inch armrest pads, with power tilt, power recline, ActiveHeight and ActiveReach, aggressive tread tires, mud guards and an oxygen bottle holder, on a Preferred-tier dealer agreement with a discount of 10 percent. No clinical seating evaluation is on file. The order states that it contains 7 options per chair. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • User weight above the model limit. The user weighs 140 kg and the selected model supports up to 136 kg.
    • 
      
  • Armrest pad length not available. Armrest pad lengths are 10, 13, 16 and 18 inches; the order has 14 inches.
    • 
      
  • Aggressive tread tires and mud guards are F5 Corpus options. Aggressive tread tires and mud guards are options of the F5 Corpus, and the order has a different model.
    • 
      
  • Clinical evaluation needed for power seating. Power seat functions or standing on a funded order need a clinical seating evaluation on file, and the order has none.
    • 
    

    
4. Clinic order: The agent resubmits after fixing the errors

    
The agent's request. Please quote 6 Permobil F5 Corpus power chairs funded by Medicaid for a 140 kg user, with a 19 inch wide by 18 inch deep seat at 18.5 inches from the floor, a 25 inch backrest and 16 inch armrest pads, with power tilt, power recline, ActiveHeight and ActiveReach, aggressive tread tires, mud guards and an oxygen bottle holder, on a Preferred-tier dealer agreement with a discount of 18 percent. The clinical seating evaluation is on file. The order states that it contains 7 options per chair. It is ready to send.

    
Verdict: Needs approval.

    
    
      
  • Discount above the dealer tier. A discount of 18 percent is above the 15 percent that the dealer tier allows without sign-off.
    • 
      
  • Order summary. 6 chair(s); the selected model supports up to 150 kg; 7 option(s) per chair.
    • 
    

    
5. Clinic order: The agent resubmits after fixing the errors

    
The agent's request. Please quote 6 Permobil F5 Corpus power chairs funded by Medicaid for a 140 kg user, with a 19 inch wide by 18 inch deep seat at 18.5 inches from the floor, a 25 inch backrest and 16 inch armrest pads, with power tilt, power recline, ActiveHeight and ActiveReach, aggressive tread tires, mud guards and an oxygen bottle holder, on a Preferred-tier dealer agreement with a discount of 15 percent. The clinical seating evaluation is on file. The order states that it contains 7 options per chair. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 6 chair(s); the selected model supports up to 150 kg; 7 option(s) per chair.
    • 
    

    
6. Heavy-duty order: An F5 Corpus order for a 190 kg user with a swing-away knee support

    
The agent's request. Please quote 1 Permobil F5 Corpus power chair funded by Medicaid for a 190 kg user, with a 22 inch wide by 18 inch deep seat at 18.5 inches from the floor, a 25 inch backrest and 16 inch armrest pads, with power tilt, power recline and power legrest elevation, the mo-vis Micro Joystick and the swing-away knee support, on a Preferred-tier dealer agreement with a discount of 10 percent. The clinical seating evaluation is on file. The order states that it contains 5 options per chair. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • User weight above the model limit. The user weighs 190 kg and the selected model supports up to 150 kg.
    • 
      
  • Swing-away knee support is for standing models. The swing-away knee support is a standing option, and the order has a model without standing.
    • 
    

    
7. Heavy-duty order: The agent resubmits after fixing the errors

    
The agent's request. Please quote 1 Permobil M300 Corpus HD power chair funded by Medicaid for a 190 kg user, with a 22 inch wide by 18 inch deep seat at 18.5 inches from the floor, a 25 inch backrest and 16 inch armrest pads, with power tilt, power recline and power legrest elevation and the mo-vis Micro Joystick, on a Preferred-tier dealer agreement with a discount of 10 percent. The clinical seating evaluation is on file. The order states that it contains 4 options per chair. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 1 chair(s); the selected model supports up to 204 kg; 4 option(s) per chair.
    • 
    

  

  

    
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 an order from a mobility provider: the Corpus power chair model, seat size, power seat functions, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the product and ordering rules and returns a verdict, every reason and the figures it computed.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Please quote 6 Permobil F3 Corpus power chairs funded by Medicaid for a 140 kg user, with a 19 inch wide by 18 inch deep seat at 18.5 inches from the floor. No clinical seating evaluation is on file. The rest of the request is on screen.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with four findings, all in one answer. The user weighs 140 kg and the selected model supports up to 136 kg. Armrest pad lengths are 10, 13, 16 and 18 inches; the order has 14 inches. Aggressive tread tires and mud guards are options of the F5 Corpus, and the order has a different model. The other one is on screen.
    6. 
      
  6. The validator returned four blocking findings 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 order are checked against each other.
    7. 
      
  7. What this shows: for options that exist only on certain models (tread tires, swing-away knee support), a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the model to F5 Corpus, the armrest pad length to 16 in, the clinical evaluation on file to yes and the discount to 18 percent.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. Not blocked, but held for a person.
    12. 
      
  12. The four blocking findings are cleared; one approval remains for a person: discount above the dealer tier.
    13. 
      
  13. The agent resubmits once more.
    14. 
      
  14. The revised request. It changes the discount to 15 percent.
    15. 
      
  15. It calls the validator once more.
    16. 
      
  16. This time the validator clears it.
    17. 
      
  17. The earlier finding is cleared, and the validator's figure matches the order.
    18. 
      
  18. Four problems caught in one call, fixed in two passes, and a clean order. That is the value of Predictika's validator: catching mistakes before they reach the customer. Now you can try the other scenarios yourself.
    19.