Predictika · Standard PET bottle orders

An AI sales agent's PET bottle order, checked before it goes out

An AI sales agent prepares an order for a standard PET bottle from a public product catalogue, with a matching closure, a quantity and a recycled-PET share. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the catalogue's published rules and returns a verdict, every reason and the figures it computed.

Scope: ALPLA standard PET bottles (nine catalogue bottles): closure neck finish, minimum order quantity and recycled-PET share. See everything this validator covers

This validator models orders for nine standard PET bottles in the public ALPLA product catalogue, not just the scenarios shown below.

  • Bottles — 80 ml, 100 ml food, 100 ml round 24/415, 500 ml milk, 1000 ml milk, 750 ml Eco-Line 28/410, 750 ml spray 32 g, 250 ml agrochemical and 1000 ml PET bottles, each with the neck finish and minimum order quantity its catalogue page lists.
  • Closures — each page says the bottle combines with the closures of its own neck finish (PCO 1881, PCO 1810, 24/415, 28/410, 28/410 / ASG, 38 mm 2-start or 45VTE), so a closure of another neck finish is rejected.
  • Quantity and recycled content — the order must reach the bottle's minimum order quantity; the recycled-PET share can be chosen up to 100 per cent; a minimum order quantity stated on the order is compared with the catalogue figure.

Any order for these bottles that touches these rules is in scope — not only the scenarios pictured here. Not covered: prices (the catalogue pages list none, so this validator produces no price build-up or line-item quote), custom bottle and closure design, the rest of the catalogue, decoration, and closure products (a closure is chosen here by its neck finish only).

The AI sales agentBuilds the bottle 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
A closure that does not fit the bottle neckOnly with care
Each bottle has its own neck finish, so each needs its own compatibility rule, and every new bottle or closure adds more rules to maintain.		The bottle and the closure are in one request and compared on every call.
A minimum order quantity that differs by bottleOnly with care
A threshold per product, usually kept in a table or a rule per bottle and maintained by hand as the catalogue changes.		The bottle sets its own minimum and every quantity is compared with it on every call.
A stated minimum that disagrees with the catalogueOnly with workarounds
The figure the agent states is free text or a separate field, so it takes an extra rule that compares it with the product's own minimum.		The stated figure is part of the request and is compared with the catalogue figure 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 quote; approval findings need a person to sign off; everything else is computed.

    
1The selected closure does not fit the neck finish of the selected bottle; the catalogue says each bottle combines with the closures of its own neck finish.
2The quote has 149,999 units; the minimum order quantity for the selected bottle is 150,000 units.
3The recycled PET share is 101 per cent; the catalogue allows any share up to 100 per cent rPET.
4The quote states a minimum order quantity of 100,000 units, but the catalogue lists 150,000 units for the selected bottle.
5The quote states a minimum order quantity of 200,000 units, but the catalogue lists 150,000 units for the selected bottle.
6The quote has 50,000 units; the minimum order quantity for the selected bottle is 150,000 units.
7The recycled PET share is 120 per cent; the catalogue allows any share up to 100 per cent rPET.
8The quote has 119,999 units; the minimum order quantity for the selected bottle is 120,000 units.
9The quote has 9,999 units; the minimum order quantity for the selected bottle is 10,000 units.
10The quote has 11,395 units; the minimum order quantity for the selected bottle is 11,396 units.

  

  

    
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. Spray bottle order: A 750 ml spray bottle with the wrong closure, too few units and 120 per cent recycled PET

    
The agent's request. Please quote 40,000 units of the 750 ml spray bottle, 32 g (28/410 / ASG neck) with a 28/410 closure and 120 per cent recycled PET. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Closure does not fit the bottle neck. The selected closure does not fit the neck finish of the selected bottle; the catalogue says each bottle combines with the closures of its own neck finish.
    • 
      
  • Below the minimum order quantity. The quote has 40,000 units; the minimum order quantity for the selected bottle is 50,000 units.
    • 
      
  • Recycled content outside 0 to 100 per cent. The recycled PET share is 120 per cent; the catalogue allows any share up to 100 per cent rPET.
    • 
    

    
2. Spray bottle order: The agent resubmits after fixing the errors

    
The agent's request. Please quote 40,000 units of the 750 ml spray bottle, 32 g (28/410 / ASG neck) with a 28/410 / ASG closure and 100 per cent recycled PET. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Below the minimum order quantity. The quote has 40,000 units; the minimum order quantity for the selected bottle is 50,000 units.
    • 
    

    
3. Spray bottle order: The agent resubmits after fixing the errors

    
The agent's request. Please quote 50,000 units of the 750 ml spray bottle, 32 g (28/410 / ASG neck) with a 28/410 / ASG closure and 100 per cent recycled PET. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 50,000 units ordered, 100 per cent rPET; the minimum order quantity for this bottle is 50,000 units.
    • 
    

    
4. Closure and quantity: A 500 ml milk bottle with a 28/410 closure and 100,000 units

    
The agent's request. Please quote 100,000 units of the 500 ml milk bottle (38 mm 2-start neck) with a 28/410 closure and 0 per cent recycled PET. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Closure does not fit the bottle neck. The selected closure does not fit the neck finish of the selected bottle; the catalogue says each bottle combines with the closures of its own neck finish.
    • 
      
  • Below the minimum order quantity. The quote has 100,000 units; the minimum order quantity for the selected bottle is 150,000 units.
    • 
    

    
5. Closure and quantity: The agent resubmits after fixing the errors

    
The agent's request. Please quote 150,000 units of the 500 ml milk bottle (38 mm 2-start neck) with a 38 mm 2-start closure and 30 per cent recycled PET. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 150,000 units ordered, 30 per cent rPET; the minimum order quantity for this bottle is 150,000 units.
    • 
    

    
6. Stated minimum: A 250 ml agrochemical bottle order stating a minimum of 5,000 units

    
The agent's request. Please quote 10,000 units of the 250 ml agrochemical bottle (45VTE neck) with a 45VTE closure and 25 per cent recycled PET. The order states a minimum order quantity of 5,000 units. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Stated minimum order quantity differs from the catalogue. The quote states a minimum order quantity of 5,000 units, but the catalogue lists 10,000 units for the selected bottle.
    • 
    

    
7. Stated minimum: The agent resubmits after fixing the errors

    
The agent's request. Please quote 10,000 units of the 250 ml agrochemical bottle (45VTE neck) with a 45VTE closure and 25 per cent recycled PET. The order states a minimum order quantity of 10,000 units. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 10,000 units ordered, 25 per cent rPET; the minimum order quantity for this bottle is 10,000 units.
    • 
    

  

  

    
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 for a standard PET bottle from a public product catalogue, with a matching closure, a quantity and a recycled-PET share. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the catalogue's published 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 40,000 units of the 750 ml spray bottle, 32 g (28/410 / ASG neck) with a 28/410 closure and 120 per cent recycled PET. It is ready to send.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with three findings, all in one answer. The selected closure does not fit the neck finish of the selected bottle; the catalogue says each bottle combines with the closures of its own neck finish. The quote has 40,000 units; the minimum order quantity for the selected bottle is 50,000 units. The recycled PET share is 120 per cent; the catalogue allows any share up to 100 per cent rPET.
    6. 
      
  6. The validator returned three 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 quote are checked against each other.
    7. 
      
  7. What this shows: for a closure that does not fit the bottle neck, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the closure neck finish to 28/410 / ASG and the Recycled PET share to 100 per cent.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. Still blocked, with one finding, all in one answer. The quote has 40,000 units; the minimum order quantity for the selected bottle is 50,000 units.
    12. 
      
  12. Two findings cleared; still blocked on below the minimum order quantity.
    13. 
      
  13. The agent resubmits once more.
    14. 
      
  14. The revised request. It changes the quantity to 50,000 units.
    15. 
      
  15. It calls the validator once more.
    16. 
      
  16. This time the validator clears it.
    17. 
      
  17. The earlier finding is cleared.
    18. 
      
  18. Three problems 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.
    19.