Predictika · Small-size aseptic carton filling machines

An AI sales agent's filling-machine order, checked before it goes out

An AI sales agent prepares an order for a small-size aseptic carton filling machine: a machine model, a pack volume, the number of pack volumes, the output the customer needs and, for products with pieces or body, a Drinksplus or Food option. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the machine specifications published on the SIG website and returns a verdict, every reason and the figures it computed.

Scope: SIG small-size aseptic carton filling machines (Small, MiniBloc, XSlimBloc and CompactBloc 12/24 lines): pack volume range, volumes per machine, output and Drinksplus / Food option limits. See everything this validator covers

This validator models orders for seven small-size aseptic carton filling machines in SIG's public package-finder pages, not just the scenarios shown below.

  • Machines — SIG Small 12 and 24 (150 to 350 ml), MiniBloc 12 and 24 (125 to 250 ml), XSlimBloc 12 and 24 (80 to 200 ml) and CompactBloc 12 (200 to 500 ml); the 12 models are listed at 12,000 packs per hour and the 24 models at 24,000.
  • Pack volumes — the pack volume must lie in the machine's range, and one machine handles up to 9 pack volumes.
  • Output — the output the customer needs cannot exceed the machine's rated packs per hour, and a rating stated on the order is compared with the published one.
  • Drinksplus and Food options — the product's particulate size, chunky share, fiber length and viscosity are compared with the published limits of each option (Drinksplus: 6 mm, 10 per cent, 15 mm, 1,000 mPas; Food: 6 mm, 15 per cent, 15 mm, 3,500 mPas).

Any order for these machines that touches these rules is in scope — not only the scenarios pictured here. Not covered: prices (SIG publishes none for filling machines, so this validator produces no price build-up or line-item quote), the medium-size and large-size machines, the SIG Neo range, spouted-pouch and bag-in-box equipment, closures, packaging materials and service contracts.

The AI sales agentBuilds the filling-machine 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 pack volume outside a machine's rangeOnly with care
Each machine has its own volume range, so each needs its own rule, and every new machine adds more rules to maintain.		The machine sets its own range and every pack volume is compared with it on every call.
Product limits that depend on the option chosenOnly with workarounds
The limits for particulates, chunks, fibers and viscosity differ between Drinksplus and Food, so the rules multiply by option and by property.		Each option's limits are checked against the product on every call, whatever order the choices arrived in.
A stated output that disagrees with the machine ratingOnly 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 machine's own rating.		The stated figure is part of the request and is compared with the published rating 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.

    
1A pack volume of 149 ml is outside the range of the selected machine, 150 to 350 ml.
2A pack volume of 351 ml is outside the range of the selected machine, 150 to 350 ml.
3A pack volume of 251 ml is outside the range of the selected machine, 125 to 250 ml.
4A pack volume of 300 ml is outside the range of the selected machine, 80 to 200 ml.
5The order has 12 pack volumes on one machine; a machine handles up to 9 volumes.
6The order needs 24,000 packs per hour; the selected machine is rated at 12,000 packs per hour.
7The quote states 24,000 packs per hour, but the selected machine is rated at 12,000 packs per hour.
8The Drinksplus option handles viscosity up to 1,000 mPas; the product has 3,000 mPas.
9A pack volume of 79 ml is outside the range of the selected machine, 80 to 200 ml.
10A pack volume of 199 ml is outside the range of the selected machine, 200 to 500 ml.
11A pack volume of 501 ml is outside the range of the selected machine, 200 to 500 ml.
12The order has 10 pack volumes on one machine; a machine handles up to 9 volumes.
13The order has 0 pack volumes on one machine; a machine handles up to 9 volumes.
14The order needs 24,001 packs per hour; the selected machine is rated at 24,000 packs per hour.
15The quote states 12,000 packs per hour, but the selected machine is rated at 24,000 packs per hour.
16The Drinksplus option handles particulates up to 6 mm; the product has 7 mm.
17The Drinksplus option handles up to 10 per cent chunky ingredients; the product has 11 per cent.
18The Drinksplus option handles fibers up to 15 mm long; the product has 16 mm.
19The Drinksplus option handles viscosity up to 1,000 mPas; the product has 1,001 mPas.
20The Food option handles particulates up to 6 mm; the product has 7 mm.
21The Food option handles up to 15 per cent chunky ingredients; the product has 16 per cent.
22The Food option handles fibers up to 15 mm long; the product has 16 mm.
23The Food option handles viscosity up to 3,500 mPas; the product has 3,501 mPas.
24The Drinksplus option handles viscosity up to 1,000 mPas; the product has 2,000 mPas.

  

  

    
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. Machine fit: A fruit drink order on a 12,000 packs-per-hour machine

    
The agent's request. Please quote a SIG Small 12 for 400 ml packs, 4 pack volumes on the machine, at 18,000 packs per hour. The order states a rated output of 24,000 packs per hour and uses the Drinksplus option. The product has particulates up to 3 mm, 5 per cent chunky ingredients, fibers up to 8 mm and a viscosity of 600 mPas. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Pack volume outside the machine range. A pack volume of 400 ml is outside the range of the selected machine, 150 to 350 ml.
    • 
      
  • Required output above the machine rating. The order needs 18,000 packs per hour; the selected machine is rated at 12,000 packs per hour.
    • 
      
  • Stated output differs from the machine rating. The quote states 24,000 packs per hour, but the selected machine is rated at 12,000 packs per hour.
    • 
    

    
2. Machine fit: The agent resubmits after fixing the errors

    
The agent's request. Please quote a SIG Small 24 for 330 ml packs, 4 pack volumes on the machine, at 18,000 packs per hour. The order states a rated output of 24,000 packs per hour and uses the Drinksplus option. The product has particulates up to 3 mm, 5 per cent chunky ingredients, fibers up to 8 mm and a viscosity of 600 mPas. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 330 ml packs, 4 pack volume(s) on one machine; the machine is rated at 24,000 packs per hour.
    • 
    

    
3. Drink with pulp: A pulpy drink in ten pack volumes on the Drinksplus option

    
The agent's request. Please quote a SIG XSlimBloc 24 for 220 ml packs, 10 pack volumes on the machine, at 24,000 packs per hour. The order states a rated output of 24,000 packs per hour and uses the Drinksplus option. The product has particulates up to 5 mm, 12 per cent chunky ingredients, fibers up to 10 mm and a viscosity of 2,500 mPas. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Pack volume outside the machine range. A pack volume of 220 ml is outside the range of the selected machine, 80 to 200 ml.
    • 
      
  • Too many pack volumes on one machine. The order has 10 pack volumes on one machine; a machine handles up to 9 volumes.
    • 
      
  • Drinksplus chunky share too high. The Drinksplus option handles up to 10 per cent chunky ingredients; the product has 12 per cent.
    • 
      
  • Drinksplus viscosity too high. The Drinksplus option handles viscosity up to 1,000 mPas; the product has 2,500 mPas.
    • 
    

    
4. Drink with pulp: The agent resubmits after fixing the errors

    
The agent's request. Please quote a SIG XSlimBloc 24 for 200 ml packs, 9 pack volumes on the machine, at 24,000 packs per hour. The order states a rated output of 24,000 packs per hour and uses the Drinksplus option. The product has particulates up to 5 mm, 12 per cent chunky ingredients, fibers up to 10 mm and a viscosity of 2,500 mPas. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Drinksplus chunky share too high. The Drinksplus option handles up to 10 per cent chunky ingredients; the product has 12 per cent.
    • 
      
  • Drinksplus viscosity too high. The Drinksplus option handles viscosity up to 1,000 mPas; the product has 2,500 mPas.
    • 
    

    
5. Drink with pulp: The agent resubmits after fixing the errors

    
The agent's request. Please quote a SIG XSlimBloc 24 for 200 ml packs, 9 pack volumes on the machine, at 24,000 packs per hour. The order states a rated output of 24,000 packs per hour and uses the Food option. The product has particulates up to 5 mm, 12 per cent chunky ingredients, fibers up to 10 mm and a viscosity of 2,500 mPas. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 200 ml packs, 9 pack volume(s) on one machine; the machine is rated at 24,000 packs per hour.
    • 
    

    
6. Stated output: A milk drink order stating a rated output of 24,000 packs per hour

    
The agent's request. Please quote a SIG MiniBloc 12 for 200 ml packs, 5 pack volumes on the machine, at 12,000 packs per hour. The order states a rated output of 24,000 packs per hour and uses no option. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Stated output differs from the machine rating. The quote states 24,000 packs per hour, but the selected machine is rated at 12,000 packs per hour.
    • 
    

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

    
The agent's request. Please quote a SIG MiniBloc 12 for 200 ml packs, 5 pack volumes on the machine, at 12,000 packs per hour. The order states a rated output of 12,000 packs per hour and uses no option. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 200 ml packs, 5 pack volume(s) on one machine; the machine is rated at 12,000 packs per hour.
    • 
    

  

  

    
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 small-size aseptic carton filling machine: a machine model, a pack volume, the number of pack volumes, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the machine specifications published on the SIG website 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 a SIG XSlimBloc 24 for 220 ml packs, 10 pack volumes on the machine, at 24,000 packs per hour. The order states a rated output of 24,000 packs per hour and uses the Drinksplus option. 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. A pack volume of 220 ml is outside the range of the selected machine, 80 to 200 ml. The order has 10 pack volumes on one machine; a machine handles up to 9 volumes. The Drinksplus option handles up to 10 per cent chunky ingredients; the product has 12 per cent. 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 quote are checked against each other.
    7. 
      
  7. What this shows: for a pack volume outside a machine's range, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the pack volume to 200 ml and the pack volumes on the machine to 9.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. Still blocked, with two findings, all in one answer. The Drinksplus option handles up to 10 per cent chunky ingredients; the product has 12 per cent. The Drinksplus option handles viscosity up to 1,000 mPas; the product has 2,500 mPas.
    12. 
      
  12. Two findings cleared. Still blocking: Drinksplus chunky share too high and Drinksplus viscosity too high.
    13. 
      
  13. The agent resubmits once more.
    14. 
      
  14. The revised request. It changes the option to food.
    15. 
      
  15. It calls the validator once more.
    16. 
      
  16. This time the validator clears it.
    17. 
      
  17. Both earlier findings are cleared, and the validator's figure matches the quote.
    18. 
      
  18. Four 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. Now you can try the other scenarios yourself.
    19.