Predictika · Aseptic carton filling machine orders

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

An AI sales agent prepares an order for an aseptic carton filling machine from public product pages, with a pack volume, a number of formats and pack sizes, and an output. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published machine facts and returns a verdict, every reason and the figures it computed.

Scope: SIG aseptic carton filling machines (small-pack, medium-pack and SIG Neo): pack volume range, output, formats and pack sizes per machine. See everything this validator covers

This validator models orders for 13 aseptic carton filling machines named on public SIG pages, not just the scenarios shown below.

  • Small-pack machines — SIG Small 12 and 24, MiniBloc 12 and 24, XSlimBloc 12 and 24 and CompactBloc 12 Aseptic, each with the pack volume range of its format (80–200 ml, 125–250 ml, 150–350 ml, 200–500 ml), an output of 12,000 or 24,000 packs per hour, two formats on one machine and up to nine pack sizes.
  • Medium-pack machines — SIG Premium 9 Aseptic (500, 750 or 1000 ml packs, 9,000 packs per hour, two formats) and the volume ranges of StandardBloc 12, Midi 12 and SlimlineBloc 12 Aseptic.
  • SIG Neo machines — Neo XSlim 32 Aseptic (32,000 packs per hour, up to nine pack sizes) and Neo Midi 15 Aseptic (15,000 packs per hour, three pack sizes), as stated in the launch coverage.

Any order for these machines that touches these rules is in scope — not only the scenarios pictured here. Not covered: prices (SIG publishes none, so this validator produces no price build-up or line-item quote), the Food variants of the machines, outputs of the 12-series medium-pack machines (not read consistently), carton material, filling and service contracts, and any machine not named above.

The AI sales agentBuilds the 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 the 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.
Too many pack sizes or formats on one machineOnly with care
Limits differ by machine family and are usually kept in a table or a rule per machine and maintained by hand.		The machine sets its own limits and every count is compared with them on every call.
A stated output that disagrees with the machineOnly with workarounds
The output the agent states is free text or a separate field, so it takes an extra rule that compares it with the machine's own output.		The stated output is part of the request and is compared with the published output 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 pack volume is 600 ml; SIG lists the Premium 9 for 500, 750 and 1,000 ml packs.
2The pack volume is 1,100 ml; SIG lists the Premium 9 for 500, 750 and 1,000 ml packs.
3The order puts 3 pack formats on one machine; SIG lists up to 2 formats on one filling machine for the selected machine.
4The order asks for 10,000 packs per hour; the selected machine runs at 9,000 packs per hour.
5The order states an output of 12,000 packs per hour, but SIG lists 9,000 packs per hour for the selected machine.
6The pack volume is 1,200 ml; the selected machine fills 500 to 1,100 ml according to the SIG pages.
7The pack volume is 1,100 ml; the selected machine fills 500 to 1,000 ml according to the SIG pages.
8The pack volume is 400 ml; the selected machine fills 500 to 1,100 ml according to the SIG pages.
9The pack volume is 360 ml; the selected machine fills 150 to 350 ml according to the SIG pages.
10The pack volume is 124 ml; the selected machine fills 125 to 250 ml according to the SIG pages.
11The order asks for 24,000 packs per hour; the selected machine runs at 12,000 packs per hour.
12The pack volume is 520 ml; the selected machine fills 200 to 500 ml according to the SIG pages.
13The order asks for 10 pack sizes on one machine; SIG lists up to 9 pack sizes on the selected machine.
14The order states an output of 12,000 packs per hour, but SIG lists 24,000 packs per hour for the selected machine.
15The order asks for 33,000 packs per hour; the selected machine runs at 32,000 packs per hour.
16The order asks for 4 pack sizes on one machine; SIG lists up to 3 pack sizes on the selected machine.
17The order asks for 16,000 packs per hour; the selected machine runs at 15,000 packs per hour.
18The pack volume is 250 ml; the selected machine fills 80 to 200 ml according to the SIG pages.
19The order asks for 15,000 packs per hour; the selected machine runs at 12,000 packs per hour.
20The order states an output of 15,000 packs per hour, but SIG lists 12,000 packs per hour for the selected machine.

  

  

    
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. XSlimBloc order: An XSlimBloc 12 order at 24,000 packs per hour with ten pack sizes

    
The agent's request. Please quote a SIG XSlimBloc 12 Aseptic filling 180 ml packs, 2 formats and 10 pack sizes on the machine, at 24,000 packs per hour. The order states an output of 24,000 packs per hour. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Output above the machine speed. The order asks for 24,000 packs per hour; the selected machine runs at 12,000 packs per hour.
    • 
      
  • Too many pack sizes on one machine. The order asks for 10 pack sizes on one machine; SIG lists up to 9 pack sizes on the selected machine.
    • 
      
  • Stated output differs from SIG figure. The order states an output of 24,000 packs per hour, but SIG lists 12,000 packs per hour for the selected machine.
    • 
    

    
2. XSlimBloc order: The agent resubmits after fixing the errors

    
The agent's request. Please quote a SIG XSlimBloc 12 Aseptic filling 180 ml packs, 2 formats and 9 pack sizes on the machine, at 12,000 packs per hour. The order states an output of 24,000 packs per hour. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Stated output differs from SIG figure. The order states an output of 24,000 packs per hour, but SIG lists 12,000 packs per hour for the selected machine.
    • 
    

    
3. XSlimBloc order: The agent resubmits after fixing the errors

    
The agent's request. Please quote a SIG XSlimBloc 12 Aseptic filling 180 ml packs, 2 formats and 9 pack sizes on the machine, at 12,000 packs per hour. The order states an output of 12,000 packs per hour. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 180 ml packs, 2 format(s), 9 pack size(s), 12,000 packs per hour requested.
    • 
    

    
4. Small-pack machine: A MiniBloc 12 order with 300 ml packs and three formats

    
The agent's request. Please quote a SIG MiniBloc 12 Aseptic filling 300 ml packs, 3 formats and 4 pack sizes on the machine, at 12,000 packs per hour. The order states an output of 12,000 packs per hour. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Pack volume outside the machine range. The pack volume is 300 ml; the selected machine fills 125 to 250 ml according to the SIG pages.
    • 
      
  • Too many formats on one machine. The order puts 3 pack formats on one machine; SIG lists up to 2 formats on one filling machine for the selected machine.
    • 
    

    
5. Small-pack machine: The agent resubmits after fixing the errors

    
The agent's request. Please quote a SIG MiniBloc 12 Aseptic filling 250 ml packs, 2 formats and 4 pack sizes on the machine, at 12,000 packs per hour. The order states an output of 12,000 packs per hour. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 250 ml packs, 2 format(s), 4 pack size(s), 12,000 packs per hour requested.
    • 
    

    
6. SIG Neo order: A Neo Midi 15 order with four pack sizes

    
The agent's request. Please quote a SIG Neo Midi 15 Aseptic filling 1,000 ml packs, 1 format and 4 pack sizes on the machine, at 15,000 packs per hour. The order states an output of 15,000 packs per hour. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Too many pack sizes on one machine. The order asks for 4 pack sizes on one machine; SIG lists up to 3 pack sizes on the selected machine.
    • 
    

    
7. SIG Neo order: The agent resubmits after fixing the errors

    
The agent's request. Please quote a SIG Neo Midi 15 Aseptic filling 1,000 ml packs, 1 format and 3 pack sizes on the machine, at 15,000 packs per hour. The order states an output of 15,000 packs per hour. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 1,000 ml packs, 1 format(s), 3 pack size(s), 15,000 packs per hour requested.
    • 
    

  

  

    
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 an aseptic carton filling machine from public product pages, with a pack volume. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published machine facts 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 12 Aseptic filling 180 ml packs, 2 formats and 10 pack sizes on the machine, at 24,000 packs per hour. The order states an output of 24,000 packs per hour. The rest of the request is on screen.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with three findings, all in one answer. The order asks for 24,000 packs per hour; the selected machine runs at 12,000 packs per hour. The order asks for 10 pack sizes on one machine; SIG lists up to 9 pack sizes on the selected machine. The order states an output of 24,000 packs per hour, but SIG lists 12,000 packs per hour for the selected machine.
    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 too many pack sizes or formats on one machine, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the pack sizes on the machine to 9 and the output requested to 12,000 packs per hour.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. Still blocked, with one finding, all in one answer. The order states an output of 24,000 packs per hour, but SIG lists 12,000 packs per hour for the selected machine.
    12. 
      
  12. Two findings cleared; still blocked on stated output differs from SIG figure.
    13. 
      
  13. The agent resubmits once more.
    14. 
      
  14. The revised request. It changes the stated output as to 12,000 packs per hour.
    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 quote.
    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.