Predictika · Packaging machine configurations

An AI sales agent's Lightline machine configuration, checked before it goes out

An AI sales agent prepares a configuration for a preconfigured packaging machine: the machine, the number of robots, the carton type or sealing technology and the output it states. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published product pages and returns a verdict, every reason and the figures it computed.

Scope: Schubert Lightline preconfigured machines (Cartonpacker, Flowpacker, Pickerline): robots, carton type, sealing technology, product types and output. See everything this validator covers

This validator models one Schubert Lightline machine configuration at a time, from the public Lightline product pages, not just the scenarios shown below.

  • Lightline Flowpacker and Pickerline — 1, 2, 4 or 6 F4 pick-and-place robots; the Flowpacker is equipped with one of four sealing technologies, so a Flowpacker without one is incomplete.
  • Lightline Cartonpacker — a one-module case packer with three F2 robots, built for one carton type (trays, RSC cartons or wrap-around cartons among them) and one type of product at a time (bags, boxes, bottles or cans), up to 25 two-piece cases per minute.

Any Lightline configuration that touches these rules is in scope — not only the scenarios pictured here. Not covered: Schubert TLM machines, which are engineered to order, other Schubert lines, the fourth Cartonpacker carton type (the product pages name it differently in two places), robot tools, output of the Flowpacker and the Pickerline (not published on the pages read), and prices — Schubert does not publish prices, so this validator produces no price build-up.

The AI sales agentBuilds the machine configuration 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 robot count that must be one of 1, 2, 4 or 6Only with care
A product rule on a numeric attribute with a list of allowed values, per machine.		The robot count is in the request and checked against the allowed list on every call.
A machine that must have one of four sealing technologies selectedOnly with care
A required-choice rule per machine, kept in step with the machine variants.		A missing selection is reported with the other findings.
A published maximum output and a one-product-type limitOnly with workarounds
The stated output and the number of product types are not product attributes; they need validation rules built and kept current.		Both figures travel with the configuration and are checked on each call.

  

  

    
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 configuration; approval findings need a person to sign off; everything else is computed.

    
1The configuration has 3 F4 pick-and-place robots; the Flowpacker and the Pickerline come with 1, 2, 4 or 6.
2The configuration has 5 F4 pick-and-place robots; the Flowpacker and the Pickerline come with 1, 2, 4 or 6.
3The configuration has 8 F4 pick-and-place robots; the Flowpacker and the Pickerline come with 1, 2, 4 or 6.
4The Flowpacker is equipped with one of four sealing technologies and the configuration has none selected.
5The Cartonpacker is built for one carton type (trays, RSC cartons or wrap-around cartons among them) and the configuration has none selected.
6The configuration states 26 cases per minute; the Lightline Cartonpacker is published at up to 25 two-piece cases per minute.
7The configuration has 2 product types; the Lightline Cartonpacker is designed for one type of product at a time.
8The configuration has 2 F2 robots; the Lightline Cartonpacker has three F2 robots.
9The configuration states 40 cases per minute; the Lightline Cartonpacker is published at up to 25 two-piece cases per minute.
10The configuration has 3 product types; the Lightline Cartonpacker is designed for one type of product at a time.

  

  

    
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. Flowpacker, robots: A Flowpacker with three F4 robots

    
The agent's request. Please configure a Lightline Flowpacker with 3 F4 pick-and-place robots and ultrasonic longitudinal sealing with flying cross sealing. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Number of F4 robots is not available. The configuration has 3 F4 pick-and-place robots; the Flowpacker and the Pickerline come with 1, 2, 4 or 6.
    • 
    

    
2. Flowpacker, robots: The agent resubmits after fixing the errors

    
The agent's request. Please configure a Lightline Flowpacker with 4 F4 pick-and-place robots and ultrasonic longitudinal sealing with flying cross sealing. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Configuration summary. Lightline Flowpacker with 4 F4 pick-and-place robots and one of four sealing technologies. No price build-up: Schubert does not publish prices.
    • 
    

    
3. Cartonpacker, output and products: A Cartonpacker at 30 cases per minute for two product types

    
The agent's request. Please configure a Lightline Cartonpacker for RSC cartons packing bottles, with 3 F2 robots. It will pack 2 product types. The configuration states an output of 30 cases per minute. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Cartonpacker output above the published maximum. The configuration states 30 cases per minute; the Lightline Cartonpacker is published at up to 25 two-piece cases per minute.
    • 
      
  • Cartonpacker packs one product type at a time. The configuration has 2 product types; the Lightline Cartonpacker is designed for one type of product at a time.
    • 
    

    
4. Cartonpacker, output and products: The agent resubmits after fixing the errors

    
The agent's request. Please configure a Lightline Cartonpacker for RSC cartons packing bottles, with 3 F2 robots. It will pack one product type. The configuration states an output of 25 cases per minute. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Configuration summary. One-module Lightline Cartonpacker with 3 F2 robots, footprint about 3.5 x 2.5 meters, up to 25 two-piece cases per minute. No price build-up: Schubert does not publish prices.
    • 
    

    
5. Flowpacker, sealing: A Flowpacker with no sealing technology

    
The agent's request. Please configure a Lightline Flowpacker with 2 F4 pick-and-place robots. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Flowpacker needs a sealing technology. The Flowpacker is equipped with one of four sealing technologies and the configuration has none selected.
    • 
    

    
6. Flowpacker, sealing: The agent resubmits after fixing the errors

    
The agent's request. Please configure a Lightline Flowpacker with 2 F4 pick-and-place robots and ultrasonic longitudinal sealing with rotary cross sealing. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Configuration summary. Lightline Flowpacker with 2 F4 pick-and-place robots and one of four sealing technologies. No price build-up: Schubert does not publish prices.
    • 
    

    
7. Pickerline, robots: A Pickerline with eight F4 robots

    
The agent's request. Please configure a Lightline Pickerline with 8 F4 pick-and-place robots. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Number of F4 robots is not available. The configuration has 8 F4 pick-and-place robots; the Flowpacker and the Pickerline come with 1, 2, 4 or 6.
    • 
    

  

  

    
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 configuration for a preconfigured packaging machine: the machine, the number of robots, the carton type or sealing technology and the output it states. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published product pages 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 configure a Lightline Cartonpacker for RSC cartons packing bottles, with 3 F2 robots. It will pack 2 product types. The rest of the request is on screen.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with two findings, all in one answer. The configuration states 30 cases per minute; the Lightline Cartonpacker is published at up to 25 two-piece cases per minute. The configuration has 2 product types; the Lightline Cartonpacker is designed for one type of product at a time.
    6. 
      
  6. The validator returned two 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 configuration are checked against each other.
    7. 
      
  7. What this shows: for a published maximum output and a one-product-type limit, a rules-based CPQ can do this only with workarounds.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the product types to 1 and the stated output as to 25 cases per minute.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. This time the validator clears it.
    12. 
      
  12. Both earlier findings are cleared.
    13. 
      
  13. Two problems caught in one call, fixed in one pass, and a clean configuration. That is the value of Predictika's validator: catching mistakes before the configuration goes live. Now you can try the other scenarios yourself.
    14.