Predictika · Automated warehouse storage and picking systems

An AI sales agent's shuttle storage order, checked before it goes out

An AI sales agent prepares an order for an automated shuttle storage system: an OSR Shuttle Evo variant, the container size and load, the rack, the climate, the Pick-it-Easy workstations, the throughput the customer needs and the container locations it states. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the system rules and returns a verdict, every reason and the capacities it computed.

Scope: OSR Shuttle Evo (1D, 2D) and OSR Shuttle Evo+, Pick-it-Easy Evo and Pick-it-Easy Robot workstations, containers, depth, rack height, climate and capacity. See everything this validator covers

This validator models one automated shuttle storage order at a time, not just the scenarios shown below.

  • Shuttle and containers — the OSR Shuttle Evo in 1D and 2D variants and the Evo+ with Open Shuttle mobile robots; containers from 250 by 250 mm to 850 by 650 mm, loads up to 50 kg and storage up to 4 deep.
  • Rack and climate — the number of levels against the rack height, racks over 30 meters, and ambient, chilled and freezer stores.
  • Workstations — Pick-it-Easy Evo and Pick-it-Easy Robot, and whether the workstations and shuttle aisles can deliver the order lines and container moves per hour the customer needs.
  • Capacity — container locations from aisles, levels, depth and bays, and the location count the order states.

Any OSR Shuttle Evo storage order that touches these rules is in scope — not only the scenarios pictured here. The product names (OSR Shuttle Evo and Evo+, Open Shuttle, Pick-it-Easy Evo and Pick-it-Easy Robot), the container size range, the 50 kg load, the depth of up to 4 and the 1D and 2D variants come from KNAPP's public information. Throughput per aisle and workstation, the freezer and robot restriction, the rack height limit and the approval thresholds are modeled from comparable products and are not KNAPP's published rules. Not covered: prices (none are modeled, so there is no price build-up), software, conveyors, other KNAPP systems and engineering of a real installation.

The AI sales agentBuilds the storage 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.

6 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
Capacity that depends on several choicesOnly with care
Container moves and order lines per hour come from the shuttle variant, the number of aisles and the workstations together, so each pairing needs its own calculation rule.		Variant, aisles and workstations are in one request, and both capacities are computed and compared with the need on every call.
Options that exist only on one variantOnly with care
The Open Shuttle link exists only on the Evo+, so a product rule per option and variant is needed and kept up to date.		The variant and the option are in one request and the link is checked with everything else.
Climate that limits the workstationOnly with workarounds
The freezer restriction links the climate on one line with the workstation on another, so it needs a cross-line rule.		The climate and workstation are in one request and checked together.
Levels that must fit the rack heightOnly with care
The levels, container height and rack height interact, and the calculation sits in a price or validation rule that is easy to miss.		The needed height is computed from the levels and container height and compared with the rack 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 person 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 container is 860 by 400 mm; the OSR Shuttle Evo handles containers from 250 by 250 mm up to 850 by 650 mm.
2The container is 600 by 240 mm; the OSR Shuttle Evo handles containers from 250 by 250 mm up to 850 by 650 mm.
3The load per container is 51 kg; the OSR Shuttle Evo handles loads up to 50 kg.
4The storage depth is 5; the shuttle stores containers from 1 up to 4 deep.
5A rack over 30 meters needs a structural and fire protection review; a person should confirm it.
6The rack height is 37 meters; this model accepts racks up to 36 meters.
740 levels need about 16 meters of rack height; the rack is 12 meters.
8A freezer store down to minus 28 degrees Celsius needs a project review of the climate design; a person should confirm it.
9The Pick-it-Easy Robot cell is not accepted in a freezer environment in this model; use the Pick-it-Easy Evo workstation.
10Linking Open Shuttle mobile robots to the store needs the OSR Shuttle Evo+.
11The aisles supply 2,000 container moves per hour; the order needs 2200.
12The workstations handle 3,000 order lines per hour; the order needs 3100.
13More than 10 aisles is a multi-phase installation; a person should confirm the project plan.
14The order states 57,601 container locations; the aisles, levels, depth and bays give 57600.
15The storage depth is 0; the shuttle stores containers from 1 up to 4 deep.
1645 levels need about 18 meters of rack height; the rack is 12 meters.
17The aisles supply 3,200 container moves per hour; the order needs 4000.

  

  

    
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. E-commerce store: E-commerce fulfilment store with a 55 kg load, 5-deep racks and too little capacity

    
The agent's request. Please prepare an order for 10 aisles of the OSR Shuttle Evo (1D) storing 600 by 400 mm containers up to 55 kg, 5 deep, with 45 levels in a 33.0 meter rack in a chilled store, with 6 Pick-it-Easy Evo workstations, linked to Open Shuttle mobile robots, for 7,500 container moves and 4,200 order lines per hour. The order states 560,000 container locations. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Load above 50 kg. The load per container is 55 kg; the OSR Shuttle Evo handles loads up to 50 kg.
    • 
      
  • Storage depth not available. The storage depth is 5; the shuttle stores containers from 1 up to 4 deep.
    • 
      
  • Open Shuttle link needs Evo+. Linking Open Shuttle mobile robots to the store needs the OSR Shuttle Evo+.
    • 
      
  • Shuttle capacity below required moves. The aisles supply 5,000 container moves per hour; the order needs 7500.
    • 
      
  • Workstations below required lines. The workstations handle 3,000 order lines per hour; the order needs 4200.
    • 
      
  • Stated locations do not match. The order states 560,000 container locations; the aisles, levels, depth and bays give 540000.
    • 
      
  • Rack over 30 meters to confirm. A rack over 30 meters needs a structural and fire protection review; a person should confirm it.
    • 
    

    
2. E-commerce store: The agent resubmits after fixing the errors

    
The agent's request. Please prepare an order for 10 aisles of the OSR Shuttle Evo+ storing 600 by 400 mm containers up to 45 kg, 4 deep, with 45 levels in a 30.0 meter rack in a chilled store, with 9 Pick-it-Easy Evo workstations, linked to Open Shuttle mobile robots, for 7,500 container moves and 4,200 order lines per hour. The order states 432,000 container locations. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 432,000 container locations in 10 aisle(s); 8,000 container moves per hour and 4,500 order lines per hour of capacity.
    • 
    

    
3. Freezer store: Freezer store with robot workstations

    
The agent's request. Please prepare an order for 4 aisles of the OSR Shuttle Evo (2D) storing 600 by 400 mm containers up to 30 kg, 2 deep, with 36 levels in a 15.0 meter rack in a freezer store, with 3 Pick-it-Easy Robot workstations, for 3,000 container moves and 2,400 order lines per hour. The order states 57,600 container locations. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Robot workstation not for freezer. The Pick-it-Easy Robot cell is not accepted in a freezer environment in this model; use the Pick-it-Easy Evo workstation.
    • 
      
  • Freezer environment to confirm. A freezer store down to minus 28 degrees Celsius needs a project review of the climate design; a person should confirm it.
    • 
    

    
4. Freezer store: The agent resubmits after fixing the errors

    
The agent's request. Please prepare an order for 4 aisles of the OSR Shuttle Evo (2D) storing 600 by 400 mm containers up to 30 kg, 2 deep, with 36 levels in a 15.0 meter rack in a freezer store, with 6 Pick-it-Easy Evo workstations, for 3,000 container moves and 2,400 order lines per hour. The order states 57,600 container locations. It is ready to send.

    
Verdict: Needs approval.

    
    
      
  • Freezer environment to confirm. A freezer store down to minus 28 degrees Celsius needs a project review of the climate design; a person should confirm it.
    • 
      
  • Order summary. 57,600 container locations in 4 aisle(s); 3,200 container moves per hour and 3,000 order lines per hour of capacity.
    • 
    

    
5. Spare parts store: Spare parts store with oversize containers and too many levels

    
The agent's request. Please prepare an order for 4 aisles of the OSR Shuttle Evo (2D) storing 900 by 600 mm containers up to 40 kg, 2 deep, with 40 levels in a 12.0 meter rack in a ambient store, with 6 Pick-it-Easy Evo workstations, for 3,000 container moves and 2,400 order lines per hour. The order states 76,800 container locations. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Container size outside the shuttle range. The container is 900 by 600 mm; the OSR Shuttle Evo handles containers from 250 by 250 mm up to 850 by 650 mm.
    • 
      
  • Levels do not fit the rack height. 40 levels need about 16 meters of rack height; the rack is 12 meters.
    • 
    

    
6. Spare parts store: The agent resubmits after fixing the errors

    
The agent's request. Please prepare an order for 4 aisles of the OSR Shuttle Evo (2D) storing 800 by 600 mm containers up to 40 kg, 2 deep, with 30 levels in a 12.0 meter rack in a ambient store, with 6 Pick-it-Easy Evo workstations, for 3,000 container moves and 2,400 order lines per hour. The order states 57,600 container locations. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 57,600 container locations in 4 aisle(s); 3,200 container moves per hour and 3,000 order lines per hour of capacity.
    • 
    

  

  

    
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 automated shuttle storage system: an OSR Shuttle Evo variant, the container size and load, the rack, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the system rules and returns a verdict, every reason and the capacities it computed.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Please prepare an order for 10 aisles of the OSR Shuttle Evo (1D) storing 600 by 400 mm containers up to 55 kg. The order states 560,000 container locations. The rest of the request is on screen.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with six findings and one approval, all in one answer. The load per container is 55 kg; the OSR Shuttle Evo handles loads up to 50 kg. The storage depth is 5; the shuttle stores containers from 1 up to 4 deep. Linking Open Shuttle mobile robots to the store needs the OSR Shuttle Evo+. The other three are on screen.
    6. 
      
  6. The validator returned six blocking findings and one approval 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 capacity that depends on several choices, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the shuttle to OSR Shuttle Evo+, the load per container to 45 kg, the storage depth to 4, the rack height to 30.0, the workstations to 9 and the stated container locations as to 432000.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. This time the validator clears it.
    12. 
      
  12. All seven earlier findings are cleared, and the validator's figure matches the quote.
    13. 
      
  13. Seven problems caught in one call, fixed in one pass, 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.
    14.