Predictika · Industrial compressed air

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

An AI sales agent prepares an order for a Kaeser fixed-speed rotary screw compressor for a machine shop or plant: the model, the operating pressure, the flow the customer needs, whether an integral dryer is wanted, and the capacity the quote states. Before it goes out, the agent sends the order to Predictika, which checks it against a declarative model of the capacities in Kaeser's published SX to HSD brochure and returns a verdict, every reason and the brochure capacity it computed. The customer is fictional.

Scope: Kaeser fixed-speed rotary screw compressors, SX 3 to HSD 650 (37 models): operating pressure, flow needed, integral dryer and stated capacity. See everything this validator covers

This validator models orders for the 37 fixed-speed models in Kaeser's "Industrial Rotary Screw Compressors SX - HSD Series" brochure (USSCRWBULLTN 05/25), not just the scenarios shown below.

  • Models — SX, SM, SK, AS (belt drive) and ASD, BSD, CSD, DSD, ESD, FSD and HSD (direct drive), each with the free air delivery the brochure gives at 125 psig, at its middle pressure (160 psig belt drive, 175 psig direct drive) and at 217 psig.
  • Operating pressure — a model the brochure shows with a dash at a pressure has no listed capacity there and is blocked. A pressure that is not one of the brochure's columns for the series needs a person to confirm the capacity.
  • Flow — the flow the customer needs, in cfm, is compared with the brochure capacity at the ordered pressure.
  • Integral dryer — the brochure lists integral dryers from SX 3 through DSD 175; a dryer on a larger model is blocked.
  • Stated capacity — the capacity the quote states must equal the brochure figure for the model and pressure.

Any order for these models is in scope — not only the scenarios pictured here. Not covered: SFC variable-frequency models, AIRCENTER and custom systems, prices (the brochure gives none), motor voltage and options, and installation.

The AI sales agentBuilds the compressor order from the customer's request 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 model with no capacity at the ordered pressureOnly with workarounds
The brochure leaves some model and pressure cells empty. A rules-based CPQ needs a rule for every empty cell, and each new model means new rules.		The capacity is looked up for the model and pressure on every call, and a missing figure is flagged.
Flow needed above what the model deliversOnly with care
The capacity depends on both the model and the pressure, so a rule has to carry the whole table and keep it in step with the brochure.		The brochure capacity is computed from the model and pressure and compared with the flow needed on every call.
An integral dryer on a model that does not offer oneOnly with care
The dryer applies only to part of the range. A rule has to name every larger model, and is easy to miss when a model is added.		The dryer choice is checked against the model on every call, wherever it was entered.
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 Kaeser brochure lists no capacity for this model at this operating pressure.
2The order needs 9.3 cfm; the Kaeser brochure gives 9.2 cfm for this model at this operating pressure.
3The order needs 192.5 cfm; the Kaeser brochure gives 192 cfm for this model at this operating pressure.
4The order needs 320 cfm; the Kaeser brochure gives 307 cfm for this model at this operating pressure.
5The order needs 2008 cfm; the Kaeser brochure gives 2007 cfm for this model at this operating pressure.
6The Kaeser brochure gives capacities only at 125, 160 and 217 psig for this series of drive (belt: 160 psig; direct drive: 175 psig); a person should confirm the capacity at the pressure ordered.
7The Kaeser brochure lists integral dryers for SX 3 through DSD 175 only; the model ordered is larger.
8The order states a capacity of 160 cfm; the Kaeser brochure gives 192 cfm for this model at this operating pressure.
9The order states a capacity of 12 cfm; the Kaeser brochure gives 15.9 cfm for this model at this operating pressure.
10The order states a capacity of 374 cfm; the Kaeser brochure gives 469 cfm for this model at this operating pressure.
11The order states a capacity of 2471 cfm; the Kaeser brochure gives 3000 cfm for this model at this operating pressure.
12The order states a capacity of 320 cfm; the Kaeser brochure gives 307 cfm for this model at this operating pressure.
13The order needs 900 cfm; the Kaeser brochure gives 689 cfm for this model at this operating pressure.
14The order states a capacity of 1000 cfm; the Kaeser brochure gives 689 cfm for this model at this operating pressure.

  

  

    
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. Pressure: An SX 3 ordered at 217 psig

    
The agent's request. Please prepare the order for a Kaeser SX 3 compressor operating at 217 psig. The customer needs 8 cfm. The quote states a capacity of 8.8 cfm. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Model lists no capacity at this pressure. The Kaeser brochure lists no capacity for this model at this operating pressure.
    • 
    

    
2. Pressure: The agent resubmits after fixing the errors

    
The agent's request. Please prepare the order for a Kaeser SX 4 compressor operating at 217 psig. The customer needs 8 cfm. The quote states a capacity of 8.8 cfm. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Brochure capacity. The Kaeser brochure gives this model a capacity of 8.8 cfm at this operating pressure.
    • 
    

    
3. Integral dryer: A large plant compressor with an integral dryer

    
The agent's request. Please prepare the order for a Kaeser DSD 250 compressor with an integral dryer operating at 125 psig. The customer needs 1000 cfm. The quote states a capacity of 1075 cfm. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Integral dryer not offered on this model. The Kaeser brochure lists integral dryers for SX 3 through DSD 175 only; the model ordered is larger.
    • 
    

    
4. Integral dryer: The agent resubmits after fixing the errors

    
The agent's request. Please prepare the order for a Kaeser DSD 250 compressor operating at 125 psig. The customer needs 1000 cfm. The quote states a capacity of 1075 cfm. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Brochure capacity. The Kaeser brochure gives this model a capacity of 1075 cfm at this operating pressure.
    • 
    

    
5. Flow and pressure: A CSD 110 for 320 cfm at 175 psig

    
The agent's request. Please prepare the order for a Kaeser CSD 110 compressor operating at 175 psig. The customer needs 320 cfm. The quote states a capacity of 320 cfm. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Flow needed above the brochure capacity. The order needs 320 cfm; the Kaeser brochure gives 307 cfm for this model at this operating pressure.
    • 
      
  • Stated capacity does not match. The order states a capacity of 320 cfm; the Kaeser brochure gives 307 cfm for this model at this operating pressure.
    • 
    

    
6. Flow and pressure: The agent resubmits after fixing the errors

    
The agent's request. Please prepare the order for a Kaeser CSD 130 compressor operating at 160 psig. The customer needs 320 cfm. The quote states a capacity of 374 cfm. It is ready to send.

    
Verdict: Needs approval.

    
    
      
  • Pressure is not a rated point for this series. The Kaeser brochure gives capacities only at 125, 160 and 217 psig for this series of drive (belt: 160 psig; direct drive: 175 psig); a person should confirm the capacity at the pressure ordered.
    • 
    

    
7. Flow and pressure: The agent resubmits after fixing the errors

    
The agent's request. Please prepare the order for a Kaeser CSD 130 compressor operating at 175 psig. The customer needs 320 cfm. The quote states a capacity of 374 cfm. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Brochure capacity. The Kaeser brochure gives this model a capacity of 374 cfm at this operating pressure.
    • 
    

  

  

    
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 Kaeser fixed-speed rotary screw compressor for a machine shop or plant: the model, the operating pressure, the flow the customer needs, and more. Before it goes out, the agent sends the order to Predictika, which checks it against a declarative model of the capacities in Kaeser's published SX to HSD brochure and returns a verdict, every reason and the brochure capacity it computed. The customer is fictional.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Please prepare the order for a Kaeser CSD 110 compressor operating at 175 psig. The customer needs 320 cfm. The rest of the request is on screen. The quote states a capacity of 320 cfm.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with two findings, all in one answer. The order needs 320 cfm; the Kaeser brochure gives 307 cfm for this model at this operating pressure. The order states a capacity of 320 cfm; the Kaeser brochure gives 307 cfm for this model at this operating pressure.
    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 quote are checked against each other.
    7. 
      
  7. What this shows: for flow needed above what the model delivers, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the model to CSD 130, the operating pressure to 160 psig and the stated capacity to 374.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. Not blocked, but held for a person.
    12. 
      
  12. The two blocking findings are cleared; one approval remains for a person: pressure is not a rated point for this series.
    13. 
      
  13. The agent resubmits once more.
    14. 
      
  14. The revised request. It changes the operating pressure to 175 psig.
    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. Two 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.