Predictika · Steam trap orders

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

An AI sales agent prepares an order for ball float steam traps for a customer's steam line, with the pressures and temperature the customer gave. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published product data and returns a verdict, every reason and the figures it computed.

Scope: FT14 ball float steam traps (screwed and flanged): differential pressure variant, operating pressure and temperature limits. See everything this validator covers

This validator models orders for the FT14 ball float steam trap in the public technical information sheets for the screwed and flanged versions, not just the scenarios shown below.

  • Variants — FT14-4.5, FT14-10 and FT14-14, rated for a maximum differential pressure of 65, 145 and 203 psi; the differential pressure across the trap (inlet minus back pressure) must not exceed the variant's rating.
  • Operating limits — the sheets give a maximum operating pressure of 203 psi g and a maximum operating temperature of 482 degrees F at 189 psi g, which every order is checked against.
  • Connections and options — sizes 1/2, 3/4 and 1 inch (DN15, DN20, DN25), screwed BSP or NPT, or flanged EN 1092 PN16, ASME 150 or JIS/KS 20, with flow right-to-left or left-to-right; the needle valve (C) and integral strainer (X) options are accepted. Ratings stated on the order are compared with the data sheet figures.

Any order for these traps that touches these rules is in scope — not only the scenarios pictured here. Not covered: prices (no public price list, so this validator produces no price build-up or line-item quote), other Spirax Sarco trap types and product lines, the vertical-flow version, capacity sizing, and installation design.

The AI sales agentBuilds the steam trap 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 differential pressure above the variant ratingOnly with care
The usable differential pressure depends on the variant chosen, so it needs a computed value (inlet minus back pressure) and a rule per variant, kept in step with the data sheet.		The inlet and back pressures are in one request, the differential is computed and compared with the variant on every call.
Limits that depend on the customer's steam conditionsOnly with care
Pressure and temperature limits are customer conditions, not catalogue options, so they usually live in separate validation rules that someone must keep current.		The conditions are part of the request and checked against the sheet limits on every call.
A stated rating that disagrees with the data sheetOnly with workarounds
The rating the agent states is free text or a separate field, so it takes an extra rule that compares it with the variant's own rating.		The stated figures are part of the request and are compared with the data sheet figures 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 differential pressure across the trap is 66 psi; the selected variant is rated for at most 65 psi.
2The differential pressure across the trap is 146 psi; the selected variant is rated for at most 145 psi.
3The inlet pressure is 204 psi g; the FT14 maximum operating pressure (PMO) is 203 psi g.
4The differential pressure across the trap is 204 psi; the selected variant is rated for at most 203 psi.
5The operating temperature is 483 degrees F; the FT14 maximum operating temperature is 482 degrees F at 189 psi g.
6The quote states a maximum differential pressure of 65 psi; the selected variant is rated 145 psi.
7The quote states a maximum differential pressure of 203 psi; the selected variant is rated 65 psi.
8The quote states a maximum operating pressure of 232 psi g; the FT14 data sheet gives 203 psi g.
9The inlet pressure is 250 psi g; the FT14 maximum operating pressure (PMO) is 203 psi g.
10The differential pressure across the trap is 250 psi; the selected variant is rated for at most 65 psi.
11The operating temperature is 500 degrees F; the FT14 maximum operating temperature is 482 degrees F at 189 psi g.
12The quote states a maximum differential pressure of 145 psi; the selected variant is rated 65 psi.

  

  

    
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. Steam conditions: An FT14-14 with inlet pressure and temperature over the limits

    
The agent's request. Please quote 3 FT14 ball float steam traps, FT14-14 variant, 1 inch (DN25), flanged EN 1092 PN16, flow left to right, for a steam line at 220 psi g inlet and 15 psi g back pressure, at 500 degrees F. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Inlet pressure above the trap maximum operating pressure. The inlet pressure is 220 psi g; the FT14 maximum operating pressure (PMO) is 203 psi g.
    • 
      
  • Differential pressure above the variant rating. The differential pressure across the trap is 205 psi; the selected variant is rated for at most 203 psi.
    • 
      
  • Temperature above the trap maximum. The operating temperature is 500 degrees F; the FT14 maximum operating temperature is 482 degrees F at 189 psi g.
    • 
    

    
2. Steam conditions: The agent resubmits after fixing the errors

    
The agent's request. Please quote 3 FT14 ball float steam traps, FT14-14 variant, 1 inch (DN25), flanged EN 1092 PN16, flow left to right, for a steam line at 195 psi g inlet and 15 psi g back pressure, at 500 degrees F. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Temperature above the trap maximum. The operating temperature is 500 degrees F; the FT14 maximum operating temperature is 482 degrees F at 189 psi g.
    • 
    

    
3. Steam conditions: The agent resubmits after fixing the errors

    
The agent's request. Please quote 3 FT14 ball float steam traps, FT14-14 variant, 1 inch (DN25), flanged EN 1092 PN16, flow left to right, for a steam line at 195 psi g inlet and 15 psi g back pressure, at 450 degrees F. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 3 trap(s); differential pressure 180 psi against a variant rating of 203 psi.
    • 
    

    
4. Differential pressure: An FT14-4.5 on a line with an 80 psi differential pressure

    
The agent's request. Please quote 6 FT14 ball float steam traps, FT14-4.5 variant, 3/4 inch (DN20), screwed BSP, flow right to left, for a steam line at 110 psi g inlet and 30 psi g back pressure, at 345 degrees F. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Differential pressure above the variant rating. The differential pressure across the trap is 80 psi; the selected variant is rated for at most 65 psi.
    • 
    

    
5. Differential pressure: The agent resubmits after fixing the errors

    
The agent's request. Please quote 6 FT14 ball float steam traps, FT14-10 variant, 3/4 inch (DN20), screwed BSP, flow right to left, for a steam line at 110 psi g inlet and 30 psi g back pressure, at 345 degrees F. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 6 trap(s); differential pressure 80 psi against a variant rating of 145 psi.
    • 
    

    
6. Stated ratings: An FT14-10 order stating ratings that differ from the data sheet

    
The agent's request. Please quote 8 FT14 ball float steam traps, FT14-10 variant, 1/2 inch (DN15), flanged ASME 150, flow right to left, for a steam line at 120 psi g inlet and 10 psi g back pressure, at 350 degrees F. The quote states a maximum differential pressure of 203 psi and a maximum operating pressure of 232 psi g. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Stated differential rating differs from the variant. The quote states a maximum differential pressure of 203 psi; the selected variant is rated 145 psi.
    • 
      
  • Stated operating pressure differs from the data sheet. The quote states a maximum operating pressure of 232 psi g; the FT14 data sheet gives 203 psi g.
    • 
    

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

    
The agent's request. Please quote 8 FT14 ball float steam traps, FT14-10 variant, 1/2 inch (DN15), flanged ASME 150, flow right to left, for a steam line at 120 psi g inlet and 10 psi g back pressure, at 350 degrees F. The quote states a maximum differential pressure of 145 psi and a maximum operating pressure of 203 psi g. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 8 trap(s); differential pressure 110 psi against a variant rating of 145 psi.
    • 
    

  

  

    
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 ball float steam traps for a customer's steam line, with the pressures and temperature the customer gave. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published product data 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 3 FT14 ball float steam traps, FT14-14 variant, 1 inch (DN25), flanged EN 1092 PN16, flow left to right. It is ready to send. 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 inlet pressure is 220 psi g; the FT14 maximum operating pressure (PMO) is 203 psi g. The differential pressure across the trap is 205 psi; the selected variant is rated for at most 203 psi. The operating temperature is 500 degrees F; the FT14 maximum operating temperature is 482 degrees F at 189 psi g.
    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 a differential pressure above the variant rating, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the inlet pressure to 195 psi g.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. Still blocked, with one finding, all in one answer. The operating temperature is 500 degrees F; the FT14 maximum operating temperature is 482 degrees F at 189 psi g.
    12. 
      
  12. Two findings cleared; still blocked on temperature above the trap maximum.
    13. 
      
  13. The agent resubmits once more.
    14. 
      
  14. The revised request. It changes the operating temperature to 450 degrees F.
    15. 
      
  15. It calls the validator once more.
    16. 
      
  16. This time the validator clears it.
    17. 
      
  17. The earlier finding is cleared.
    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.