Predictika · Commercial vehicle components

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

An AI sales agent prepares an order for a SAF MODUL rigid trailer axle: the axle version, wheel configuration, wheel bolt pattern and rim, brake, axle load and speed, and the load rating, brake size and ABS ring it quotes. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the manufacturer's published product overview and returns a verdict, every reason and the figures it looked up.

Scope: SAF-HOLLAND SAF MODUL rigid axles (35 versions, 9 to 12 t, disc and drum brakes), from the published MODUL product overview. See everything this validator covers

This validator models orders for the 35 rigid axle versions in the SAF-HOLLAND MODUL 7–14 t air suspension overview (Rev B, 08/2018), not just the scenarios shown below.

  • Axle version data — axle load up to 105 km/h, single or twin wheels, wheel offset, brake size and brake, and ABS exciter-ring teeth, as listed for each version; the order must not exceed the rating or the speed, and the figures the quote states must match.
  • Wheel end — the wheel bolt pattern and the rim sizes listed for each version, and the brake listed for it.
  • Special axles — 7 t, 13 to 14 t, friction-steered and forced-steering axles are named in the overview with no data, so a person has to confirm them.

Any MODUL rigid axle order that touches these rules is in scope — not only the scenarios pictured here. Not covered: prices (SAF-HOLLAND publishes no list prices, so this validator produces no price build-up), the air suspension models, trailing-arm and air-spring combinations, and options such as lift axles or tyre inflation. The overview's application recommendation tables were not modeled.

The AI sales agentBuilds the axle 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.

8 scenarios in 4 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
Dozens of axle versions with their own dataOnly with workarounds
Each version has its own load rating, brake, exciter-ring teeth, bolt patterns and rims, so the lists multiply across product and compatibility rules.		Every version is a row of the model and is checked together with the rest of the order.
Wheel bolt and rim lists per versionOnly with care
Which bolt patterns and rims fit depends on the version, so an allowed value for one axle is an error for another.		The lists for the selected version are looked up on every call and the mismatch is explained in plain words.
Figures typed in by the rep must match the catalogueOnly with workarounds
A rating, brake size or tooth count quoted by hand is rarely compared with the product data.		Each stated figure is compared with the listed one 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 axle ratings are for speeds up to 105 km/h; the quote has 106 km/h.
2The wheel bolt pattern on the quote is not listed for this axle version.
3The rim size on the quote is not listed for this axle version.
4The quote has an axle load of 10.5 t, but this axle version is rated 10 t.
5The wheel configuration on the quote (single or twin wheels) does not match this axle version.
6The quote has an axle load of 12.5 t, but this axle version is rated 12 t.
7The brake on the quote is not the brake listed for this axle version.
8The quote has an axle load of 12 t, but this axle version is rated 11 t.
9The quote has an axle load of 11.5 t, but this axle version is rated 11 t.
10The quote states an axle load rating of 10 t, but this axle version is rated 9 t.
11The quote states a wheel offset of 0 mm, but this axle version is listed with 120 mm.
12The quote states a wheel offset of 120 mm, but this axle version is listed with 0 mm.
13The quote states a brake diameter of 430 mm, but this axle version has a 377 mm brake.
14The quote states a brake width of 200 mm, but this axle version has a 45 mm brake width.
15The quote states 100 teeth on the ABS exciter ring, but this axle version has 90.
16The quote states 90 teeth on the ABS exciter ring, but this axle version has 100.
17The overview lists 7 t axles, 13 to 14 t axles, friction-steered axles and axles for forced steering only as also available, with no data; a person should confirm the combination with SAF-HOLLAND.
18The quote has an axle load of 11 t, but this axle version is rated 9 t.
19The axle ratings are for speeds up to 105 km/h; the quote has 110 km/h.
20The quote states 90 teeth on the ABS exciter ring, but this axle version has 80.

  

  

    
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. Twin-wheel disc axle: ZI9-19S with a 10-hole bolt pattern

    
The agent's request. Please quote the SAF MODUL axle ZI9-19S for twin wheels with the 10-hole 280/335 bolt pattern on 19.5 inch rims and the SAF SBS 1918 brake. The axle load is 9 t at 80 km/h. The quote states a load rating of 9 t, a 377 x 45 mm brake and 90 exciter-ring teeth. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Wheel bolt pattern not listed for this axle version. The wheel bolt pattern on the quote is not listed for this axle version.
    • 
    

    
2. Twin-wheel disc axle: The agent resubmits after fixing the errors

    
The agent's request. Please quote the SAF MODUL axle ZI9-19S for twin wheels with the 8-hole 220/275 bolt pattern on 19.5 inch rims and the SAF SBS 1918 brake. The axle load is 9 t at 80 km/h. The quote states a load rating of 9 t, a 377 x 45 mm brake and 90 exciter-ring teeth. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Axle data. This axle version is rated 9 t up to 105 km/h with a 377 x 45 mm brake and 90 exciter-ring teeth.
    • 
    

    
3. Heavier load: SI11-22K11 for a 12 t axle load

    
The agent's request. Please quote the SAF MODUL axle SI11-22K11 for single wheels with the 10-hole 280/335 bolt pattern on 22.5 inch rims and the KNORR SB7 (SK7) brake. The axle load is 12 t at 80 km/h. The quote states a 430 x 45 mm brake and 100 exciter-ring teeth. It states a wheel offset of 0 mm. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Axle load over the axle version rating. The quote has an axle load of 12 t, but this axle version is rated 11 t.
    • 
    

    
4. Heavier load: The agent resubmits after fixing the errors

    
The agent's request. Please quote the SAF MODUL axle SI12-22K10 for single wheels with the 10-hole 280/335 bolt pattern on 22.5 inch rims and the KNORR SB7 (SN7) brake. The axle load is 12 t at 80 km/h. The quote states a load rating of 12 t, a 430 x 45 mm brake and 100 exciter-ring teeth. It states a wheel offset of 0 mm. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Axle data. This axle version is rated 12 t up to 105 km/h with a 430 x 45 mm brake and 100 exciter-ring teeth.
    • 
    

    
5. Brake figures on the quote: B(I)9-19S quoted with a 430 mm brake

    
The agent's request. Please quote the SAF MODUL axle B(I)9-19S for single wheels with the 10-hole 280/335 bolt pattern on 22.5 inch rims and the SAF SBS 1918 brake. The axle load is 9 t at 80 km/h. The quote states a load rating of 9 t, a 430 x 45 mm brake and 90 exciter-ring teeth. It states a wheel offset of 120 mm. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Stated brake diameter does not match. The quote states a brake diameter of 430 mm, but this axle version has a 377 mm brake.
    • 
    

    
6. Brake figures on the quote: The agent resubmits after fixing the errors

    
The agent's request. Please quote the SAF MODUL axle B(I)9-19S for single wheels with the 10-hole 280/335 bolt pattern on 22.5 inch rims and the SAF SBS 1918 brake. The axle load is 9 t at 80 km/h. The quote states a load rating of 9 t, a 377 x 45 mm brake and 90 exciter-ring teeth. It states a wheel offset of 120 mm. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Axle data. This axle version is rated 9 t up to 105 km/h with a 377 x 45 mm brake and 90 exciter-ring teeth.
    • 
    

    
7. Road speed: B(I)9-19K at 110 km/h

    
The agent's request. Please quote the SAF MODUL axle B(I)9-19K for single wheels with the 10-hole 280/335 bolt pattern on 22.5 inch rims and the KNORR SB6 (ST6) brake. The axle load is 9 t at 110 km/h. The quote states a load rating of 9 t, a 377 x 45 mm brake and 90 exciter-ring teeth. It states a wheel offset of 120 mm. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Speed over 105 km/h. The axle ratings are for speeds up to 105 km/h; the quote has 110 km/h.
    • 
    

    
8. Road speed: The agent resubmits after fixing the errors

    
The agent's request. Please quote the SAF MODUL axle B(I)9-19K for single wheels with the 10-hole 280/335 bolt pattern on 22.5 inch rims and the KNORR SB6 (ST6) brake. The axle load is 9 t at 100 km/h. The quote states a load rating of 9 t, a 377 x 45 mm brake and 90 exciter-ring teeth. It states a wheel offset of 120 mm. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Axle data. This axle version is rated 9 t up to 105 km/h with a 377 x 45 mm brake and 90 exciter-ring teeth.
    • 
    

  

  

    
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 SAF MODUL rigid trailer axle: the axle version, wheel configuration, wheel bolt pattern and rim, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the manufacturer's published product overview and returns a verdict, every reason and the figures it looked up.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Please quote the SAF MODUL axle B(I)9-19S for single wheels with the 10-hole 280/335 bolt pattern on 22.5 inch rims and the SAF SBS 1918 brake. The axle load is 9 t at 80 km/h. The rest of the request is on screen.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with one finding, all in one answer. The quote states a brake diameter of 430 mm, but this axle version has a 377 mm brake.
    6. 
      
  6. The validator returned one blocking finding 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 figures typed in by the rep must match the catalogue, a rules-based CPQ can do this only with workarounds.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the brake size on the quote to 377 x 45.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. This time the validator clears it.
    12. 
      
  12. The earlier finding is cleared.
    13. 
      
  13. One problem 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.