Predictika · Motorcoach configurations

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

An AI sales agent prepares a configuration for a J4500 or J3500 touring coach: the engine, the number of passenger seats, passive rear steering, and the axle, horsepower and alternator figures it orders. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published MCI J-Series brochure and returns a verdict, every reason and the listed values it compared against.

Scope: MCI J4500 and J3500 coaches: engine for the model, seating capacity, passive rear steering, and stated horsepower, axle ratings and alternators. See everything this validator covers

This validator models availability and figures printed in the MCI J-Series brochure (updated May 2025) and the MCI J-Series specs page, not just the scenarios shown below.

  • Engine — the Cummins X12 (410 hp standard, 455 hp optional) is listed for the J4500 and the Cummins L9 (350 hp) for the J3500; an engine from the other model is blocked.
  • Seating — up to 60 passengers on the J4500 and up to 44 on the J3500.
  • Rear steering — the passive rear steering system is listed for the J4500 and is not listed for the J3500.
  • Stated figures — the horsepower, the front axle rating (J4500 17,000 lb; J3500 14,500 lb), the drive axle rating (J4500 23,000 lb; J3500 27,500 lb), the tag axle rating (J4500 16,500 lb; none listed for the J3500) and the alternators (J4500 two 250 A; J3500 two 180 A) are compared with what the order states.

Any configuration of these two coaches that touches these rules is in scope — not only the scenarios pictured here. Not covered: prices (MCI publishes no price list for its coaches, so there is no price build-up or line items); the J4500 CHARGE and the other MCI coaches; the Base, Preferred and High specification columns, which the brochure describes as typically included or not and not as rules; options that are listed the same way for both models (for example the 360-degree camera, seat styles, lighting, audio and the application groups); and the turning-radius figures, which the public specs table does not align reliably. The brochure says specifications are subject to change without notice.

The AI sales agentBuilds the coach 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.

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
Engine and axle choices that exist for one model onlyOnly with care
The J4500 and J3500 share a platform but have different engines, axle ratings, alternators and rear steering, so each choice needs a rule against the model, and a pick-list copied from the other model has to be caught.
The model decides which engine and ratings are listed, and every choice is checked against it on every call.
A stated rating checked against the listed oneOnly with workarounds
The agent states a horsepower and axle and alternator figures, and each has to be compared with a value that depends on the model and engine; a mismatch has to stop the order.
The stated figures are fields in the order, and the validator blocks when one differs from the brochure.
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 order; approval findings need a person to sign off; everything else is computed.

1The engine Cummins L9 350 hp is not listed for the J4500; the brochure lists the Cummins X12 (410 hp standard, 455 hp optional) for the J4500 and the Cummins L9 (350 hp) for the J3500.
2The engine Cummins X12 410 hp is not listed for the J3500; the brochure lists the Cummins X12 (410 hp standard, 455 hp optional) for the J4500 and the Cummins L9 (350 hp) for the J3500.
3The engine Cummins X12 455 hp is not listed for the J3500; the brochure lists the Cummins X12 (410 hp standard, 455 hp optional) for the J4500 and the Cummins L9 (350 hp) for the J3500.
4The order has 61 passenger seats; the brochure lists seating for up to 60 passengers on this model.
5The order has 45 passenger seats; the brochure lists seating for up to 44 passengers on this model.
6The passive rear steering system is listed for the J4500 only; it is not listed (N/A) for the J3500.
7The order states 455 hp; the brochure lists 410 hp for this engine.
8The order states a front axle rating of 14,500 lb; the brochure lists 17,000 lb for this model.
9The order states a front axle rating of 17,000 lb; the brochure lists 14,500 lb for this model.
10The order states a drive axle rating of 27,500 lb; the brochure lists 23,000 lb for this model.
11The order states a drive axle rating of 23,000 lb; the brochure lists 27,500 lb for this model.
12The order states a tag axle rating of 16,500 lb; the brochure lists a 16,500 lb tag axle for the J4500 only and none for the J3500.
13The order states a tag axle rating of 14,500 lb; the brochure lists a 16,500 lb tag axle for the J4500 only and none for the J3500.
14The order states two alternators of 180 A each; the brochure lists two alternators of 250 A each for this model.
15The order states two alternators of 250 A each; the brochure lists two alternators of 180 A each for this model.
16The order has 50 passenger seats; the brochure lists seating for up to 44 passengers on this model.

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. Touring operator J4500: A J4500 for a touring operator

The agent's request. Please configure a J4500 coach with the Cummins L9 350 hp and 62 passenger seats. The order states 350 hp, a front axle rating of 17,000 lb and a drive axle rating of 23,000 lb. It is ready to send.

Verdict: Blocked.

  • Engine not listed for this model. The engine Cummins L9 350 hp is not listed for the J4500; the brochure lists the Cummins X12 (410 hp standard, 455 hp optional) for the J4500 and the Cummins L9 (350 hp) for the J3500.
  • More passengers than the model seats. The order has 62 passenger seats; the brochure lists seating for up to 60 passengers on this model.

2. Touring operator J4500: The agent resubmits after fixing the errors

The agent's request. Please configure a J4500 coach with the Cummins X12 455 hp and 60 passenger seats. The order states 455 hp, a front axle rating of 17,000 lb and a drive axle rating of 23,000 lb. It is ready to send.

Verdict: Allowed.

  • Listed values for this configuration. Listed for this configuration: 455 hp, seating up to 60 passengers, front axle 17,000 lb, drive axle 23,000 lb, two 250 A alternators.

3. Boutique charter J3500: A J3500 for a boutique charter company

The agent's request. Please configure a J3500 coach with the Cummins L9 350 hp and 44 passenger seats, including the passive rear steering system. The order states a front axle rating of 17,000 lb, a drive axle rating of 27,500 lb and a tag axle rating of 16,500 lb. It is ready to send.

Verdict: Blocked.

  • Passive rear steering is listed for the J4500 only. The passive rear steering system is listed for the J4500 only; it is not listed (N/A) for the J3500.
  • Stated front axle rating differs from the brochure. The order states a front axle rating of 17,000 lb; the brochure lists 14,500 lb for this model.
  • Stated tag axle rating differs from the brochure. The order states a tag axle rating of 16,500 lb; the brochure lists a 16,500 lb tag axle for the J4500 only and none for the J3500.

4. Boutique charter J3500: The agent resubmits after fixing the errors

The agent's request. Please configure a J3500 coach with the Cummins L9 350 hp and 44 passenger seats. The order states a front axle rating of 14,500 lb and a drive axle rating of 27,500 lb. It is ready to send.

Verdict: Allowed.

  • Listed values for this configuration. Listed for this configuration: 350 hp, seating up to 44 passengers, front axle 14,500 lb, drive axle 27,500 lb, two 180 A alternators.

5. Airport shuttle J3500: A J3500 for an airport shuttle contract

The agent's request. Please configure a J3500 coach with the Cummins X12 410 hp and 40 passenger seats. The order states 410 hp, a drive axle rating of 23,000 lb and two 250 A alternators. It is ready to send.

Verdict: Blocked.

  • Engine not listed for this model. The engine Cummins X12 410 hp is not listed for the J3500; the brochure lists the Cummins X12 (410 hp standard, 455 hp optional) for the J4500 and the Cummins L9 (350 hp) for the J3500.
  • Stated drive axle rating differs from the brochure. The order states a drive axle rating of 23,000 lb; the brochure lists 27,500 lb for this model.
  • Stated alternators differ from the brochure. The order states two alternators of 250 A each; the brochure lists two alternators of 180 A each for this model.

6. Airport shuttle J3500: The agent resubmits after fixing the errors

The agent's request. Please configure a J3500 coach with the Cummins L9 350 hp and 40 passenger seats. The order states 350 hp, a drive axle rating of 27,500 lb and two 180 A alternators. It is ready to send.

Verdict: Allowed.

  • Listed values for this configuration. Listed for this configuration: 350 hp, seating up to 44 passengers, front axle 14,500 lb, drive axle 27,500 lb, two 180 A alternators.

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 J4500 or J3500 touring coach: the engine, the number of passenger seats, passive rear steering, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published MCI J-Series brochure and returns a verdict, every reason and the listed values it compared against.
  2. I will start with the first request by the agent.
  3. The agent says. Please configure a J3500 coach with the Cummins L9 350 hp and 44 passenger seats, including the passive rear steering system. The order states a front axle rating of 17,000 lb, a drive axle rating of 27,500 lb and a tag axle rating of 16,500 lb. The rest of the request is on screen.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with three findings, all in one answer. The passive rear steering system is listed for the J4500 only; it is not listed (N/A) for the J3500. The order states a front axle rating of 17,000 lb; the brochure lists 14,500 lb for this model. The order states a tag axle rating of 16,500 lb; the brochure lists a 16,500 lb tag axle for the J4500 only and none for the J3500.
  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 order are checked against each other.
  7. What this shows: for a stated rating checked against the listed one, a rules-based CPQ can do this only with workarounds.
  8. Now the agent resubmits.
  9. The corrected request. It changes the stated front axle rating to 14,500 lb. It removes the passive rear steering and stated tag axle rating.
  10. It calls the validator again.
  11. This time the validator clears it.
  12. All three earlier findings are cleared.
  13. Three problems caught in one call, fixed in one pass, and a clean order. That is the value of Predictika's validator: catching mistakes before they reach the customer. Now you can try the other scenarios yourself.