Predictika · truck model, mast and battery package, dealer programs, rated capacity, attachments and service years

An AI sales agent's lift truck quote, checked before it goes to the dealer

An AI sales agent prepares a quote for lift trucks: a truck model, a mast and battery package, a dealer program, a number of trucks, a rated capacity in pounds, a service term, optional attachments and any extra discount, and says it is ready to send. Before it goes out, the agent sends it to Predictika's validator, which checks it against a declarative model of the truck, package and dealer program rules, prices it, and reports every problem it finds in one pass.

Scope: Quotes for four lift truck models with three mast and battery packages and three dealer programs, checked against illustrative capacity, option, term and order-size rules. Prices and limits are estimates in US dollars, not a manufacturer quote. See everything this validator covers

This validator checks any quote built from these truck models, packages and dealer programs, not just the scenarios shown below.

  • Trucks and mast packages — a pallet jack, an electric lift truck, an internal combustion lift truck and a heavy internal combustion lift truck, with standard lead-acid, high visibility lithium-ion and heavy duty lithium-ion packages, including the package that cannot support the heavy duty configuration.
  • Rated capacity — a rated capacity in pounds checked against the truck limit and the package limit, with a capacity and load center review above 12,000 pounds.
  • Options and dealer programs — the fork positioner attachment and telematics service by truck model, and standard dealer purchase, fleet lease and national fleet account programs with their truck minimums and discounts.
  • Term and order size — service terms from 1 to 5 years, a finance review above 3 years, a production slot review above 25 trucks, an approval band above 10 percent total discount, and a deal desk review above USD 5,000,000.
  • The stated total — a check that the net total the agent states matches the total the validator computes.

Any quote for these truck models, packages and dealer programs is in scope, not only the scenarios pictured here. Not checked: other products such as automation or hydrogen fuel cell systems, real list prices, load chart or aisle width engineering, regional safety and emissions rules, or tax and multi-currency quoting.

The AI sales agentBuilds the lift truck quote from the conversation and says it is ready to send.
Predictika validatorChecks every rule at once and returns the verdict, each finding, and the computed figures.

4 scenarios in 2 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 a rules-based CPQ gets this wrong

Click to expand

Our assessment of what a typical rules-based CPQ (product rules, price rules and validation rules, as in Salesforce CPQ or Conga) does with the same cases. It is a judgment about effort and reliability, not a claim that nothing can be built.

What the validator caughtA rules-based CPQPredictika
Rated capacity against both the truck and the packageOnly with care
Two separate limits on two different products, each maintained by hand, that must agree on every combination.
Both limits are checked together against the rated capacity on every call.
A package that cannot support a heavy duty truckOnly with care
A compatibility matrix between trucks and packages that grows with every new product.
The incompatibility is one check on the chosen truck and package.
A dealer program with a truck minimumOnly with workarounds
The minimum, the program discount and the volume discount interact, so changing the truck count changes the price and the allowed program at once.
Quantity, program, discount and price are computed together.
Options that exist only on some truck modelsEasy
A product rule on model.
The same, from the catalog.
A stated total that must match the computed priceOnly with care
The total is typed or generated elsewhere, so a mismatch is caught only if someone writes a rule that recomputes the price.
The price is computed in the same model, and the stated total is compared with it.
Every problem returned in one answerOnly with workarounds
Rules tend to fire as the quote is saved, 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.

1A quote is limited to 1 to 100 trucks.
2A dealer program has a minimum number of trucks, such as 5 for the fleet lease program.
3The rated capacity must be within the range of the truck model.
4The rated capacity must be within the limit of the mast and battery package.
5A heavy duty truck cannot use a package that does not support the heavy duty configuration.
6The fork positioner attachment is not available on some truck models.
7The telematics service is not available on some truck models.
8A contract must be 1 to 5 years.
9A contract longer than 3 years needs finance approval of the price lock.
10A rated capacity above 12,000 pounds needs a capacity and load center review.
11More than 25 trucks need a production slot review.
12A total discount above 10 percent needs sales director approval.
13An order value above USD 5,000,000 needs a deal desk review.
14The net total the agent states must match the total the validator computes.

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. A fleet program with too few trucks: Three trucks on the fleet lease program

The agent's request. Please check this quote for Ridgeway Material Handling, a dealer: three internal combustion lift trucks of 8000 lb with the high visibility lithium-ion mast and battery package, a rated capacity of 7,000 lb, on the fleet lease program with a two-year service term, at a net total of USD 211,641. It is ready to send.

Verdict: Blocked.

  • Dealer program minimum. 3 trucks are below the 5 trucks minimum of the Fleet lease program.
  • Price build-up. Estimated list price: USD 211,641 net for 3 trucks over 2 years (USD 73,000 per truck, USD 1,890 per year of service, USD 222,780 before discount, 5 percent total discount).

2. A fleet program with too few trucks: Five trucks on the fleet lease program

The agent's request. Ridgeway Material Handling will take five trucks instead, so the quote is five internal combustion lift trucks of 8000 lb with the high visibility lithium-ion mast and battery package, a rated capacity of 7,000 lb, on the fleet lease program with a two-year service term, at a net total of USD 345,309. It is ready to send.

Verdict: Allowed.

  • Price build-up. Estimated list price: USD 345,309 net for 5 trucks over 2 years (USD 73,000 per truck, USD 3,150 per year of service, USD 371,300 before discount, 7 percent total discount).

3. A stated total that does not match: Three trucks with a net total that is too low

The agent's request. Please check this quote for Cascade Forklift Sales, a dealer: three internal combustion lift trucks of 8000 lb with the high visibility lithium-ion mast and battery package, a rated capacity of 7,000 lb, on the standard dealer purchase with a two-year service term, at a net total of USD 200,502. It is ready to send.

Verdict: Blocked.

  • Stated total does not match. The quoted net total of USD 200,502 does not match the USD 222,780 the validator computed.
  • Price build-up. Estimated list price: USD 222,780 net for 3 trucks over 2 years (USD 73,000 per truck, USD 1,890 per year of service, USD 222,780 before discount, 0 percent total discount).

4. A stated total that does not match: The same trucks with the net total corrected

The agent's request. I recomputed the Cascade Forklift Sales quote: the same three internal combustion lift trucks of 8000 lb with the high visibility lithium-ion package, on the standard dealer purchase with a two-year service term, now at a net total of USD 222,780. It is ready to send.

Verdict: Allowed.

  • Price build-up. Estimated list price: USD 222,780 net for 3 trucks over 2 years (USD 73,000 per truck, USD 1,890 per year of service, USD 222,780 before discount, 0 percent total discount).

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 quote for lift trucks: a truck model, a mast and battery package, a dealer program, and more. Before it goes out, the agent sends it to Predictika's validator, which checks it against a declarative model of the truck, package and dealer program rules, prices it, and reports every problem it finds in one pass.
  2. I will start with the first request by the agent.
  3. The agent says. Please check this quote for Ridgeway Material Handling, a dealer: three internal combustion lift trucks of 8000 lb. It is ready to send. The rest of the request is on screen.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with one finding, all in one answer. 3 trucks are below the 5 trucks minimum of the fleet lease program.
  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. What this shows: for a dealer program with a truck minimum, a rules-based CPQ can do this only with workarounds.
  8. Now the agent resubmits.
  9. The corrected request. It changes the trucks to 5 and the net total stated by the agent to USD 345,309.
  10. It calls the validator again.
  11. This time the validator clears it.
  12. The earlier finding is cleared, and the validator's total, USD 345,309, matches the quote.
  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.