Predictika · Commercial vehicle fleet quotes

An AI sales agent's van fleet quote, checked before it goes out

An AI sales agent prepares a fleet quote for panel vans, with up to three lines of body, powertrain and trim. Before it goes out, the agent sends it to Predictika, which checks every line against the published price list, adds up the listed prices and returns a verdict, every reason and the figures it computed.

Scope: Renault Master panel van fleet quotes (Blue dCi diesel and E-Tech electric; Advance and Extra trim; five bodies) in the UK launch price list. See everything this validator covers

This validator models fleet quotes for the Renault Master panel van, not just the scenarios shown below.

  • Listed versions — each line's body (MM35, MM40, LM35, LM40, LH35), powertrain (Blue dCi 130, 150, 150 automatic, 150 Heavy Duty, dCi 170 automatic, or E-Tech electric) and trim must be one of the 22 versions on the published list; anything else is blocked.
  • Prices and totals — each line is priced from the list, the lines are added up, and the total the agent states must equal the sum.
  • Plug-in Van Grant — the listed electric prices include the grant, so a quote with an electric line goes to a person to confirm eligibility.

Any Master panel van fleet quote that touches these rules is in scope — not only the scenarios pictured here. Not covered: chassis cab, platform and other bodies, options and paint, fleet discounts and leasing (no public rules), and other markets. Prices are on-the-road prices in pounds as listed at launch, not current prices.

The AI sales agentBuilds the fleet quote 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 body, powertrain and trim that exist only in some combinationsOnly with care
A product catalogue can list the 22 versions, but gaps such as no Extra trim on electric vans, no Heavy Duty in Extra, or the 170 powertrain only as an automatic need many exclusion rules that must be kept in step with the price list.
Each line is looked up against the published list on every call and any combination not on it is blocked.
A stated total that must equal the sum of listed prices across linesOnly with care
Price rules can compute a total, but a total typed in by an agent is a free-entry field and comparing it with the computed sum needs a separate validation rule.
The stated total travels with the quote and is compared with the sum of listed prices on every call.
Every problem returned in one answerOnly with workarounds
Rules tend to fire as the quote is saved or a step is completed, so a rep often fixes one line and then meets the next.
All findings, for every line, 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 listed electric prices include the Plug-in Van Grant; a person should confirm the customer is eligible for it.
2Line N (body, powertrain, trim) is not a version on the published price list.
3The quote states a total of an amount; the listed prices give an amount.
4The quote has no vans.
5A line has a negative quantity.

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. Heavy Duty and long high roof diesel fleet: Three-line diesel fleet with a Heavy Duty van in a trim that is not listed

The agent's request. Please quote a fleet of 6 Renault Master LM35 panel vans with the Blue dCi 150 Heavy Duty in Extra trim; 4 Renault Master MM35 panel vans with the Blue dCi 130 in Advance trim; 2 Renault Master LH35 panel vans with the Blue dCi 150 in Advance trim. The quote states a total of £523,080. It is ready to send.

Verdict: Blocked.

  • Line 1 is not a listed version. Line 1 (LM35, Blue dCi 150 Heavy Duty, Extra trim) is not a version on the published price list.
  • Stated total does not match the listed prices. The quote states a total of £523,080; the listed prices give £253,740.

2. Heavy Duty and long high roof diesel fleet: The agent resubmits after fixing the errors

The agent's request. Please quote a fleet of 6 Renault Master LM35 panel vans with the Blue dCi 150 Heavy Duty in Advance trim; 4 Renault Master MM35 panel vans with the Blue dCi 130 in Advance trim; 2 Renault Master LH35 panel vans with the Blue dCi 150 in Advance trim. The quote states a total of £512,280. It is ready to send.

Verdict: Allowed.

  • Fleet summary. 12 vans in total; total £512,280 (on-the-road prices as listed).

3. Diesel and electric fleet: Diesel and electric fleet with an electric van in a body that is not listed

The agent's request. Please quote a fleet of 5 Renault Master LM35 panel vans with the Blue dCi 150 in Advance trim; 3 Renault Master LH35 panel vans with the E-Tech electric in Advance trim. The quote states a total of £358,415. It is ready to send.

Verdict: Blocked.

  • Line 2 is not a listed version. Line 2 (LH35, E-Tech electric, Advance trim) is not a version on the published price list.
  • Stated total does not match the listed prices. The quote states a total of £358,415; the listed prices give £215,450.
  • Plug-in Van Grant eligibility to confirm. The listed electric prices include the Plug-in Van Grant; a person should confirm the customer is eligible for it.

4. Diesel and electric fleet: The agent resubmits after fixing the errors

The agent's request. Please quote a fleet of 5 Renault Master LM35 panel vans with the Blue dCi 150 in Advance trim; 3 Renault Master LM40 panel vans with the E-Tech electric in Advance trim. The quote states a total of £369,215. It is ready to send.

Verdict: Needs approval.

  • Plug-in Van Grant eligibility to confirm. The listed electric prices include the Plug-in Van Grant; a person should confirm the customer is eligible for it.
  • Fleet summary. 8 vans in total; total £369,215 (on-the-road prices as listed).

5. Diesel and electric fleet: The agent resubmits after fixing the errors

The agent's request. Please quote a fleet of 5 Renault Master LM35 panel vans with the Blue dCi 150 in Advance trim; 3 Renault Master LM40 panel vans with the E-Tech electric in Advance trim. The quote states a total of £369,215. It is ready to send.

Verdict: Allowed.

  • Fleet summary. 8 vans in total; total £369,215 (on-the-road prices as listed).

6. Stated total: Three-line fleet whose stated total is below the listed prices

The agent's request. Please quote a fleet of 5 Renault Master LM35 panel vans with the Blue dCi 150 in Advance trim; 3 Renault Master MM35 panel vans with the Blue dCi 130 in Extra trim; 2 Renault Master LH35 panel vans with the Blue dCi 150 automatic in Advance trim. The quote states a total of £430,000. It is ready to send.

Verdict: Blocked.

  • Stated total does not match the listed prices. The quote states a total of £430,000; the listed prices give £438,100.

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

The agent's request. Please quote a fleet of 5 Renault Master LM35 panel vans with the Blue dCi 150 in Advance trim; 3 Renault Master MM35 panel vans with the Blue dCi 130 in Extra trim; 2 Renault Master LH35 panel vans with the Blue dCi 150 automatic in Advance trim. The quote states a total of £438,100. It is ready to send.

Verdict: Allowed.

  • Fleet summary. 10 vans in total; total £438,100 (on-the-road prices as listed).

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 fleet quote for panel vans, with up to three lines of body, powertrain and trim. Before it goes out, the agent sends it to Predictika, which checks every line against the published price list, adds up the listed prices and returns a verdict, every reason and the figures it computed.
  2. I will start with the first request by the agent.
  3. The agent says. Please quote a fleet of 6 Renault Master LM35 panel vans. The quote states a total of £523,080. The rest of the request is on screen.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with two findings, all in one answer. Line 1 (LM35, Blue dCi 150 Heavy Duty, Extra trim) is not a version on the published price list. The quote states a total of £523,080; the listed prices give £253,740.
  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 and against the stated total.
  7. What this shows: for a stated total that must equal the sum of listed prices across lines, a rules-based CPQ is error-prone for this.
  8. Now the agent resubmits.
  9. The corrected request. It changes the line 1 trim to advance and the stated total to 512,280 GBP.
  10. It calls the validator again.
  11. This time the validator clears it.
  12. The validator also returns the line-item quote. It starts with Renault Master LM35 panel van and Renault Master MM35 panel van; the other line is on screen.
  13. Both earlier findings are cleared, and the validator's total, £512,280, matches the quote.
  14. Two problems 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.