Predictika · Geosynthetic clay liner quotes

An AI sales agent's clay liner order quote, checked before it goes out

An AI sales agent prepares a quote for a geosynthetic clay liner order: the BENTOMAT product, the application, the slope, the rolls ordered against the liner area, the roll length, the cover soil, and the net price the quote states. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of where each product is used and how the choices fit together, and returns a verdict, every reason and the price it computed.

Scope: One liner order quote: product, application, slope, rolls, roll length, high-head pond, cover soil and the stated net price. See everything this validator covers

This validator models nine BENTOMAT products and four applications, not just the scenarios shown below.

  • Product and application — which products are used for landfill bases, landfill covers, ponds and lagoons, and mine tailings.
  • Slope — the steepest slope each product is used on, from 1.5 to 1 up to 10 to 1.
  • Rolls and coverage — the rolls needed to cover the liner area with a 5 percent allowance for overlaps and waste, and the roll lengths supplied, with long rolls needing sales approval.
  • Cover, ponds and price — calcium-rich cover soil, high-head ponds that call for the CL product, the volume discount tiers, large orders, and the net price stated on the quote compared with the computed one.

Any order of these products that touches these rules is in scope — not only the scenarios pictured here. The product names, constructions, standard roll sizes, slope limits, the CL recommendation for high-head ponds, the calcium-rich cover warning and the roll length guidance follow public CETCO pages; the prices, volume discounts, overlap allowance and sales approvals are modeled from comparable products, and all prices are illustrative.

The AI sales agentBuilds the liner order quote from the conversation with the customer and says it is ready to send.
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
Products that depend on the applicationOnly with care
Each product is used for only some applications, so every rule has to test the pair first.
The product and the application are checked together on every call.
Slope limits that differ by productOnly with care
Nine products have nine different steepest slopes, so each limit needs its own rule and message.
The slope limit is part of the model and the message names the limit and the slope on the quote.
Rolls against the liner areaOnly with workarounds
The rolls needed depend on the roll width of the product and the roll length, plus an allowance for overlaps and waste, so a separate rule must recompute the coverage.
Roll area, allowance and rolls ordered are computed in the same pass as the rest of the quote.
A stated price that must match the computed oneOnly with workarounds
The net price depends on the product price, the area and the volume discount tier, so a separate rule must recompute it and compare it with the stated figure.
The stated price is a field of the request and is compared with the computed price on every call.
Every problem returned in one answerOnly with workarounds
Rules tend to fire as a step is completed, so a rep often fixes one error and meets the next.
All findings come back together, so the agent can fix them in a single pass.

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 slope is steeper than this product is used on; its limit is 30 tenths of a horizontal unit per vertical unit and the quote has 29.
2This product is not used for the selected application.
3The rolls ordered do not cover the liner area with the 5 percent allowance for overlaps and waste.
4The order must include at least one roll.
5Rolls longer than 150 feet are discouraged for handling and need sales approval.
6A roll length of 260 feet is not supplied; rolls up to 250 feet are available.
7For high head ponds and lagoons CETCO recommends the CL product, so this selection needs technical approval.
8Calcium rich cover material is not recommended over bentonite, so technical approval is needed.
9Orders of 500,000 square feet or more need sales manager pricing approval.
10The quote states a net price of 6,371,999 cents; the modeled price list and volume discount give a different amount.

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 landfill base: A mining product for a landfill base, a steep slope, too few rolls and a wrong price

The agent's request. Please prepare a quote for BENTOMAT STM for a landfill base, on a 2 to 1 slope, with 40 rolls of 150 feet, over a liner area of 100,000 square feet. The quote states a net price of $50,000. It is ready to send.

Verdict: Blocked.

  • Slope too steep for the product. The slope is steeper than this product is used on; its limit is 30 tenths of a horizontal unit per vertical unit and the quote has 20.
  • Product not used for this application. This product is not used for the selected application.
  • Rolls do not cover the area. The rolls ordered do not cover the liner area with the 5 percent allowance for overlaps and waste.
  • Stated net price does not match. The quote states a net price of 5,000,000 cents; the modeled price list and volume discount give a different amount.

2. A landfill base: The agent resubmits after fixing the errors

The agent's request. Please prepare a quote for BENTOMAT DN for a landfill base, on a 2 to 1 slope, with 40 rolls of 150 feet, over a liner area of 100,000 square feet. The quote states a net price of $62,640. It is ready to send.

Verdict: Blocked.

  • Rolls do not cover the area. The rolls ordered do not cover the liner area with the 5 percent allowance for overlaps and waste.

3. A landfill base: The agent resubmits after fixing the errors

The agent's request. Please prepare a quote for BENTOMAT DN for a landfill base, on a 2 to 1 slope, with 49 rolls of 150 feet, over a liner area of 100,000 square feet. The quote states a net price of $73,664.64. It is ready to send.

Verdict: Allowed.

  • Quote summary. Net price of 7,366,464,000 cents after a volume discount of 4 percent (modeled illustrative price, the figure is cents multiplied by 1,000).

4. A pond: A landfill product for a pond on a steep slope with a wrong price

The agent's request. Please prepare a quote for BENTOMAT DN for a pond, on a 1 to 1 slope, with 49 rolls of 150 feet, over a liner area of 100,000 square feet. The quote states a net price of $60,000. It is ready to send.

Verdict: Blocked.

  • Slope too steep for the product. The slope is steeper than this product is used on; its limit is 15 tenths of a horizontal unit per vertical unit and the quote has 10.
  • Product not used for this application. This product is not used for the selected application.
  • Stated net price does not match. The quote states a net price of 6,000,000 cents; the modeled price list and volume discount give a different amount.

5. A pond: The agent resubmits after fixing the errors

The agent's request. Please prepare a quote for BENTOMAT CL for a pond, on a 3 to 1 slope, with 47 rolls of 150 feet, for a high-head pond, over a liner area of 100,000 square feet. The quote states a net price of $77,155.20. It is ready to send.

Verdict: Allowed.

  • Quote summary. Net price of 7,715,520,000 cents after a volume discount of 4 percent (modeled illustrative price, the figure is cents multiplied by 1,000).

6. A landfill cover: A flat-slope product on a 3 to 1 slope with long rolls and calcium-rich cover soil

The agent's request. Please prepare a quote for BENTOMAT 600CL for a landfill cover, on a 3 to 1 slope, with 35 rolls of 200 feet, with calcium-rich cover soil, over a liner area of 100,000 square feet. The quote states a net price of $70,560. It is ready to send.

Verdict: Blocked.

  • Slope too steep for the product. The slope is steeper than this product is used on; its limit is 100 tenths of a horizontal unit per vertical unit and the quote has 30.
  • Long rolls. Rolls longer than 150 feet are discouraged for handling and need sales approval.
  • Calcium rich cover. Calcium rich cover material is not recommended over bentonite, so technical approval is needed.

7. A landfill cover: The agent resubmits after fixing the errors

The agent's request. Please prepare a quote for BENTOMAT 600CL for a landfill cover, on a 50 to 1 slope, with 47 rolls of 150 feet, over a liner area of 100,000 square feet. The quote states a net price of $71,064. It is ready to send.

Verdict: Allowed.

  • Quote summary. Net price of 7,106,400,000 cents after a volume discount of 4 percent (modeled illustrative price, the figure is cents multiplied by 1,000).

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 a geosynthetic clay liner order: the BENTOMAT product, the application, the slope, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of where each product is used and how the choices fit together, and returns a verdict, every reason and the price it computed.
  2. I will start with the first request by the agent.
  3. The agent says. Please prepare a quote for BENTOMAT STM for a landfill base, on a 2 to 1 slope, with 40 rolls of 150 feet. The quote states a net price of $50,000. The rest of the request is on screen.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with four findings, all in one answer. The slope is steeper than this product is used on; its limit is 30 tenths of a horizontal unit per vertical unit and the quote has 20. This product is not used for the selected application. The rolls ordered do not cover the liner area with the 5 percent allowance for overlaps and waste. The other one is on screen.
  6. The validator returned four 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. What this shows: for a stated price that must match the computed one, a rules-based CPQ can do this only with workarounds.
  8. Now the agent resubmits.
  9. The corrected request. It changes the product to BENTOMAT DN and the net price stated on the quote to $62,640.
  10. It calls the validator again.
  11. Still blocked, with one finding, all in one answer. The rolls ordered do not cover the liner area with the 5 percent allowance for overlaps and waste.
  12. Three findings cleared. Still blocking: rolls do not cover the area.
  13. The agent resubmits once more.
  14. The revised request. It changes the rolls to 49 and the net price stated on the quote to $73,664.64.
  15. It calls the validator once more.
  16. This time the validator clears it.
  17. The earlier finding is cleared.
  18. Four problems caught in one call, fixed in two passes, and a clean $73,664.64 quote. That is the value of Predictika's validator: catching mistakes before they reach the customer. Now you can try the other scenarios yourself.