Predictika · Sheet paper order quotes

An AI sales agent's sheet paper quote, checked before it goes out

An AI sales agent prepares a quote for an order of sheet paper: a brand (McCoy, Opus, Somerset, Flo or Magno), a finish, text or cover grade, a basis weight, a sheet size, a grain direction, a number of thousand sheets, delivered or will-call shipping and a discount. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of sheet paper orders and returns a verdict, every reason and the total it computed.

Scope: Sheet paper orders for five Sappi brand names (McCoy, Opus, Somerset, Flo, Magno): finish, basis weight, sheet size, grain, order weight, discount and the stated total. See everything this validator covers

This validator models sheet paper order quotes, not just the scenarios shown below.

  • Brand, finish, weight and size — which finishes, basis weights and sheet sizes each brand is offered in, and long grain only on Flo.
  • Order weight — the weight computed from the sheets, basis weight and sheet size, with a 2,000 lb minimum and a 44,000 lb truckload limit.
  • Discount and stated total — up to 5 percent without approval, 6 to 12 percent sent to a manager, above 12 percent blocked, and the stated total compared with the total computed from the modeled prices.

Any sheet paper order that touches these rules is in scope — not only the scenarios pictured here. Not covered: reels, digital papers, packaging and other regions. Public versus modeled: the brand names and some finishes come from Sappi's public pages; the finish, weight, size and grain matrix, the order limits, the discount thresholds and every price are modeled by Predictika from comparable products, are illustrative and are not published by Sappi.

The AI sales agentBuilds the sheet paper 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.

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
A finish, weight or size that depends on the brandOnly with care
Each brand has its own finishes, weight range and sheet sizes, so the rules grow into a matrix that has to be kept in step with the catalog.		Brand, finish, weight and size are fields of one order and are checked together on every call.
An order weight computed from sheets, basis weight and sheet sizeOnly with workarounds
The weight is derived from several fields and drives the minimum and truckload rules, so the formulas interact with those rules.		The order weight is computed in the model and checked against both limits on every call.
Discount tiers that block, approve or passOnly with care
Two thresholds with different outcomes need separate rules that must not overlap.		Blocks and approvals come back together; an approval-only discount is not blocked.
A stated total that must match the computed totalOnly with workarounds
The total is built from weight, rate, discount and freight, so a separate rule is needed to recompute it and compare it with the stated figure.		The stated total is a field of the request and is compared with the computed total 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 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 basis weight of 69 lb is outside the range of 70 to 120 lb for this brand.
2A basis weight of 101 lb is outside the range of 60 to 100 lb for this brand.
3The finish chosen is not offered in the brand chosen.
4The sheet size chosen is not offered in the brand chosen.
5Flo is offered in long grain only.
6Short grain is made to order and the mill must confirm availability.
7The order weighs 1,920 lb; the minimum is 2,000 lb.
8The order weighs 44,160 lb; one truckload is limited to 44,000 lb.
9A discount of 6 percent is above 5 percent and needs sales management approval.
10A discount of 12 percent is above 5 percent and needs sales management approval.
11A discount of 13 percent is above the 12 percent maximum.
12The quote states a total of 266,239 cents; the modeled prices give 266,240 cents.
13The quote states a total of 266,340 cents; the modeled prices give 266,240 cents.
14The quote states a total of 1 cents; the modeled prices give 246,272 cents.
15A discount of 8 percent is above 5 percent and needs sales management approval.
16A discount of 10 percent is above 5 percent and needs sales management approval.
17A basis weight of 120 lb is outside the range of 60 to 100 lb for this brand.
18A discount of 20 percent is above the 12 percent maximum.

  

  

    
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. Flo order with spec problems: A Flo order with a satin finish, 28 by 40 inch short-grain sheets at 120 lb and a 20 percent discount

    
The agent's request. Please quote Flo satin text paper, 120 lb, 28 by 40 inch sheets, short grain, 20 thousand sheets, delivered, with a 20 percent discount, for a total of $3,419.61. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Finish not made in this brand. The finish chosen is not offered in the brand chosen.
    • 
      
  • Weight outside the brand range. A basis weight of 120 lb is outside the range of 60 to 100 lb for this brand.
    • 
      
  • Sheet size not offered in this brand. The sheet size chosen is not offered in the brand chosen.
    • 
      
  • Short grain not offered on Flo. Flo is offered in long grain only.
    • 
      
  • Discount above 12 percent. A discount of 20 percent is above the 12 percent maximum.
    • 
    

    
2. Flo order with spec problems: The agent resubmits after fixing the errors

    
The agent's request. Please quote Flo gloss text paper, 100 lb, 25 by 38 inch sheets, long grain, 20 thousand sheets, delivered, with a 5 percent discount, for a total of $2,830.00. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. Order weight 4,000 lb, 40 hundredweight, total of 283,000 cents at modeled prices.
    • 
    

    
3. Order just under the minimum: A McCoy short-grain order of 12 thousand sheets with an 8 percent discount

    
The agent's request. Please quote McCoy silk text paper, 80 lb, 25 by 38 inch sheets, short grain, 12 thousand sheets, delivered, with a 8 percent discount, for a total of $1,481.79. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Below minimum order weight. The order weighs 1,920 lb; the minimum is 2,000 lb.
    • 
      
  • Discount needs approval. A discount of 8 percent is above 5 percent and needs sales management approval.
    • 
      
  • Short grain availability to confirm. Short grain is made to order and the mill must confirm availability.
    • 
    

    
4. Order just under the minimum: The agent resubmits after fixing the errors

    
The agent's request. Please quote McCoy silk text paper, 80 lb, 25 by 38 inch sheets, short grain, 13 thousand sheets, delivered, with a 8 percent discount, for a total of $1,601.80. It is ready to send.

    
Verdict: Needs approval.

    
    
      
  • Discount needs approval. A discount of 8 percent is above 5 percent and needs sales management approval.
    • 
      
  • Short grain availability to confirm. Short grain is made to order and the mill must confirm availability.
    • 
      
  • Order summary. Order weight 2,080 lb, 21 hundredweight, total of 160,180 cents at modeled prices.
    • 
    

    
5. Opus cover order, discount and total: An Opus cover order with a 13 percent discount and a stated total

    
The agent's request. Please quote Opus gloss cover paper, 100 lb, 23 by 35 inch sheets, long grain, 15 thousand sheets, delivered, with a 13 percent discount, for a total of $4,073.06. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Discount above 12 percent. A discount of 13 percent is above the 12 percent maximum.
    • 
      
  • Stated total does not match. The quote states a total of 407,306 cents; the modeled prices give 412,306 cents.
    • 
    

    
6. Opus cover order, discount and total: The agent resubmits after fixing the errors

    
The agent's request. Please quote Opus gloss cover paper, 100 lb, 23 by 35 inch sheets, long grain, 15 thousand sheets, delivered, with a 5 percent discount, for a total of $4,479.72. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. Order weight 4,644 lb, 47 hundredweight, total of 447,972 cents at modeled prices.
    • 
    

  

  

    
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 an order of sheet paper: a brand (McCoy, Opus, Somerset, Flo or Magno), a finish, text or cover grade, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of sheet paper orders and returns a verdict, every reason and the total it computed.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Please quote Flo satin text paper, 120 lb, 28 by 40 inch sheets, short grain, 20 thousand sheets, delivered, with a 20 percent discount, for a total of $3,419.61. It is ready to send.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with five findings, all in one answer. The finish chosen is not offered in the brand chosen. A basis weight of 120 lb is outside the range of 60 to 100 lb for this brand. The sheet size chosen is not offered in the brand chosen. The other two are on screen.
    6. 
      
  6. The validator returned five 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. 
      
  7. What this shows: for a finish, weight or size that depends on the brand, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the finish to gloss, the basis weight to 100 lb, the sheet size to 25 x 38, the grain to long grain, the discount to 5 percent and the total as stated on the quote to $2,830.00.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. This time the validator clears it.
    12. 
      
  12. All five earlier findings are cleared.
    13. 
      
  13. Five problems caught in one call, fixed in one pass, and a clean $2,830.00 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.