Predictika · Interior paint orders

An AI sales agent's interior paint order, checked before it goes out

An AI sales agent prepares an interior paint order from the Flugger range: the product and the gloss level the specification asks for, the room, the surface and its primer, the tint depth, the number of coats, the liters of paint and primer, the customer type and any total the order states. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the product range and returns a verdict, every reason and the figures it computed.

Scope: Flugger interior wall and ceiling paint orders: gloss level, wash resistance for the room, ceiling gloss, priming, tint depth and coats, coverage, professional-range sales, volume pricing and the stated total. See everything this validator covers

This validator models Flugger interior paint orders, not just the scenarios shown below.

  • Products — the Dekso, Flutex, Flutex Pro and Perform interior ranges, with the primers Wall Primer Pro, Wall Primer Perform and Special Grund.
  • Product against room and specification — the gloss level must equal the specification, the wash class must meet what the room needs, and a ceiling is limited to low gloss.
  • Surface and quantities — new plasterboard or concrete must be primed, a chalky surface needs Special Grund, the primer must cover the area, a dark tint needs three coats, and the paint must cover the area times the coats.
  • Customer, value and stated total — a professional-range product sold to a consumer, much more paint than the area needs, or an order value of 20,000 euros or more goes to a sales manager; a total the order states is compared with the computed one.

Any Flugger interior paint order that touches these rules is in scope — not only the scenarios pictured here. Not covered: exterior and wood paints, fillers, adhesives, floors and other countries' ranges. Product names come from public Flugger listings; wash classes, spreading rates, preparation and tint rules, the professional-range rule, all prices, discounts and thresholds are modeled assumptions, not published by Flugger.

The AI sales agentBuilds the paint order from the conversation with the customer 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 product that must match the gloss specification and the roomOnly with care
Gloss level and wash class are properties of each product, so every product needs lookups and a comparison rule against the specification and against the room.		The product's properties are compared with the specification and the room directly on every call.
Surface preparation that depends on the surfaceOnly with care
New surfaces need a primer and chalky ones need a specific primer, so each surface needs its own rule that reads the primer choice.		The surface and the primer are fields of the same request and are checked together on every call.
Coats and liters that must cover the areaOnly with workarounds
The needed coats depend on the tint and the coverage on the product, so a separate rule is needed to compute each and compare it with the order.		The coats and coverage are derived once and compared with the order on every call.
A stated total that must match the computed oneOnly with workarounds
The total depends on product, tint, volume discount and primer, so it has to be recomputed in a separate rule before it can be compared.		The total is derived from the order and compared with the stated one on every call.
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 chosen product has gloss level 5 but the specification asks for gloss level 7.
2The chosen product has wash class 2 but the room needs wash class 3.
3The chosen product has wash class 1 but the room needs wash class 2.
4A ceiling with gloss level 7 will show every flaw; ceilings are limited to gloss level 5.
5A new plasterboard or concrete surface must be primed before painting.
6A chalky painted surface needs the acrylic priming paint Special Grund.
739 liters of primer do not cover 400 square meters at 10 square meters a liter.
82 coats are fewer than the 3 needed for this tint depth.
979 liters at 10 square meters a liter cannot cover 800 square meter coats.
10The 161 liters ordered cover more than twice the area to paint; a person should confirm the quantity.
11An area of 0 square meters is not valid; at least 1 is needed.
12The 100 liters ordered cover more than twice the area to paint; a person should confirm the quantity.
13A professional-range product is being sold to a consumer customer; a sales manager should confirm it.
14The quote states a total of 114,999 euro cents; the price list gives 115,000 euro cents.
15The quote states a total of 120,000 euro cents; the price list gives 115,000 euro cents.
16The order value of 16,975,000 euro cents is 20,000 euros or more; a sales manager should confirm it.
17The chosen product has gloss level 20 but the specification asks for gloss level 5.
18A ceiling with gloss level 20 will show every flaw; ceilings are limited to gloss level 5.
1910 liters at 10 square meters a liter cannot cover 600 square meter coats.

  

  

    
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. Hotel bathrooms on new plasterboard: A Dekso 5 order for wet rooms on new plasterboard with a dark tint

    
The agent's request. Please quote Dekso 5 for Nordlys Hotels: 250 liters on 3,200 square meters of wet rooms on new plasterboard, dark tint, 2 coats, gloss level 10, with no primer, and the order states a total of 4,000 euros. The customer is a professional buyer. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Gloss level differs from the specification. The chosen product has gloss level 5 but the specification asks for gloss level 10.
    • 
      
  • Wash resistance too low for the room. The chosen product has wash class 2 but the room needs wash class 3.
    • 
      
  • New surface needs a primer. A new plasterboard or concrete surface must be primed before painting.
    • 
      
  • Too few coats for the tint. 2 coats are fewer than the 3 needed for this tint depth.
    • 
      
  • Paint quantity does not cover the area. 250 liters at 9 square meters a liter cannot cover 6,400 square meter coats.
    • 
    

    
2. Hotel bathrooms on new plasterboard: The agent resubmits after fixing the errors

    
The agent's request. Please quote Flutex Pro 10 for Nordlys Hotels: 250 liters on 3,200 square meters of wet rooms on new plasterboard, dark tint, 2 coats, gloss level 10, with 320 liters of Wall Primer Pro, and the order states a total of 6,810 euros. The customer is a professional buyer. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Too few coats for the tint. 2 coats are fewer than the 3 needed for this tint depth.
    • 
      
  • Paint quantity does not cover the area. 250 liters at 10 square meters a liter cannot cover 6,400 square meter coats.
    • 
    

    
3. Hotel bathrooms on new plasterboard: The agent resubmits after fixing the errors

    
The agent's request. Please quote Flutex Pro 10 for Nordlys Hotels: 1,000 liters on 3,200 square meters of wet rooms on new plasterboard, dark tint, 3 coats, gloss level 10, with 320 liters of Wall Primer Pro, and the order states a total of 19,060 euros. The customer is a professional buyer. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 1,000 liters of paint at 1,750 euro cents a liter after a 100 euro cent discount, 320 liters of primer, total 1,906,000 euro cents.
    • 
    

    
4. Corridors with a chalky surface: A Flutex Pro 5 order for chalky corridors with the wrong primer

    
The agent's request. Please quote Flutex Pro 5 for Nordlys Hotels: 380 liters on 1,800 square meters of corridors on chalky painted walls, medium tint, 2 coats, gloss level 5, with 180 liters of Wall Primer Pro, and the order states a total of 6,380 euros. The customer is a professional buyer. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Chalky surface needs Special Grund. A chalky painted surface needs the acrylic priming paint Special Grund.
    • 
    

    
5. Corridors with a chalky surface: The agent resubmits after fixing the errors

    
The agent's request. Please quote Flutex Pro 5 for Nordlys Hotels: 300 liters on 1,800 square meters of corridors on chalky painted walls, medium tint, 2 coats, gloss level 5, with 180 liters of Special Grund, and the order states a total of 10,000 euros. The customer is a professional buyer. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Paint quantity does not cover the area. 300 liters at 10 square meters a liter cannot cover 3,600 square meter coats.
    • 
      
  • Stated total does not match. The quote states a total of 1,000,000 euro cents; the price list gives 588,000 euro cents.
    • 
    

    
6. Corridors with a chalky surface: The agent resubmits after fixing the errors

    
The agent's request. Please quote Flutex Pro 5 for Nordlys Hotels: 380 liters on 1,800 square meters of corridors on chalky painted walls, medium tint, 2 coats, gloss level 5, with 180 liters of Special Grund, and the order states a total of 6,920 euros. The customer is a professional buyer. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 380 liters of paint at 1,350 euro cents a liter after a 50 euro cent discount, 180 liters of primer, total 692,000 euro cents.
    • 
    

    
7. Professional range sold to a consumer: A corridor order of the professional range for a consumer

    
The agent's request. Please quote Flutex Pro 5 for Nordlys Hotels: 380 liters on 1,800 square meters of corridors on chalky painted walls, medium tint, 2 coats, gloss level 5, with 180 liters of Special Grund, and the order states a total of 6,920 euros. The customer is a consumer buyer. It is ready to send.

    
Verdict: Needs approval.

    
    
      
  • Professional range sold to a consumer. A professional-range product is being sold to a consumer customer; a sales manager should confirm it.
    • 
      
  • Order summary. 380 liters of paint at 1,350 euro cents a liter after a 50 euro cent discount, 180 liters of primer, total 692,000 euro cents.
    • 
    

  

  

    
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 an interior paint order from the Flugger range: the product and the gloss level the specification asks for, the room, the surface and its primer, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the product range and returns a verdict, every reason and the figures it computed.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Please quote Dekso 5 for Nordlys Hotels: 250 liters on 3,200 square meters of wet rooms on new plasterboard, dark tint. The customer is a professional buyer. The rest of the request is on screen.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with five findings, all in one answer. The chosen product has gloss level 5 but the specification asks for gloss level 10. The chosen product has wash class 2 but the room needs wash class 3. A new plasterboard or concrete surface must be primed before painting. 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 order are checked against each other.
    7. 
      
  7. What this shows: for a product that must match the gloss specification and the room, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the product to Flutex Pro 10, the primer to Wall Primer Pro, the primer to 320 liters and the stated total to €6,810.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. Still blocked, with two findings, all in one answer. 2 coats are fewer than the 3 needed for this tint depth. 250 liters at 10 square meters a liter cannot cover 6,400 square meter coats.
    12. 
      
  12. Three findings cleared. Still blocking: too few coats for the tint and paint quantity does not cover the area.
    13. 
      
  13. The agent resubmits once more.
    14. 
      
  14. The revised request. It changes the coats to 3, the paint to 1,000 liters and the stated total to €19,060.
    15. 
      
  15. It calls the validator once more.
    16. 
      
  16. This time the validator clears it.
    17. 
      
  17. Both earlier findings are cleared.
    18. 
      
  18. Five problems caught in one call, fixed in two passes, and a clean 19,060 euros order. That is the value of Predictika's validator: catching mistakes before they reach the customer. Now you can try the other scenarios yourself.
    19.