Predictika · Outdoor LED video displays

An AI sales agent's LED video display order, checked before it goes out

An AI sales agent prepares an order for outdoor LED video displays of one product line, the LVX-3000 10SMD, from the public Daktronics product specification: the cabinet size, the video controller, sponsor logo graphics on the filler panels, the site power and the figures the order states. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of that specification and returns a verdict, every reason and the figures it computed.

Scope: LVX-3000 10SMD outdoor LED video displays: listed cabinet sizes, pixel matrix, weight and power, filler panel graphics, controller video inputs and site power. See everything this validator covers

This validator models orders for the Daktronics LVX-3000 10SMD outdoor video display as set out in the public product specification, not just the scenarios shown below.

  • Listed sizes — 29 standard cabinet sizes and 8 scoreboard-to-video upgrade sizes, each with its pixel matrix, uncrated weight and average and maximum power. A cabinet height and width that is not in the chosen table is blocked, and so is a stated power or weight that differs from the specification.
  • Filler panels and graphics — the specification says filler panels of 1 ft (305 mm) and under are simple filler panels and not offered with logo or sponsor graphics; the sizes it marks that way are blocked when graphics are requested on them.
  • Controller and site power — the controller list has one, four and eight video input versions, and the validator blocks an order with more video sources than the controller has inputs. The order's total maximum power is compared with the site power the customer states.

Any order for this display line that touches these rules is in scope — not only the scenarios pictured here. Not covered: prices (Daktronics publishes none for this product, so this validator produces no price build-up or line-item quote), other Daktronics display lines, mounting, structures, installation, software and services. Assumptions: the controller's video inputs are read as the number of video sources it can take, the maximum power listed in the specification is compared with the site power stated, and sizes are matched on the metric cabinet height and width in the specification.

The AI sales agentBuilds the display order 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 size that must be one of a published list of cabinet sizesOnly with care
A lookup of height and width against the table; every size is another row to maintain, and a size that is close but not listed is easy to type.		The requested height and width are matched against the listed sizes of the chosen table on every call.
Two size tables that must not be mixedOnly with care
A size from the upgrade list is easily quoted as a standard one; the rule has to look at the table and the size together.		The table and the size are in one request and are matched together.
A graphics option that depends on a dimension of the chosen sizeOnly with workarounds
The filler panel width is a property of the size, so the option rule has to read a derived value rather than a choice the rep made.		The filler panel limit is derived from the size and checked against the graphics request on every call.
Stated figures that must equal the specificationOnly with care
A stated power or weight is a free-entry field; a rule can compare it with the size's listed value, but only if the table is kept in step.		Each stated figure travels with the order and is compared with the listed value for the size on every call.
Site power against the total maximum power of the orderOnly with workarounds
The total depends on the quantity and the size, and is compared with a figure from the customer, so it needs a cross-line rule that interacts with the others.		Quantity, size and site power are in one request and the comparison is made with the rest.
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 quote; approval findings need a person to sign off; everything else is computed.

    
1The order asks for a cabinet 3.00 m high by 6.00 m wide; no such size is listed in the selected size table.
2The order asks for a cabinet 3.60 m high by 6.50 m wide; no such size is listed in the selected size table.
3The order asks for a cabinet 3.60 m high by 6.40 m wide; no such size is listed in the selected size table.
4The order asks for a cabinet 2.80 m high by 11.20 m wide; no such size is listed in the selected size table.
5The order has no displays.
6This size has a filler panel of 1 ft or less, which the specification calls a simple filler panel not offered with logo or sponsor graphics.
7The order needs 5 video inputs; the chosen controller has 4 video inputs.
8The order needs 2 video inputs; the chosen controller has 1 video input.
9The displays are listed at 31,224 W maximum power in total; the site supply stated for them is 31,223 W.
10The order states a maximum power of 15,611 W per display; the specification lists 15,612 W for this size.
11The order states a maximum power of 3,903 W per display; the specification lists 15,612 W for this size.
12The order states an uncrated weight of 2,874 lb per display; the specification lists 2,875 lb for this size.
13The order states an uncrated weight of 3,175 lb per display; the specification lists 2,875 lb for this size.
14The order needs 3 video inputs; the chosen controller has 1 video input.
15The displays are listed at 318,810 W maximum power in total; the site supply stated for them is 100,000 W.
16The order states a maximum power of 31,000 W per display; the specification lists 31,881 W for this size.
17The order states an uncrated weight of 5,000 lb per display; the specification lists 5,475 lb for this size.

  

  

    
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. Cabinet size: 4 displays of a 5.00 m by 9.00 m cabinet

    
The agent's request. Please quote 4 LVX-3000 10SMD outdoor video displays of the standard size 5.00 m high by 9.00 m wide, driven by a four-input video controller for 3 video sources, on a site supply of 130,000 W for the displays. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Not a listed cabinet size. The order asks for a cabinet 5.00 m high by 9.00 m wide; no such size is listed in the selected size table.
    • 
    

    
2. Cabinet size: The agent resubmits after fixing the errors

    
The agent's request. Please quote 4 LVX-3000 10SMD outdoor video displays of the standard size 5.20 m high by 9.20 m wide, driven by a four-input video controller for 3 video sources, on a site supply of 130,000 W for the displays. The order states a maximum power of 31,881 W and an uncrated weight of 5,325 lb per display. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 4 displays, each 520 rows by 920 columns of pixels, 5,325 lb uncrated and 31,881 W maximum power (127,524 W maximum for the order).
    • 
    

    
3. Filler panel graphics and stated figures: 6 displays with sponsor logos on the filler panels and stated figures that are too low

    
The agent's request. Please quote 6 LVX-3000 10SMD outdoor video displays of the standard size 3.20 m high by 6.10 m wide, driven by a four-input video controller for 4 video sources, with sponsor logo graphics on the filler panels, on a site supply of 75,000 W for the displays. The order states a maximum power of 11,000 W and an uncrated weight of 2,000 lb per display. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Logo graphics on a simple filler panel. This size has a filler panel of 1 ft or less, which the specification calls a simple filler panel not offered with logo or sponsor graphics.
    • 
      
  • Stated maximum power does not match. The order states a maximum power of 11,000 W per display; the specification lists 11,881 W for this size.
    • 
      
  • Stated weight does not match. The order states an uncrated weight of 2,000 lb per display; the specification lists 2,150 lb for this size.
    • 
    

    
4. Filler panel graphics and stated figures: The agent resubmits after fixing the errors

    
The agent's request. Please quote 6 LVX-3000 10SMD outdoor video displays of the standard size 3.20 m high by 6.10 m wide, driven by a four-input video controller for 4 video sources, on a site supply of 75,000 W for the displays. The order states a maximum power of 11,881 W and an uncrated weight of 2,150 lb per display. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 6 displays, each 320 rows by 560 columns of pixels, 2,150 lb uncrated and 11,881 W maximum power (71,286 W maximum for the order).
    • 
    

    
5. Controller and site power: 10 displays on a one-input controller with too little site power

    
The agent's request. Please quote 10 LVX-3000 10SMD outdoor video displays of the standard size 2.80 m high by 4.80 m wide, driven by a one-input video controller for 3 video sources, on a site supply of 80,000 W for the displays. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • More video sources than controller inputs. The order needs 3 video inputs; the chosen controller has 1 video input.
    • 
      
  • Site power supply below the maximum power. The displays are listed at 89,290 W maximum power in total; the site supply stated for them is 80,000 W.
    • 
    

    
6. Controller and site power: The agent resubmits after fixing the errors

    
The agent's request. Please quote 10 LVX-3000 10SMD outdoor video displays of the standard size 2.80 m high by 4.80 m wide, driven by a four-input video controller for 3 video sources, on a site supply of 80,000 W for the displays. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Site power supply below the maximum power. The displays are listed at 89,290 W maximum power in total; the site supply stated for them is 80,000 W.
    • 
    

    
7. Controller and site power: The agent resubmits after fixing the errors

    
The agent's request. Please quote 10 LVX-3000 10SMD outdoor video displays of the standard size 2.80 m high by 4.80 m wide, driven by a four-input video controller for 3 video sources, on a site supply of 90,000 W for the displays. The order states a maximum power of 8,929 W and an uncrated weight of 1,625 lb per display. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 10 displays, each 280 rows by 480 columns of pixels, 1,625 lb uncrated and 8,929 W maximum power (89,290 W maximum for the order).
    • 
    

  

  

    
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 order for outdoor LED video displays of one product line, the LVX-3000 10SMD, from the public Daktronics product specification: the cabinet size, the video controller, sponsor logo graphics on the filler panels, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of that specification 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 6 LVX-3000 10SMD outdoor video displays of the standard size 3.20 m high by 6.10 m wide, driven by a four-input video controller for 4 video sources. The order states a maximum power of 11,000 W and an uncrated weight of 2,000 lb per display. The rest of the request is on screen.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with three findings, all in one answer. This size has a filler panel of 1 ft or less, which the specification calls a simple filler panel not offered with logo or sponsor graphics. The order states a maximum power of 11,000 W per display; the specification lists 11,881 W for this size. The order states an uncrated weight of 2,000 lb per display; the specification lists 2,150 lb for this size.
    6. 
      
  6. The validator returned three 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 site power against the total maximum power of the order, a rules-based CPQ can do this only with workarounds.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the sponsor logo graphics on filler panels to no, the stated maximum power per display to 11,881 W and the stated uncrated weight per display to 2,150 lb.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. This time the validator clears it.
    12. 
      
  12. All three earlier findings are cleared, and the validator's figure matches the quote.
    13. 
      
  13. Three 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.
    14.