Predictika · onshore wind parks: turbines, site conditions, grid, AOM service and discounts

An AI sales agent's wind park quote, checked before it goes out

An AI sales agent prepares an onshore wind park quote for a fictional developer. Before it goes out, the agent sends it to Predictika’s validator, which checks it against the turbine, site, grid and service rules, compares the total the agent states with the one it computes, and returns a verdict with every reason.

Scope: onshore wind park quotes: V150, V162 and V172 turbines with AOM service. See everything this validator covers

This validator models onshore wind park quotes in the style of Vestas: V150-4.5, V162-6.2, V162-7.2 and V172-7.2 EnVentus turbines with AOM service agreements. It handles any quote made of these products and rules, not just the scenarios shown below.

  • Turbines and site — Four onshore turbines (V150-4.5, V162-6.2, V162-7.2 and V172-7.2 EnVentus) checked against the site: mean wind against the IEC wind class (with a load-assessment approval within 5 percent of the limit), turbulence category and the hub height range of the tower.
  • Climate, transport and permit — Cold climate package below minus 20 C and not offered below minus 30 C, anti-icing on icing sites, blade length against the transport route, and tip height (hub plus half the rotor) against the permit.
  • Grid and service — Park capacity against the grid connection, the advanced grid option under the GB grid code, and AOM 1000, 4000 and 5000 service agreements with availability guarantees, an approval above 97 percent on AOM 5000 and a 5 to 30 year term.
  • Lead time, discount and the stated total — Delivery lead time against the commissioning date, discount authority by order size (2 percent for a sales manager, up to 5 percent, or 8 percent on EUR 150 million or more), pricing from rated power, hub premium and options, and a check that the total the agent states matches the total the validator computes.

It does not cover offshore turbines, other Vestas products, real list prices, energy yield studies, or financing and the contract terms.

The AI sales agentBuilds the quote from the conversation and says it is ready.
Predictika validatorChecks the quote against the product and contract rules and returns every finding it has.

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 or Revenue Cloud) does with the same cases. It is a judgment about effort and reliability, not a claim that nothing can be built.

    
What the validator catchesTypical rules-based CPQPredictika
Wind class and turbulence by turbineOnly with workarounds
Each turbine has its own wind and turbulence class, so every combination of site and turbine tends to need its own validation rule.		The limits are read from the turbine record and checked against the site together.
Tip height from hub and rotorOnly with care
Tip height is hub height plus half the rotor diameter, a derived figure that rules usually recompute in several places.		It is computed once and checked against the permit.
Lead time against the commissioning dateOnly with workarounds
The longest lead time, plus two months for the cold climate package, compared with the date the customer wants, takes custom logic.		Lead time is computed on every call and compared with the date.
Discount authority by order sizeOnly with care
Who may approve how much depends on the size of the order, which means tiered approval rules that must stay in step with the price.		The limit follows the equipment price, with block and approval bands.
The total the agent statesOnly with workarounds
Comparing a stated total with a computed one means a separate rule per quote layout, and price rules rarely run on stated figures.		The stated total is a field in the request and is checked against the computed total.
Every problem returned in one answerOnly with workarounds
Rules tend to fire as the quote is saved, 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
Click to expand
    
Every rule is checked on every call, in whatever order the choices arrive, and one problem never hides another. Blocking findings stop the quote; approval findings need a person to sign off; everything else is computed.

    
RuleEffectWhat it checks
Site mean wind at hub vs turbine IEC class limitblocksite mean wind at hub vs turbine IEC class limit
Within 5 percent of the class limit needs a site-specific load assessmentneeds approvalwithin 5 percent of the class limit needs a site-specific load assessment
Site turbulence category vs turbine certificationblocksite turbulence category vs turbine certification
Hub height within the turbine tower rangeblockhub height within the turbine tower range
Below -20 C requires the cold climate packageblockbelow -20 C requires the cold climate package
Below -30 C not offered even with the packageblockbelow -30 C not offered even with the package
Icing-risk site requires anti-icingblockicing-risk site requires anti-icing
Blade length vs transport route limitblockblade length vs transport route limit
Tip height = hub + rotor/2 vs permitblocktip height = hub + rotor/2 vs permit
Park kW vs grid connection MWblockpark kW vs grid connection MW
GB grid code requires the advanced grid optionblockGB grid code requires the advanced grid option
Availability guarantee vs AOM tier maximumblockavailability guarantee vs AOM tier maximum
Above 97 percent on AOM 5000 needs service approvalneeds approvalabove 97 percent on AOM 5000 needs service approval
AOM term 5 to 30 yearsblockAOM term 5 to 30 years
Lead time = turbine lead + 2 months cold climate vs commissioning datecomputed, with bandslead time = turbine lead + 2 months cold climate vs commissioning date
Discount authority 2 manager / 5 region / 8 on EUR 150M+computed, with bandsdiscount authority 2 manager / 5 region / 8 on EUR 150M+
Unit price = kW x EUR/kW + tower premium per metre + climate/anti-icing/grid options; AOM = park kW x rate x yearscomputed, with bandsunit price = kW x EUR/kW + tower premium per metre + climate/anti-icing/grid options; AOM = park kW x rate x years

  

  

    
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. Wind class: V172 on an 8.0 m/s site

    
The agent's request. Ten V172-7.2 MW EnVentus turbines at 150 m hub height, no service agreement. Total price EUR 72,540,000. Ready to send.

    
Verdict: Blocked.

    
    
      
  • Wind class. Site mean wind 8.0 m/s exceeds the 7.5 m/s limit of the V172-7.2 MW EnVentus wind class.
    • 
    

    
2. Wind class: V162-7.2 on the same site

    
The agent's request. Ten V162-7.2 MW EnVentus turbines at 125 m hub height, no service agreement. Total price EUR 70,650,000. Ready to send.

    
Verdict: Allowed.

    
3. Delivery time and discount: Wanted in 14 months at 10 percent

    
The agent's request. Ten V162-7.2 MW EnVentus turbines at 125 m hub height with a 10 percent discount, no service agreement. Total price EUR 63,585,000. Ready to send.

    
Verdict: Blocked.

    
    
      
  • Delivery time. Delivery takes about 18 months; the customer needs commissioning in 14.
    • 
      
  • Discount limit. 10 percent discount exceeds the 5 percent that can be approved on EUR 70650000.0.
    • 
    

    
4. Delivery time and discount: V150-4.5 at 5 percent

    
The agent's request. Sixteen V150-4.5 MW turbines at 105 m hub height with a 5 percent discount, no service agreement. Total price EUR 64,980,000. Ready to send.

    
Verdict: Needs approval.

    
    
      
  • Discount approval. 5 percent discount is above the 2 percent a sales manager can give; approvable up to 5 percent.
    • 
    

    
5. Delivery time and discount: V150-4.5 at 2 percent

    
The agent's request. Sixteen V150-4.5 MW turbines at 105 m hub height with a 2 percent discount, no service agreement. Total price EUR 67,032,000. Ready to send.

    
Verdict: Allowed.

    
6. The total the agent states: Stated total too low

    
The agent's request. Ten V162-7.2 MW EnVentus turbines at 125 m hub height with a 2 percent discount and a 20-year AOM 5000 service agreement at 97 percent availability. Total price EUR 111,561,300. Ready to send.

    
Verdict: Blocked.

    
    
      
  • Total the agent stated. The quoted total of EUR 111561300.0 does not match the EUR 123957000.0 the validator computed.
    • 
    

    
7. The total the agent states: Stated total corrected

    
The agent's request. Ten V162-7.2 MW EnVentus turbines at 125 m hub height with a 2 percent discount and a 20-year AOM 5000 service agreement at 97 percent availability. Total price EUR 123,957,000. Ready to send.

    
Verdict: Allowed.

  

  

    
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 onshore wind park quote for a fictional developer. Before it goes out, the agent sends it to Predictika’s validator, which checks it against the turbine, site, grid and service rules, compares the total the agent states with the one it computes, and returns a verdict with every reason.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Ten V172-7.2 MW EnVentus turbines at 150 m hub height, no service agreement. Total price EUR 72,540,000. The rest of the request is on screen.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with one finding, all in one answer. Site mean wind 8.0 m/s exceeds the 7.5 m/s limit of the V172-7.2 MW EnVentus wind class.
    6. 
      
  6. The validator returned one blocking finding 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 wind class and turbulence by turbine, a rules-based CPQ can do this only with workarounds.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the turbine to V162-7.2 MW EnVentus, the Hub Height to 125 m and the stated total as to 70,650,000 EUR.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. This time the validator clears it.
    12. 
      
  12. The validator also returns the line-item quote, on screen.
    13. 
      
  13. The earlier finding is cleared, and the validator's total, EUR 70,650,000, matches the quote.
    14. 
      
  14. One problem 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.
    15.