Predictika · Gas turbine power plant quotes

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

An AI sales agent prepares a gas turbine plant quote for a fictional customer: the turbine model, number of units, simple or combined cycle, grid frequency, emissions permit, service agreement and schedule. Before it goes out, the agent sends it to Predictika’s validator, which checks it against the plant and commercial rules, compares the total the agent states with its own, and returns a verdict with every reason.

Scope: heavy-duty and aeroderivative gas turbine plant quotes: grid frequency, output at altitude, emissions permit, hydrogen, start time, lead time, service agreement, price concession, and the total the agent states. See everything this validator covers

This validator models the rules for a gas turbine plant quote to a utility or power producer. It handles any quote built from these turbine families, cycles and terms, not just the scenarios shown below.

  • Turbine families — GE Vernova 7HA.02, 7HA.03, 9HA.01, 9HA.02 and 7F.05 heavy-duty units, and LM6000 and LM2500XPRESS aeroderivative units, in simple or 1x1 combined cycle.
  • Plant requirements — Grid frequency, required output with altitude derate, NOx permit with SCR, hydrogen blend, start time, and months to commercial operation.
  • Commercial terms — Service agreement type and years, price concession and sales authority, and the total the agent states.

It does not cover plant balance-of-plant design, multi-site or multi-phase projects, financing, or real product ratings and prices. Ratings, prices, lead times and thresholds are estimates from public information.

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
Turbine, cycle and grid fitOnly with workarounds
Frequency, cycle, altitude derate and output are chained conditions across product families, usually a rule set per turbine model.		Each turbine is data in a catalog; the same rules evaluate every model and combination.
Emissions permit and SCROnly with care
Comparing a permit with a model’s emissions and adding SCR needs a validation rule and a price rule that must be kept in step.		Permit, turbine emissions and SCR are evaluated together with every other rule, and the reason names the fix.
Schedule against lead timeOnly with care
Lead time depends on the model and the cycle, so a calculated field and a validation rule are needed for each case.		Lead time and start time are derived on each call and compared with the schedule.
Concession authority bandsOnly with care
An approval band, a hard maximum and a plant-size tier are separate price and validation rules that must be chained.		Concession, plant size and authority are derived on each call and compared with both thresholds.
The total the agent statesOnly with workarounds
Comparing a stated figure with a computed one means a separate rule per 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 built, so a problem raised late can hide an earlier one.		Every rule is evaluated at the end of input and all findings come back together.

  

  

    
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
1blockThe turbine frequency must match the grid (the aeroderivative units run on 50 or 60 Hz)
2block, approvalInstalled output, derated 3 percent per 1,000 feet of altitude, must meet the requirement; more than 150 percent of it needs approval
3blockTurbine NOx (2 ppm with SCR) must be within the permit
4blockHydrogen blend must be within the combustor capability of the turbine
5blockStart time to full load (longer in combined cycle) must fit the site requirement
6blockHA-class units need a contractual service agreement; a combined-cycle block holds at most 3 turbines
7blockTurbine lead time (longer in combined cycle) must fit the months to commercial operation
8block, approvalA price concession above the 2 percent sales authority needs approval; above 5 percent (8 percent on large plants) blocks
9computedPlant price is units times the unit price, with adders for combined cycle, SCR and hydrogen capability; the service agreement is added
10blockThe total the agent states must match the validator total within $0.05 million

  

  

    
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. Grid frequency: Turbine for the wrong grid

    
The agent's request. Quote for Prairie Wind Power: one GE Vernova 9HA.01 gas turbine in simple cycle for the 400 MW requirement on the 60 Hz grid, 25 ppm NOx permit, commercial operation in 36 months. Total price $225.20 million. Ready to send.

    
Verdict: Blocked.

    
    
      
  • Turbine does not match the grid frequency. The GE Vernova 9HA.01 is a 50 Hz machine; the grid is 60 Hz.
    • 
    

    
2. Grid frequency: A 60 Hz turbine

    
The agent's request. Quote for Prairie Wind Power: one GE Vernova 7HA.03 gas turbine in simple cycle for the 400 MW requirement on the 60 Hz grid, 25 ppm NOx permit, commercial operation in 36 months. Total price $214.48 million. Ready to send.

    
Verdict: Allowed.

    
3. Emissions permit: Permit tighter than the turbine

    
The agent's request. Quote for Riverbend Energy: one GE Vernova 7HA.02 gas turbine in 1x1 combined cycle for the 550 MW requirement on the 60 Hz grid, 2 ppm NOx permit, commercial operation in 40 months. Total price $321.60 million. Ready to send.

    
Verdict: Blocked.

    
    
      
  • Emissions above the permit. The GE Vernova 7HA.02 emits 25 ppm NOx without SCR; the permit allows 2 ppm - add SCR.
    • 
    

    
4. Emissions permit: Same turbine with SCR

    
The agent's request. Quote for Riverbend Energy: one GE Vernova 7HA.02 gas turbine in 1x1 combined cycle with SCR for the 550 MW requirement on the 60 Hz grid, 2 ppm NOx permit, commercial operation in 40 months. Total price $329.60 million. Ready to send.

    
Verdict: Allowed.

    
5. The total the agent states: Stated total leaves out service

    
The agent's request. Quote for Mesa Grid Partners: two GE Vernova 7F.05 gas turbines in 1x1 combined-cycle blocks for the 700 MW requirement on the 60 Hz grid, 9 ppm NOx permit, 20-year full service agreement, 2 percent price concession, commercial operation in 30 months. Total price $401.80 million. Ready to send.

    
Verdict: Blocked.

    
    
      
  • Stated total differs from the validator total. The total price the agent states ($401.8M) differs from the total the validator computes ($481.8M).
    • 
    

    
6. The total the agent states: Stated total corrected

    
The agent's request. Quote for Mesa Grid Partners: two GE Vernova 7F.05 gas turbines in 1x1 combined-cycle blocks for the 700 MW requirement on the 60 Hz grid, 9 ppm NOx permit, 20-year full service agreement, 2 percent price concession, commercial operation in 30 months. Total price $481.80 million. Ready to send.

    
Verdict: Allowed.

    
7. Needs approval: Concession above sales authority

    
The agent's request. Quote for Coastal Power Authority: two GE Vernova 7HA.03 gas turbines in 1x1 combined-cycle blocks for the 1,200 MW requirement on the 60 Hz grid, 2 ppm NOx permit with SCR, 6 percent price concession, commercial operation in 44 months. Total price $722.00 million. Ready to send.

    
Verdict: Needs approval.

    
    
      
  • Price concession needs approval. 6 percent price concession is above the 2 percent sales authority; approvable up to 8 percent.
    • 
    

  

  

    
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 gas turbine plant quote for a fictional customer: the turbine model, number of units, simple or combined cycle, and more. Before it goes out, the agent sends it to Predictika’s validator, which checks it against the plant and commercial rules, compares the total the agent states with its own, and returns a verdict with every reason.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Quote for Prairie Wind Power: one GE Vernova 9HA.01 gas turbine in simple cycle for the 400 MW requirement on the 60 Hz grid. Total price $225.20 million. 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. The GE Vernova 9HA.01 is a 50 Hz machine; the grid is 60 Hz.
    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 turbine, cycle and grid fit, 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 GE Vernova 7HA.03 and the stated total as to 214.48.
    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.
    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.
    15.