Predictika · Gas turbine power block quotes

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

An AI sales agent prepares a quote for a gas turbine power block: a turbine model, simple cycle or combined cycle, a steam turbine, the number of blocks, and the output, efficiency, emissions and flexibility the customer needs. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the DGT6-300H series and returns a verdict, every reason and the totals it computed.

Scope: Doosan DGT6-300H.S1 and .S2 gas turbines as simple cycle, 1-on-1 or 2-on-1 combined cycle power blocks, with DST-S10, S20 or S30 steam turbines and optional SCR. See everything this validator covers

This validator models Doosan DGT6-300H power block quotes, not just the scenarios shown below.

  • Configuration — simple cycle, 1-on-1 and 2-on-1 combined cycle, with a steam turbine that must fit the configuration, and one or more power blocks.
  • Performance — the output, efficiency, NOx level, minimum load, start time and ramp rate the customer needs, each compared with what the quoted configuration is rated for, with SCR as the way to a lower NOx.
  • Price and approvals — the stated output and list total against the computed values, a discount limit, and people to confirm a large discount, the upgraded S2 model or three or more blocks.

Any DGT6-300H power block quote that touches these rules is in scope — not only the scenarios pictured here. Not covered: services, other turbine sizes, steam and boiler products, and taxes. The validator shows computed totals but no line-item table.

The AI sales agentBuilds the power block 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
Steam turbine that must fit the configurationOnly with care
Each configuration allows only certain steam turbines, so every pairing needs its own rule, and the rule changes with the number of gas turbines per block.		The configuration and the steam turbine are fields of one request and are checked together on every call.
Customer needs against rated valuesOnly with care
Output, efficiency, NOx, load, start time and ramp each need their own comparison with the rating, and the rating changes with the turbine model and configuration.		Every requirement is a field of the request and is compared with the rated value of the chosen configuration on every call.
A lower NOx that depends on SCROnly with care
The reachable NOx level depends on whether SCR is added, so the check and the price both depend on that choice.		The SCR choice and the NOx requirement are in one request and are compared on every call.
Stated figures that must match the computed onesOnly with workarounds
The output and the list total are built from turbines, boilers, steam turbines and blocks, so separate rules are needed to recompute them and compare them with the stated figures.		The stated figures are fields of the request and are compared with the computed ones 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.

    
1The steam turbine choice does not fit the configuration (simple cycle has none; 1-on-1 uses DST-S10 or DST-S20; 2-on-1 uses DST-S20 or DST-S30).
2The customer needs 450 MW; the quoted configuration delivers 400 MW.
3The customer asks for 610 tenths of a percent efficiency; the configuration is rated for 600.
4The permit needs 10 ppm NOx; this configuration reaches 15 ppm.
5The permit needs 8 ppm NOx; this configuration reaches 9 ppm.
6The customer needs operation down to 30 percent load; turn-down is 40 percent.
7The customer needs a start in 10 minutes; the fast start is 12 minutes.
8The customer needs 45 MW per minute per gas turbine; this model ramps at 40.
9The quote states 450 MW; the configuration delivers 400 MW.
10The quote states a list total of 170 million; the equipment adds up to 178 million.
11The discount of 9 million is more than 5 percent of the list total of 178 million; a sales director must approve it.
12The discount of 25 million is more than 12 percent of the list total of 178 million.
13The DGT6-300H.S2 is the upgraded 380 MW model; a person should confirm its reference status and guarantee terms.
14The permit needs 25 ppm NOx; this configuration reaches 30 ppm.
153 power blocks in one quote; a person should confirm the delivery schedule and manufacturing slots.

  

  

    
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. Configuration and performance: A 1-on-1 power block with a DST-S30 steam turbine, 450 MW and NOx of 10 ppm

    
The agent's request. Please quote 1 DGT6-300H.S1 1-on-1 combined cycle power block with a DST-S30 steam turbine. The customer needs 450 MW, 59.0 percent efficiency, NOx of 10 ppm, operation down to 30 percent load, a start in 20 minutes and a ramp of 45 MW per minute per gas turbine. The quote states 400 MW and a list total of 220 million dollars, with a discount of 4 million. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Steam turbine not valid for this configuration. The steam turbine choice does not fit the configuration (simple cycle has none; 1-on-1 uses DST-S10 or DST-S20; 2-on-1 uses DST-S20 or DST-S30).
    • 
      
  • Required output exceeds the configuration. The customer needs 450 MW; the quoted configuration delivers 400 MW.
    • 
      
  • NOx limit below the achievable level. The permit needs 10 ppm NOx; this configuration reaches 15 ppm.
    • 
      
  • Minimum load below the turn-down. The customer needs operation down to 30 percent load; turn-down is 40 percent.
    • 
      
  • Ramp rate over the rated value. The customer needs 45 MW per minute per gas turbine; this model ramps at 40.
    • 
      
  • Stated list total does not match. The quote states a list total of 220 million; the equipment adds up to 238 million.
    • 
    

    
2. Configuration and performance: The agent resubmits after fixing the errors

    
The agent's request. Please quote 2 DGT6-300H.S1 1-on-1 combined cycle power blocks with a DST-S20 steam turbine and SCR. The customer needs 450 MW, 59.0 percent efficiency, NOx of 10 ppm, operation down to 50 percent load, a start in 20 minutes and a ramp of 30 MW per minute per gas turbine. The quote states 800 MW and a list total of 418 million dollars, with a discount of 4 million. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Plant summary. 2 gas turbine(s), 800 MW total, list total 418 million, net 414 million.
    • 
    

    
3. Output, efficiency and discount: A 2-on-1 power block asked for 900 MW, with a large discount

    
The agent's request. Please quote 1 DGT6-300H.S1 2-on-1 combined cycle power block with a DST-S10 steam turbine. The customer needs 900 MW, 62.0 percent efficiency, NOx of 25 ppm, operation down to 50 percent load, a start in 20 minutes and a ramp of 30 MW per minute per gas turbine. The quote states 800 MW and a list total of 301 million dollars, with a discount of 50 million. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Steam turbine not valid for this configuration. The steam turbine choice does not fit the configuration (simple cycle has none; 1-on-1 uses DST-S10 or DST-S20; 2-on-1 uses DST-S20 or DST-S30).
    • 
      
  • Required output exceeds the configuration. The customer needs 900 MW; the quoted configuration delivers 800 MW.
    • 
      
  • Efficiency above the rated value. The customer asks for 620 tenths of a percent efficiency; the configuration is rated for 600.
    • 
      
  • Discount over 12 percent. The discount of 50 million is more than 12 percent of the list total of 301 million.
    • 
    

    
4. Output, efficiency and discount: The agent resubmits after fixing the errors

    
The agent's request. Please quote 1 DGT6-300H.S1 2-on-1 combined cycle power block with a DST-S30 steam turbine. The customer needs 780 MW, 60.0 percent efficiency, NOx of 25 ppm, operation down to 50 percent load, a start in 20 minutes and a ramp of 30 MW per minute per gas turbine. The quote states 800 MW and a list total of 361 million dollars, with a discount of 15 million. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Plant summary. 2 gas turbine(s), 800 MW total, list total 361 million, net 346 million.
    • 
    

    
5. Simple cycle and stated figures: A simple cycle unit with a steam turbine and a fast start

    
The agent's request. Please quote 1 DGT6-300H.S1 simple cycle power block with a DST-S10 steam turbine. The customer needs 250 MW, 41.0 percent efficiency, NOx of 25 ppm, operation down to 50 percent load, a start in 8 minutes and a ramp of 30 MW per minute per gas turbine. The quote states 300 MW and a list total of 95 million dollars, with a discount of 0 million. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Steam turbine not valid for this configuration. The steam turbine choice does not fit the configuration (simple cycle has none; 1-on-1 uses DST-S10 or DST-S20; 2-on-1 uses DST-S20 or DST-S30).
    • 
      
  • Efficiency above the rated value. The customer asks for 410 tenths of a percent efficiency; the configuration is rated for 400.
    • 
      
  • Start time faster than the fast start. The customer needs a start in 8 minutes; the fast start is 12 minutes.
    • 
      
  • Stated output does not match. The quote states 300 MW; the configuration delivers 270 MW.
    • 
      
  • Stated list total does not match. The quote states a list total of 95 million; the equipment adds up to 150 million.
    • 
    

    
6. Simple cycle and stated figures: The agent resubmits after fixing the errors

    
The agent's request. Please quote 1 DGT6-300H.S1 simple cycle power block with no steam turbine. The customer needs 250 MW, 39.0 percent efficiency, NOx of 25 ppm, operation down to 50 percent load, a start in 12 minutes and a ramp of 30 MW per minute per gas turbine. The quote states 270 MW and a list total of 95 million dollars, with a discount of 0 million. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Plant summary. 1 gas turbine(s), 270 MW total, list total 95 million, net 95 million.
    • 
    

  

  

    
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 a gas turbine power block: a turbine model, simple cycle or combined cycle, a steam turbine, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the DGT6-300H series and returns a verdict, every reason and the totals it computed.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Please quote 1 DGT6-300H.S1 1-on-1 combined cycle power block with a DST-S30 steam turbine. The customer needs 450 MW, 59.0 percent efficiency, NOx of 10 ppm, operation down to 30 percent load, a start in 20 minutes and a ramp of 45 MW per minute per gas turbine. The rest of the request is on screen.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with six findings, all in one answer. The steam turbine choice does not fit the configuration (simple cycle has none; 1-on-1 uses DST-S10 or DST-S20; 2-on-1 uses DST-S20 or DST-S30). The customer needs 450 MW; the quoted configuration delivers 400 MW. The permit needs 10 ppm NOx; this configuration reaches 15 ppm. The other three are on screen.
    6. 
      
  6. The validator returned six 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 and against the stated total.
    7. 
      
  7. What this shows: for steam turbine that must fit the configuration, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the steam turbine to DST-S20 steam turbine, the power blocks to 2, the SCR to yes, the minimum load to 50 percent, the ramp to 30 MW per minute, the output stated on the quote to 800 MW and the stated list total to 418 million dollars.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. This time the validator clears it.
    12. 
      
  12. All six earlier findings are cleared.
    13. 
      
  13. Six 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.