Predictika · PEM electrolyzer plant quotes

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

An AI sales agent prepares a quote for a Nel MC Series containerized PEM hydrogen plant for an industrial customer: the model, the number of plants, delivery pressure, purity and the site conditions it was given. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published Nel MC Series data sheet and returns a verdict, every reason and the figures it computed.

Scope: Nel MC Series modular PEM plants (MC1000, MC2000, MC4000): hydrogen production, purity and high purity dryer, delivery pressure, site conditions and utilities. See everything this validator covers

This validator models quotes for the Nel MC Series modular PEM electrolyzer plants (MC1000 at 5 MW, MC2000 at 10 MW, MC4000 at 20 MW), as published in the Nel MC Series Modular Plants data sheet (PD-0600-0145 Rev A). It handles any quote for these plants, not just the scenarios shown below.

  • Production — the nominal rate is 984, 1,968 and 3,936 Nm3/h for the three models (2,124, 4,248 and 8,496 kg per 24 h); the hydrogen the customer needs and the production the agent states must agree with the number of plants quoted.
  • Purity and pressure — standard purity is 99.95%, and 99.999+% needs the optional high purity dryer; the nominal delivery pressure is 30 barg, and any other pressure goes to a person.
  • Site and utilities — ambient temperature from -30 to 40 degrees C, altitude up to 2,000 m, medium voltage 4.16 to 35 kV, potable feed water at 5 to 35 degrees C and 2.7 to 4.8 barg, and a site area at least the footprint of one plant (315, 561 and 1,053 m2). The data sheet gives the footprint per plant, so a site that does not cover several plants at that figure goes to a person.

Any quote for these plants that touches these rules is in scope — not only the scenarios pictured here. Not covered: prices (Nel publishes none, so this validator produces no price build-up or line-item quote), the turndown range, ramp rates, water quality analysis, other Nel electrolyzer lines (alkaline, containerized MC250 and MC500, PEM 100) and compression or storage.

The AI sales agentBuilds the plant 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.

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
Site limits that depend on the plantOnly with care
Ambient range, altitude, voltage, water temperature and water pressure each need their own rule against a site record; it works, but every site attribute is another rule to maintain.		The site conditions travel with the quote and every limit is checked on every call, with the reason for each failure.
Production the agent states against the plants quotedOnly with care
A stated figure is a free-entry field; a rule can compare it with plants times rate, but someone has to write and maintain that comparison.		The stated figure travels with the quote and is compared with the computed figure on every call.
Footprint that grows with the number of plantsOnly with workarounds
The area check depends on the chosen model and the plant count, which means derived values the product rules were not built to hold.		The footprint is looked up from the model and compared with the site area in the same answer; a site that cannot hold every plant at that figure goes to a person.
A pressure other than nominal that a person must confirmOnly with workarounds
Approval routing has to be built as a separate flow and kept in step with the product rules.		The quote comes back as needs approval with the reason, in the same answer as every other finding.

  

  

    
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 customer needs 1000 Nm3/h of hydrogen; the quoted plant produces 984 Nm3/h at nominal rate.
2The quote states a production of 2000 Nm3/h; the quoted plant gives 1968 Nm3/h.
3The customer needs 99.999+% purity hydrogen; the standard plant gives 99.95% and the high purity dryer is not on the quote.
4The site ambient temperature range is -35 to 30 degrees C; the plant is rated for -30 to 40 degrees C.
5The site ambient temperature range is 5 to 45 degrees C; the plant is rated for -30 to 40 degrees C.
6The site altitude is 2400 m; the plant is rated from sea level to 2,000 m.
7The site medium voltage is 3.3 kV; the plant takes 4.16 to 35 kV three phase.
8The potable feed water is at 40 degrees C; the plant needs 5 to 35 degrees C.
9The potable feed water pressure is 5.5 barg; the plant needs 2.7 to 4.8 barg.
10The site has 900 m2 available; one quoted plant needs 1053 m2 of footprint.
11The data sheet gives a footprint of 1053 m2 for one plant; the site has 1500 m2, which does not cover 2 plants at that figure, so a person should confirm the site layout for several plants.
12The data sheet gives a nominal delivery pressure of 30 barg; a person should confirm that 45 barg can be supplied.
13The customer needs 2500 Nm3/h of hydrogen; the quoted plant produces 1968 Nm3/h at nominal rate.

  

  

    
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. Cold-site plant: An MC1000 for 1,200 Nm3/h at a site that falls to -35 degrees C

    
The agent's request. Please quote one Nel MC1000 PEM electrolyzer plant for a customer that needs 1200 Nm3/h of hydrogen at a site with 600 square meters available, an ambient range of -35 to 30 degrees C, delivered at 30 barg. The quote states a production of 1200 Nm3/h. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Hydrogen needed exceeds the plant. The customer needs 1200 Nm3/h of hydrogen; the quoted plant produces 984 Nm3/h at nominal rate.
    • 
      
  • Stated production does not match. The quote states a production of 1200 Nm3/h; the quoted plant gives 984 Nm3/h.
    • 
      
  • Ambient temperature outside the plant range. The site ambient temperature range is -35 to 30 degrees C; the plant is rated for -30 to 40 degrees C.
    • 
    

    
2. Cold-site plant: The agent resubmits after fixing the errors

    
The agent's request. Please quote one Nel MC2000 PEM electrolyzer plant for a customer that needs 1200 Nm3/h of hydrogen at a site with 600 square meters available, an ambient range of -25 to 30 degrees C, delivered at 30 barg. The quote states a production of 1968 Nm3/h. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Quote summary. 1 Nel MC2000 plant(s) producing 1968 Nm3/h (4248 kg per 24 h) of hydrogen at nominal rate.
    • 
    

    
3. High purity plant: An MC2000 with 99.999+% purity at 45 barg

    
The agent's request. Please quote one Nel MC2000 PEM electrolyzer plant for a customer that needs 1800 Nm3/h of hydrogen at a site with 1000 square meters available, an ambient range of 5 to 30 degrees C, delivered at 45 barg, with 99.999+% purity. The quote states a production of 1968 Nm3/h. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • High purity needs the optional dryer. The customer needs 99.999+% purity hydrogen; the standard plant gives 99.95% and the high purity dryer is not on the quote.
    • 
      
  • Delivery pressure other than nominal. The data sheet gives a nominal delivery pressure of 30 barg; a person should confirm that 45 barg can be supplied.
    • 
    

    
4. High purity plant: The agent resubmits after fixing the errors

    
The agent's request. Please quote one Nel MC2000 PEM electrolyzer plant for a customer that needs 1800 Nm3/h of hydrogen at a site with 1000 square meters available, an ambient range of 5 to 30 degrees C, delivered at 45 barg, with 99.999+% purity and the high purity dryer. The quote states a production of 1968 Nm3/h. It is ready to send.

    
Verdict: Needs approval.

    
    
      
  • Delivery pressure other than nominal. The data sheet gives a nominal delivery pressure of 30 barg; a person should confirm that 45 barg can be supplied.
    • 
      
  • Quote summary. 1 Nel MC2000 plant(s) producing 1968 Nm3/h (4248 kg per 24 h) of hydrogen at nominal rate.
    • 
    

    
5. High purity plant: The agent resubmits after fixing the errors

    
The agent's request. Please quote one Nel MC2000 PEM electrolyzer plant for a customer that needs 1800 Nm3/h of hydrogen at a site with 1000 square meters available, an ambient range of 5 to 30 degrees C, delivered at 30 barg, with 99.999+% purity and the high purity dryer. The quote states a production of 1968 Nm3/h. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Quote summary. 1 Nel MC2000 plant(s) producing 1968 Nm3/h (4248 kg per 24 h) of hydrogen at nominal rate.
    • 
    

    
6. Large plant order: A single MC4000 for 4,500 Nm3/h

    
The agent's request. Please quote one Nel MC4000 PEM electrolyzer plant for a customer that needs 4500 Nm3/h of hydrogen at a site with 2500 square meters available, an ambient range of 5 to 30 degrees C, delivered at 30 barg. The quote states a production of 4500 Nm3/h. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Hydrogen needed exceeds the plant. The customer needs 4500 Nm3/h of hydrogen; the quoted plant produces 3936 Nm3/h at nominal rate.
    • 
      
  • Stated production does not match. The quote states a production of 4500 Nm3/h; the quoted plant gives 3936 Nm3/h.
    • 
    

    
7. Large plant order: The agent resubmits after fixing the errors

    
The agent's request. Please quote two Nel MC4000 PEM electrolyzer plants for a customer that needs 4500 Nm3/h of hydrogen at a site with 2500 square meters available, an ambient range of 5 to 30 degrees C, delivered at 30 barg. The quote states a production of 7872 Nm3/h. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Quote summary. 2 Nel MC4000 plant(s) producing 7872 Nm3/h (16992 kg per 24 h) of hydrogen at nominal rate.
    • 
    

  

  

    
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 Nel MC Series containerized PEM hydrogen plant for an industrial customer: the model, the number of plants, delivery pressure, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published Nel MC Series data sheet 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 one Nel MC1000 PEM electrolyzer plant for a customer that needs 1200 Nm3/h of hydrogen at a site. The quote states a production of 1200 Nm3/h. 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. The customer needs 1200 Nm3/h of hydrogen; the quoted plant produces 984 Nm3/h at nominal rate. The quote states a production of 1200 Nm3/h; the quoted plant gives 984 Nm3/h. The site ambient temperature range is -35 to 30 degrees C; the plant is rated for -30 to 40 degrees C.
    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 production the agent states against the plants quoted, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the model to Nel MC2000, the site ambient minimum to -25 C and the stated production to 1,968.
    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.