Predictika · Airbus A321neo family orders

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

An AI sales agent drafts a quote for an airline order of Airbus A321neo family aircraft: the A321neo, A321LR or A321XLR, with a chosen takeoff weight, extra fuel tanks, cabin layout, galley, ETOPS package, engine, delivery year and discount. Before the quote goes out, the agent sends it to Predictika, which checks it against a declarative model, compares the range and net total the agent states with the ones it computes, and returns every finding together with the line-item quote.

Scope: Airbus A321neo, A321LR and A321XLR airline orders: weight, tanks, range, cabin, engine, slots and discounts. See everything this validator covers

This validator covers airline orders for the Airbus A321neo family only: the A321neo, A321LR and A321XLR narrowbody variants. It does not cover other Airbus aircraft families (A220, A330, A350), the A320neo or A319neo, or other manufacturers' aircraft.

  • Airframe and range — the takeoff weight each variant can take, additional center tanks and the weight they need, the range the configuration reaches, the long-range galley required for missions over 3,500 nm and the ETOPS package required for missions over 3,000 nm.
  • Cabin and exits — seat count against the exit configuration limit (all exits active, door 3 deactivated, overwing only) and against cabin capacity once the long-range galley takes space.
  • Engine and delivery — the Pratt and Whitney PW1100G-JM certification year on the A321XLR, the earliest open delivery slot for each variant, and the 20-aircraft-per-customer-per-year allocation.
  • Commercial terms — price escalation by delivery year, priced options (tanks, takeoff weight, galley, ETOPS), sales discount authority and the higher volume ceiling at 50 aircraft or more, and the range and net total the agent states.

Any A321neo, A321LR or A321XLR order that combines these variants, engines, weights, tanks, cabins and discounts runs through this validator, not just the seven scenarios shown on this page. It is an illustrative model built from public information about the aircraft family; prices, range increments, slots, allocations and discount limits are fictional, and it does not use Airbus' internal rules.

The AI sales agentBuilds the aircraft 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 4 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
Range computed from variant, takeoff weight and extra tanks, then compared with the mission, with galley and ETOPS requirements that switch on by mission lengthOnly with care
Range is a calculated field that has to be rebuilt for each variant and kept in step with the weight and tank options; the 3,000 and 3,500 nm thresholds are separate rules.		Range is computed on every call from the variant, weight and tanks, and every threshold is checked in the same pass.
An engine that is only certified from a given year on one variant, so the delivery year decides block, approval or clearOnly with workarounds
A date-dependent rule tied to one engine and one variant, with an approval step in the certification year; it is usually a hand-written exception that is easy to miss when the delivery year changes.		Certification year, delivery year and slot are data; the block and the approval come from the same model.
Yearly allocation per customer against order size and delivery span, plus a volume discount ceiling at 50 aircraftOnly with care
Needs the span as an input and the allocation as a rule; the higher discount ceiling for large orders is another threshold to maintain.		Allocation, span and the volume ceiling are checked together with the discount and the slot.
A stated range or net total that does not match the computed figuresOnly with workarounds
A validation rule can compare a stated figure with a calculated one only if the stated figure is a field on the quote, which it rarely is.		The stated range and net total travel with the quote and are compared with the computed ones on every call.

  

  

    
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.

    
1Takeoff weight outside the range the variant can take.
2More additional center tanks than the variant allows.
3Additional center tanks on a takeoff weight below 97 t.
4Mission longer than the range the configuration reaches.
5More seats than the exit configuration allows.
6More seats than the cabin holds with the long-range galley.
7Mission over 3,500 nm without the long-range galley.
8Mission over 3,000 nm without the ETOPS package.
9PW1100G-JM on the A321XLR delivered before its certification year (block) or in it (approval).
10Delivery earlier than the earliest open slot for the variant.
11More than 20 aircraft per customer per year.
12Discount above the maximum (50 percent, or 55 percent for 50 aircraft or more).
13Discount above the 40 percent sales may give alone (approval).
14The agent's stated net total does not match the computed total.
15The agent's stated range does not match the computed range.
16Price escalation, priced options and the line-item quote are computed on every call.

  

  

    
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. Mission range and variant: A321LR order for a 4,200 nm mission

    
The agent's request. Please quote 12 Airbus A321LR aircraft with CFM LEAP-1A engines for Northwind Air, delivered in 2031. Each aircraft has a 97 t maximum takeoff weight, one additional center tank, the long-range galley, the ETOPS package, 180 seats and the Cabin Flex layout with all exits active, and must fly a 4,200 nm mission. The discount is 30 percent. The quote states a range of 4,200 nm and a net total of $1,403.64 million. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Mission is beyond the range. The mission needs 4,200 nm but this configuration reaches 3,690 nm.
    • 
      
  • Stated range does not match. Stated range does not match: the agent stated 4,200 nm; the validator computes 3,690 nm.
    • 
    

    
2. Mission range and variant: The agent resubmits after fixing the errors

    
The agent's request. Please quote 12 Airbus A321XLR aircraft with CFM LEAP-1A engines for Northwind Air, delivered in 2031. Each aircraft has a 101 t maximum takeoff weight, one additional center tank, the long-range galley, the ETOPS package, 180 seats and the Cabin Flex layout with all exits active, and must fly a 4,200 nm mission. The discount is 30 percent. The quote states a range of 4,690 nm and a net total of $1,466.64 million. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Quote summary. Net total $1,466.64 million: aircraft $2,042.40 million; options $14.40 million; options $21.60 million; options $9.60 million; options $7.20 million; discount -$628.56 million.
    • 
    

    
3. Cabin exits and seats: A321neo order with door 3 deactivated

    
The agent's request. Please quote 15 Airbus A321neo aircraft with CFM LEAP-1A engines for Sunridge Airlines, delivered in 2031. Each aircraft has a 95 t maximum takeoff weight, standard galley and 230 seats in the Cabin Flex layout with door 3 deactivated, and must fly a 2,800 nm mission. The discount is 28 percent. The quote states a range of 3,320 nm and a net total of $1,611.90 million. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • More seats than the exits allow. 230 seats exceed the 220 seat limit of the Cabin Flex with door 3 deactivated exit configuration.
    • 
    

    
4. Cabin exits and seats: The agent resubmits after fixing the errors

    
The agent's request. Please quote 15 Airbus A321neo aircraft with CFM LEAP-1A engines for Sunridge Airlines, delivered in 2031. Each aircraft has a 95 t maximum takeoff weight, standard galley and 220 seats in the Cabin Flex layout with door 3 deactivated, and must fly a 2,800 nm mission. The discount is 28 percent. The quote states a range of 3,320 nm and a net total of $1,611.90 million. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Quote summary. Net total $1,611.90 million: aircraft $2,225.25 million; options $13.50 million; discount -$626.85 million.
    • 
    

    
5. Engine certification: A321XLR order with the PW1100G-JM engine for 2030

    
The agent's request. Please quote 10 Airbus A321XLR aircraft with Pratt and Whitney PW1100G-JM engines for Karakoram Airways, delivered in 2030. Each aircraft has a 101 t maximum takeoff weight, one additional center tank, the long-range galley, the ETOPS package and 190 seats in the Cabin Flex layout with all exits active, and must fly a 4,300 nm mission. The discount is 30 percent. The quote states a range of 4,690 nm and a net total of $1,191.12 million. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Engine not certified for the delivery year. The Pratt and Whitney PW1100G-JM is not certified on the A321XLR until 2031; a 2030 delivery cannot be committed.
    • 
    

    
6. Engine certification: The agent resubmits after fixing the errors

    
The agent's request. Please quote 10 Airbus A321XLR aircraft with Pratt and Whitney PW1100G-JM engines for Karakoram Airways, delivered in 2031. Each aircraft has a 101 t maximum takeoff weight, one additional center tank, the long-range galley, the ETOPS package and 190 seats in the Cabin Flex layout with all exits active, and must fly a 4,300 nm mission. The discount is 30 percent. The quote states a range of 4,690 nm and a net total of $1,222.20 million. It is ready to send.

    
Verdict: Needs approval.

    
    
      
  • Engine certification risk. PW1100G-JM certification on the A321XLR is expected in 2031, the delivery year; certification-risk terms are required.
    • 
      
  • Quote summary. Net total $1,222.20 million: aircraft $1,702.00 million; options $12.00 million; options $18.00 million; options $8.00 million; options $6.00 million; discount -$523.80 million.
    • 
    

    
7. Stated total: Large A321neo order with a stated total

    
The agent's request. Please quote 20 Airbus A321neo aircraft with CFM LEAP-1A engines for Coastline Air, delivered in 2031. Each aircraft has a 97 t maximum takeoff weight, standard galley and 220 seats in the Cabin Flex layout with all exits active, and must fly a 2,800 nm mission. The discount is 38 percent. The quote states a range of 3,360 nm and a net total of $1,830.42 million. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Stated total does not match. Stated total does not match: the agent stated $1,830.42 million; the validator computes $1,854.42 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 drafts a quote for an airline order of Airbus A321neo family aircraft: the A321neo, A321LR or A321XLR. Before the quote goes out, the agent sends it to Predictika, which checks it against a declarative model, compares the range and net total the agent states with the ones it computes, and returns every finding together with the line-item quote.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Please quote 12 Airbus A321LR aircraft with CFM LEAP-1A engines for Northwind Air, delivered in 2031. Each aircraft has a 97 t maximum takeoff weight, one additional center tank, the long-range galley, the ETOPS package, 180 seats and the Cabin Flex layout with all exits active. The rest of the request is on screen. The quote states a range of 4,200 nm and a net total of $1,403.64 million.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with two findings, all in one answer. The mission needs 4,200 nm but this configuration reaches 3,690 nm. Stated range does not match: the agent stated 4,200 nm; the validator computes 3,690 nm.
    6. 
      
  6. The validator returned two 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 a stated range or net total that does not match the computed figures, a rules-based CPQ can do this only with workarounds.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the aircraft variant to A321XLR, the maximum takeoff weight to 101 t, the stated range to 4,690 nm and the stated net total to 1,466.64 million dollars.
    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. It starts with A321XLR with CFM LEAP-1A engines and Additional center tank; the other four lines are on screen.
    13. 
      
  13. Both earlier findings are cleared, and the validator's total, $1,466.64M, matches the quote.
    14. 
      
  14. Two 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.
    15.