Predictika · Otis · New-installation elevators

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

An AI sales agent prepares an order quote for Otis new-installation elevators (Gen3 Core, Gen2 Premier, SkyWay and HydroFit, with Compass dispatch and OtisONE service), sold in US dollars. Before it goes out, the agent sends it to Predictika, which prices the order line by line, checks the total the agent states against its own, and returns a verdict, every reason and, for a quote that can proceed, the line-item quote itself.

Scope: New-installation elevator quotes for Otis Gen3 Core, Gen2 Premier, SkyWay and HydroFit. See everything this validator covers

This model covers order quotes for four elevator models with Compass destination dispatch and OtisONE service. It handles any case involving these, not just the scenarios shown on this page.

  • Model envelope — capacity, speed, rise and number of stops against each model's limits, and whether the model needs a machine room.
  • Code and building rules — a stretcher-size car for buildings with 4 or more stops, bed-size cars for hospitals, the fire service access elevator package above 120 ft of rise, the seismic package in seismic zones 3 and 4, Compass dispatch for groups of 3 or more cars, the IoT controller that OtisONE Premium needs, and the speed-versus-rise traffic guideline.
  • Pricing and approval — the price built up line by line (base car, landings, capacity, code packages, dispatch, discount, service), lead time against the need-by date, and discount authority by order size. The total the agent states is checked against the computed one.

Escalators, moving walks and other elevator brands are not covered. Prices, limits, lead times and discount limits are illustrative values.

The AI sales agentBuilds the elevator 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.

8 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 kinds of case. Rows a CPQ handles easily, such as plain option availability, are left out. It is a judgment about effort and reliability, not a claim that nothing can be built.

    
What the validator caughtTypical rules-based CPQPredictika
Capacity, speed, rise and stops limits that differ by model, with a machine room needed only on some modelsOnly with care
Limits held per model in lookup tables, one rule for each limit. Works, but every new model means new rows and rules.		The model envelope is checked in one pass on every call and every excess is reported.
Building-code items that depend on rise, stops and occupancy together (fire service access above 120 ft, stretcher and bed-size cars, seismic package)Only with care
Conditions spread over several rules, each tied to its own attribute. Doable, but easy to leave a gap.		All code items are evaluated together, whatever order the choices arrive in.
Compass dispatch needing a group of 3 or more cars, and OtisONE Premium needing a connected controllerOnly with care
Cross-attribute rules between the dispatch option, the car count and the model.		The dispatch, group size and model are checked together on every call.
Discount authority in tiers: a salesperson alone, an approver up to a cap that grows with the order value, a block aboveOnly with care
Thresholds in separate rules, one set for each order-size tier.		Salesperson limit, approver band and ceiling come out of one check.
A quote that states a total different from what the build givesOnly with workarounds
The stated total is rarely a field on the quote, so there is nothing to compare with the calculated one.		The stated total travels with the quote and is compared with the computed one 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.

    
1Capacity against the model maximum
2Speed against the model maximum
3Rise against the model maximum
4Stops against the model maximum
5Models that need a machine room
6Stretcher-size car (3500 lb or more) for buildings with 4 or more stops
7Bed-size cars (4500 lb or more) for hospitals
8Fire service access elevator package above 120 ft of rise
9Compass destination dispatch needs a group of 3 or more cars
10Seismic package in seismic zones 3 and 4
11OtisONE Premium needs an IoT-connected controller
12Speed below 2 fpm per ft of rise needs traffic-analysis sign-off (approval)
13Lead time against the need-by date
14Discount authority by order value (block above the maximum, approval above the salesperson limit)
15Price built up line by line (base car, landings, capacity, code packages, dispatch, discount, service)
16Stated total against the computed total

  

  

    
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. Machine room: SkyWay tower in a building with no machine room

    
The agent's request. Please quote 3 Otis SkyWay elevators for an office tower: 4,000 lb cars at 500 fpm, 240 ft of rise, 20 stops, with the fire service access elevator package, needed in 30 weeks. The quote states a total price of USD 984,000.00. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Machine room required. the Otis SkyWay needs a machine room and the building has none; use a machine-room-less Gen2 or Gen3.
    • 
    

    
2. Machine room: The agent resubmits after fixing the errors

    
The agent's request. Please quote 3 Otis SkyWay elevators for an office tower: 4,000 lb cars at 500 fpm, 240 ft of rise, 20 stops, with the fire service access elevator package, in a building that provides a machine room, needed in 30 weeks. The quote states a total price of USD 984,000.00. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Quote summary. Total price USD 984,000.00. Lead time 26 weeks.
    • 
    

    
3. Hospital cars: 4,000 lb cars for a hospital

    
The agent's request. Please quote 2 Otis Gen2 Premier elevators for a hospital: 4,000 lb cars at 200 fpm, 80 ft of rise, 6 stops, needed in 20 weeks. The quote states a total price of USD 243,600.00. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Bed-size cars needed for a hospital. hospital service needs bed-size cars of 4500 lb or more; quoted 4000 lb.
    • 
    

    
4. Hospital cars: The agent resubmits after fixing the errors

    
The agent's request. Please quote 2 Otis Gen2 Premier elevators for a hospital: 4,500 lb cars at 200 fpm, 80 ft of rise, 6 stops, needed in 20 weeks. The quote states a total price of USD 255,600.00. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Quote summary. Total price USD 255,600.00. Lead time 18 weeks.
    • 
    

    
5. Stated total: Stated total below the computed total

    
The agent's request. Please quote 4 Otis Gen2 Premier elevators for a hospital: 4,500 lb cars at 350 fpm, 170 ft of rise, 16 stops, with the fire service access elevator package, the seismic package for zone 3 or 4 and Compass destination dispatch, plus OtisONE Premium service for 5 years, needed in 24 weeks. The quote states a total price of USD 1,082,240.00. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Stated total does not match. the quote states a total of USD 1082240.0 but the validator computes USD 1139200.0.
    • 
    

    
6. Stated total: The agent resubmits after fixing the errors

    
The agent's request. Please quote 4 Otis Gen2 Premier elevators for a hospital: 4,500 lb cars at 350 fpm, 170 ft of rise, 16 stops, with the fire service access elevator package, the seismic package for zone 3 or 4 and Compass destination dispatch, plus OtisONE Premium service for 5 years, needed in 24 weeks. The quote states a total price of USD 1,139,200.00. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Quote summary. Total price USD 1,139,200.00. Lead time 18 weeks.
    • 
    

    
7. Discount authority: SkyWay tower at a 15 percent discount

    
The agent's request. Please quote 6 Otis SkyWay elevators for an office tower: 4,000 lb cars at 700 fpm, 320 ft of rise, 28 stops, with a machine room, the fire service access elevator package, Compass destination dispatch and OtisONE Premium service for 10 years, a 15 percent discount, needed in 30 weeks. The quote states a total price of USD 2,410,500.00. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Discount above the maximum. 15 percent discount exceeds the 12 percent maximum for a USD 2370000.0 order.
    • 
    

    
8. Discount authority: The agent resubmits after fixing the errors

    
The agent's request. Please quote 6 Otis SkyWay elevators for an office tower: 4,000 lb cars at 700 fpm, 320 ft of rise, 28 stops, with a machine room, the fire service access elevator package, Compass destination dispatch and OtisONE Premium service for 10 years, a 10 percent discount, needed in 30 weeks. The quote states a total price of USD 2,529,000.00. It is ready to send.

    
Verdict: Needs approval.

    
    
      
  • Approval for the discount. 10 percent discount is above the 3 percent rep authority; approvable up to 12 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 an order quote for Otis new-installation elevators (Gen3 Core, Gen2 Premier, SkyWay and HydroFit, with Compass dispatch and OtisONE service), sold in US dollars. Before it goes out, the agent sends it to Predictika, which prices the order line by line, checks the total the agent states against its own, and returns a verdict, every reason and, for a quote that can proceed, the line-item quote itself.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Please quote 3 Otis SkyWay elevators for an office tower: 4,000 lb cars at 500 fpm, 240 ft of rise. The quote states a total price of USD 984,000.00. 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 Otis SkyWay needs a machine room and the building has none; use a machine-room-less Gen2 or Gen3.
    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 capacity, speed, rise and stops limits that differ by model, with a machine room needed only on some models, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request.
    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 Otis SkyWay and Landings beyond the first two; the other two lines are on screen.
    13. 
      
  13. The earlier finding is cleared, and the validator's total, USD 984,000.00, 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.