Predictika · Metasys building automation: network engines, field controllers, licenses, Modbus integration and service (EUR)

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

An AI sales agent prepares a Metasys building automation quote for a fictional customer. Before it goes out, the agent sends it to Predictika’s validator, which checks it against the engine, controller, license, service and discount rules, compares the device count and total the agent states with the ones it computes, and returns a verdict with every reason.

Scope: Metasys building automation quotes for the SNE network engine, CGM/FAC/VMA controller and Metasys Server line (EU project, EUR). See everything this validator covers

This validator models Metasys building automation quotes for new installations in the style of Johnson Controls Metasys: network engines, field controllers, VAV boxes, Modbus devices, licenses, service, lead time and discounts. It handles any quote made of these products and terms, not just the scenarios shown below.

  • Network engines and field controllers — SNE110L, SNE11000 and SNE22000 network engines paired with CGM and FAC field controllers, sized from the points, the spare capacity, the VAV boxes, the MS/TP trunks and the devices each engine supports.
  • VAV, Modbus and licensing — A VMA controller for each VAV box, Modbus device integration (not available on the SNE110L), and Metasys Server object-count licensing and engine object capacity checked against the objects the project creates.
  • Service, delivery and discount — Planned service with optional OpenBlue remote monitoring (which needs the customer's cloud access) for 1 to 5 years, lead time against the delivery date, discount authority that rises with order value, and a check that the device count and total the agent states match the validator's own.

It does not cover other Johnson Controls product lines (fire, security, chillers), non-Metasys building automation vendors, real list prices, installation labor, or tax and multi-currency quoting.

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
Chained sizing from points to enginesOnly with workarounds
Points with spare capacity become controllers, devices, trunks and objects, each checked against an engine limit. In a rules-based CPQ that is custom code or one rule per combination.		Each step is a computed quantity, and every limit is checked together on every call.
Modbus and remote monitoring prerequisitesOnly with care
Product rules can hide an option on one engine, but a customer-network prerequisite usually needs a separate validation rule.		The engine property and the customer fact are checked against the quote on every call.
Discount authority by order valueOnly with care
Approval tiers that move with order value are doable, but they interact with price rules and the approval flow.		The limit, the approval band and the order value are evaluated together.
Lead time against the delivery dateOnly with workarounds
A lead time that grows with the device count is a computed value that price and validation rules rarely share.		Lead time is derived from the same device count and compared with the date asked for.
The figures the agent statesOnly with workarounds
Comparing a stated device count or total with a computed one means a rule per quote layout, and price rules rarely run on stated figures.		The stated device count and total are fields in the request and are checked against the computed values.
Every problem in one answerOnly with workarounds
Rules tend to fire as the quote is saved, 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
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
Network trunksblockTrunks needed = devices / 50, compared with the trunks the engines provide.
Field device capacityblockField devices (controllers plus one per VAV box) compared with the devices the engines support.
Engine nearly fullneeds approvalMore than 90 percent of the engines' device capacity needs systems-engineering approval.
Engine object capacityblockObjects (spared points, 8 per VAV box, 20 per Modbus device) compared with the engines' object capacity.
License sizeblockObjects compared with the Metasys Server license size.
Modbus supportblockModbus integration is not available on the SNE110L.
Customer cloud accessblockOpenBlue remote monitoring needs the customer's outbound cloud connectivity.
Service termblockA planned service term must be 1 to 5 years.
Delivery dateblockEngine lead time (plus 4 weeks above 500 devices) compared with the delivery date.
Spare capacityneeds approvalSpare point capacity below 10 percent needs branch-manager approval.
Discount authorityblock / needs approvalAbove 8 percent needs approval; above 15 percent (22 percent on EUR 150,000 or more) is blocked.
Stated device countblockThe device count the agent states must equal the validator's.
Stated totalblockThe total the agent states must be within EUR 1 of the validator's 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. Network capacity: Two engines

    
The agent's request. A Metasys system for the office tower: 2 Metasys SNE22000 network engines, 58 CGM09090 general purpose controllers and 150 VAV box controllers for 1,200 points with 15 percent spare capacity, a Metasys Server license for 5,000 objects, 20 graphics screens, a planned service agreement for 3 years and a 5 percent discount. 208 field devices. Total EUR 194,633.00. Delivery in 12 weeks. Ready to send.

    
Verdict: Blocked.

    
    
      
  • Not enough network trunks. 208 field devices need 5 MS/TP trunks; 2 x Metasys SNE22000 network engine provide 4.
    • 
    

    
2. Network capacity: Three engines

    
The agent's request. A Metasys system for the office tower: 3 Metasys SNE22000 network engines, 58 CGM09090 general purpose controllers and 150 VAV box controllers for 1,200 points with 15 percent spare capacity, a Metasys Server license for 5,000 objects, 20 graphics screens, a planned service agreement for 3 years and a 5 percent discount. 208 field devices. Total EUR 202,016.00. Delivery in 12 weeks. Ready to send.

    
Verdict: Allowed.

    
3. Remote monitoring: Remote monitoring, 5 years

    
The agent's request. A Metasys system for the lab building: 2 Metasys SNE11000 network engines, 37 FAC4911 advanced application controllers and 60 VAV box controllers for 800 points with 20 percent spare capacity, 20 Modbus devices integrated, a Metasys Server license for 5,000 objects, 15 graphics screens, planned service with OpenBlue remote monitoring for 5 years and an 8 percent discount. 97 field devices. Total EUR 136,170.30. Delivery in 10 weeks. Ready to send.

    
Verdict: Blocked.

    
    
      
  • Customer cloud access not confirmed. OpenBlue remote monitoring needs outbound cloud connectivity, which the customer has not allowed.
    • 
    

    
4. Remote monitoring: Cloud access confirmed

    
The agent's request. A Metasys system for the lab building: 2 Metasys SNE11000 network engines, 37 FAC4911 advanced application controllers and 60 VAV box controllers for 800 points with 20 percent spare capacity, 20 Modbus devices integrated, a Metasys Server license for 5,000 objects, 15 graphics screens, planned service with OpenBlue remote monitoring for 5 years and an 8 percent discount. The customer's IT has confirmed outbound cloud access. 97 field devices. Total EUR 136,170.30. Delivery in 10 weeks. Ready to send.

    
Verdict: Allowed.

    
5. Delivery time and discount: Hospital campus, 8 weeks, 30 percent

    
The agent's request. A Metasys system for the hospital campus: 8 Metasys SNE22000 network engines, 275 CGM09090 general purpose controllers and 400 VAV box controllers for 6,000 points with standard spare capacity, a Metasys Server license for 10,000 objects, 40 graphics screens and a 30 percent discount. 675 field devices. Total EUR 435,277.50. Delivery in 8 weeks. Ready to send.

    
Verdict: Blocked.

    
    
      
  • Delivery date cannot be met. Lead time is about 10 weeks; the project needs delivery in 8.
    • 
      
  • Discount above the limit. 30 percent discount exceeds the 22 percent that can be approved on EUR 621825.0.
    • 
    

    
6. Delivery time and discount: Hospital campus, 12 weeks, 20 percent

    
The agent's request. A Metasys system for the hospital campus: 8 Metasys SNE22000 network engines, 275 CGM09090 general purpose controllers and 400 VAV box controllers for 6,000 points with standard spare capacity, a Metasys Server license for 10,000 objects, 40 graphics screens and a 20 percent discount. 675 field devices. Total EUR 497,460.00. Delivery in 12 weeks. Ready to send.

    
Verdict: Needs approval.

    
    
      
  • Discount needs approval. 20 percent discount is above the 8 percent a sales engineer can give; approvable up to 22 percent.
    • 
    

    
7. The total the agent states: Stated total below computed

    
The agent's request. A Metasys system for the regional office: 1 Metasys SNE11000 network engine, 23 CGM09090 general purpose controllers and 20 VAV box controllers for 500 points with standard spare capacity, a Metasys Server license for 5,000 objects, 6 graphics screens, a planned service agreement for 3 years and a 5 percent discount. 43 field devices. Total EUR 47,903.75. Delivery in 8 weeks. Ready to send.

    
Verdict: Blocked.

    
    
      
  • Stated total does not match. The agent states a total of EUR 47903.75; the validator computes EUR 53954.75.
    • 
    

  

  

    
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 Metasys building automation quote for a fictional customer. Before it goes out, the agent sends it to Predictika’s validator, which checks it against the engine, controller, license, service and discount rules, compares the device count and total the agent states with the ones it computes, and returns a verdict with every reason.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. A Metasys system for the office tower: 2 Metasys SNE22000 network engines, 58 CGM09090 general purpose controllers and 150 VAV box controllers for 1,200 points with 15 percent spare capacity. Total EUR 194,633.00. 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. 208 field devices need 5 MS/TP trunks; 2 x Metasys SNE22000 network engine provide 4.
    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 chained sizing from points to engines, a rules-based CPQ can do this only with workarounds.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the Engines Quantity to 3 and the stated total as to 202,016 EUR.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. This time the validator clears it.
    12. 
      
  12. The earlier finding is cleared, and the validator's total, ['Total', 'EUR 202,016.00', 'EUR 202,016.00'], matches the quote.
    13. 
      
  13. 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.
    14.