Predictika · VRF HVAC system quotes

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

An AI sales agent prepares a quote that pairs an LG Multi V 5 outdoor unit with a list of indoor units. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published system rules and returns a verdict, every reason and the figures it computed.

Scope: LG Multi V 5 single-frame heat pump systems (ARUM072 to ARUM216 outdoor units) with ARNU indoor units: combination ratio, indoor unit count, stated capacity and the LATS line-sizing report. See everything this validator covers

This validator models Multi V 5 system quotes of this kind, not just the scenarios shown below.

  • Combination ratio — total indoor capacity must be between 50% and 130% of the outdoor unit's capacity, as LG's engineering manual states.
  • Indoor unit count — the most indoor units each outdoor model can connect (13 on the 6-ton unit up to 35 on the 18-ton unit).
  • Stated capacity and LATS — the capacity the quote states must equal what the listed indoor units give, and a quote without a LATS line-sizing report goes to a person, because LG requires LATS on all projects.

Any Multi V 5 system quote that touches these rules is in scope — not only the scenarios pictured here. Not covered: prices (LG does not publish VRF list prices, so this validator produces no price build-up or line-item quote), piping length and elevation limits (the manual points to LATS software for these), heat recovery and multi-frame systems, other LG product lines, and indoor unit types beyond the nine sizes modeled. Assumptions: indoor and outdoor capacities are the nominal Btu/h figures read from LG's public documents, and a LATS report on the quote is taken at its word.

The AI sales agentBuilds the system 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
Total indoor capacity within 50% to 130% of the outdoor unitOnly with care
The indoor units are separate lines; a rule has to roll up their capacities and compare the sum with the outdoor unit on the header, and the summing has to be kept in step with the model list.		The indoor units and the outdoor unit are in one request, and the ratio is computed and checked with the rest.
Most indoor units a given outdoor model can connectOnly with care
A product rule per outdoor model. It works, but each new model is another rule to maintain.		The limit is looked up from the outdoor model and checked together with the ratio.
A stated capacity that must equal the sum of the listed indoor unitsOnly with care
A stated figure is a free-entry field; a rule can compare it with a rolled-up total, but it has to be written and maintained per quote shape.		The stated capacity travels with the quote and is compared with the computed total 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 indoor units total 193,600 Btu/h, which is 134% of the 144,000 Btu/h outdoor unit, above the 130% maximum for the system combination ratio.
2The indoor units total 38,400 Btu/h, which is 40% of the 96,000 Btu/h outdoor unit, below the 50% minimum for the system combination ratio.
3The quote has 36 indoor units; this outdoor unit connects at most 35.
4The quote states 150,000 Btu/h of indoor capacity; the indoor units listed give 145,200 Btu/h.
5LG requires LATS software on all projects to ensure correct refrigerant line sizing and the quote has no LATS report; a person should confirm it before the quote goes out.

  

  

    
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. Eight indoor units on one outdoor unit: Eight indoor units on a 12-ton outdoor unit, with a wrong stated capacity

    
The agent's request. Please quote an LG Multi V 5 12-ton ARUM144 outdoor unit with 8 ARNU24 indoor units. The quote states 190,000 Btu/h of indoor capacity in total, and a LATS line-sizing report is attached. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Indoor capacity above 130% of the outdoor unit. The indoor units total 193,600 Btu/h, which is 134% of the 144,000 Btu/h outdoor unit, above the 130% maximum for the system combination ratio.
    • 
      
  • Stated indoor capacity does not match. The quote states 190,000 Btu/h of indoor capacity; the indoor units listed give 193,600 Btu/h.
    • 
    

    
2. Eight indoor units on one outdoor unit: The agent resubmits after fixing the errors

    
The agent's request. Please quote an LG Multi V 5 14-ton ARUM168 outdoor unit with 8 ARNU24 indoor units. The quote states 193,600 Btu/h of indoor capacity in total, and a LATS line-sizing report is attached. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 8 indoor unit(s) totaling 193,600 Btu/h on a 168,000 Btu/h outdoor unit, a combination ratio of 115%.
    • 
    

    
3. Many small indoor units: Forty small indoor units on the largest outdoor unit

    
The agent's request. Please quote an LG Multi V 5 18-ton ARUM216 outdoor unit with 40 ARNU07 indoor units. The quote states 300,000 Btu/h of indoor capacity in total, and a LATS line-sizing report is attached. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Indoor capacity above 130% of the outdoor unit. The indoor units total 300,000 Btu/h, which is 138% of the 216,000 Btu/h outdoor unit, above the 130% maximum for the system combination ratio.
    • 
      
  • Too many indoor units for this outdoor unit. The quote has 40 indoor units; this outdoor unit connects at most 35.
    • 
    

    
4. Many small indoor units: The agent resubmits after fixing the errors

    
The agent's request. Please quote an LG Multi V 5 18-ton ARUM216 outdoor unit with 36 ARNU07 indoor units. The quote states 270,000 Btu/h of indoor capacity in total, and a LATS line-sizing report is attached. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Too many indoor units for this outdoor unit. The quote has 36 indoor units; this outdoor unit connects at most 35.
    • 
    

    
5. Many small indoor units: The agent resubmits after fixing the errors

    
The agent's request. Please quote an LG Multi V 5 18-ton ARUM216 outdoor unit with 35 ARNU07 indoor units. The quote states 262,500 Btu/h of indoor capacity in total, and a LATS line-sizing report is attached. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 35 indoor unit(s) totaling 262,500 Btu/h on a 216,000 Btu/h outdoor unit, a combination ratio of 121%.
    • 
    

    
6. Mixed indoor units: Eleven mixed indoor units on a 14-ton outdoor unit

    
The agent's request. Please quote an LG Multi V 5 14-ton ARUM168 outdoor unit with 4 ARNU12, 4 ARNU18 and 3 ARNU24 indoor units. The quote states 198,200 Btu/h of indoor capacity in total. It is ready to send.

    
Verdict: Needs approval.

    
    
      
  • Refrigerant line-sizing report to confirm. LG requires LATS software on all projects to ensure correct refrigerant line sizing and the quote has no LATS report; a person should confirm it before the quote goes out.
    • 
      
  • Order summary. 11 indoor unit(s) totaling 198,200 Btu/h on a 168,000 Btu/h outdoor unit, a combination ratio of 117%.
    • 
    

    
7. Mixed indoor units: The agent resubmits after fixing the errors

    
The agent's request. Please quote an LG Multi V 5 14-ton ARUM168 outdoor unit with 4 ARNU12, 4 ARNU18 and 3 ARNU24 indoor units. The quote states 198,200 Btu/h of indoor capacity in total, and a LATS line-sizing report is attached. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. 11 indoor unit(s) totaling 198,200 Btu/h on a 168,000 Btu/h outdoor unit, a combination ratio of 117%.
    • 
    

  

  

    
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 that pairs an LG Multi V 5 outdoor unit with a list of indoor units. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published system rules 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 an LG Multi V 5 18-ton ARUM216 outdoor unit with 40 ARNU07 indoor units. The quote states 300,000 Btu/h of indoor capacity in total, and a LATS line-sizing report is attached. The rest of the request is on screen.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with two findings, all in one answer. The indoor units total 300,000 Btu/h, which is 138% of the 216,000 Btu/h outdoor unit, above the 130% maximum for the system combination ratio. The quote has 40 indoor units; this outdoor unit connects at most 35.
    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 total indoor capacity within 50% to 130% of the outdoor unit, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the ARNU07 indoor units to 36 and the stated indoor capacity to 270,000 Btu/h.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. Still blocked, with one finding, all in one answer. The quote has 36 indoor units; this outdoor unit connects at most 35.
    12. 
      
  12. One finding cleared. Still blocking: too many indoor units for this outdoor unit.
    13. 
      
  13. The agent resubmits once more.
    14. 
      
  14. The revised request. It changes the ARNU07 indoor units to 35 and the stated indoor capacity to 262,500 Btu/h.
    15. 
      
  15. It calls the validator once more.
    16. 
      
  16. This time the validator clears it.
    17. 
      
  17. The earlier finding is cleared, and the validator's figure matches the quote.
    18. 
      
  18. Two problems caught in one call, fixed in two passes, 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.
    19.