Predictika · Facility management platform subscription quotes

An AI sales agent's SMART FM 360 subscription quote, checked before it goes out

An AI sales agent prepares an annual subscription quote for a facility management platform: a plan, the number of sites, assets and users, modules such as helpdesk, client portal, IoT connector, predictive maintenance, Energy Management package and ESG reporting, a discount and a stated total. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of these quotes and returns a verdict, every reason and the total it computed.

Scope: Annual subscription quotes for a SMART FM 360 style facility management platform: plan limits, module dependencies, discount and the stated total. See everything this validator covers

This validator models SMART FM 360 subscription quotes, not just the scenarios shown below.

  • Plans and limits — Essential, Advanced and Premium, with the assets and users each plan allows and the IoT connector and predictive maintenance reserved for the higher plans.
  • Module dependencies — sensor points, predictive maintenance and the Energy Management package need the IoT connector, ESG reporting needs the Energy Management package, and the client portal needs the helpdesk.
  • Discount, migration and stated total — a discount over 25 percent blocked and one between 10 and 25 percent sent to a sales manager, data migration scoped by a delivery lead, and the stated total compared with the computed total.

Any SMART FM 360 subscription quote that touches these rules is in scope — not only the scenarios pictured here. Not covered: other SPIE services and products. Public versus modeled: the SMART FM 360 name, its helpdesk and request tracking, interconnection with building tools, predictive maintenance and the Energy Management package come from SPIE's public pages; plan names and limits, module dependencies, thresholds and every price are modeled by Predictika from comparable platforms, are illustrative and are not published by SPIE.

The AI sales agentBuilds the subscription 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.

6 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
A module that depends on another moduleOnly with care
Predictive maintenance, the Energy Management package and sensor points all need the IoT connector, and ESG reporting needs the Energy Management package, so the dependencies form a chain that each needs its own rule.		Every module is a field of one quote and the whole chain is checked on every call.
Limits that depend on the planOnly with care
Assets, users and the modules a plan can include differ by plan, so the rules form a table that must be kept in step with the plans.		Plan, assets, users and modules are fields of one quote and are compared on every call.
A stated total that must match the computed totalOnly with workarounds
The total is built from site fees, assets, users, sensor points, modules and discount, so a separate rule is needed to recompute it and compare it with the stated figure.		The stated total is a field of the request and is compared with the computed total on every call.
Discounts and migration that go to a personOnly with care
Separate approval paths with their own thresholds that must not overlap the blocking rules.		Blocks and approvals come back together; an approval-only quote is not blocked.

  

  

    
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 quote registers 2,001 assets; the selected plan allows at most 2,000.
2The quote has 26 users; the selected plan allows at most 25.
3The IoT connector is quoted but the building has no connectable building management system or sensors.
4The IoT connector is not available on the Essential plan in this model.
5The quote lists 200 sensor points but no IoT connector.
6Predictive maintenance needs equipment data from the IoT connector, which is not quoted.
7Predictive maintenance is not available on the Essential plan in this model.
8The Energy Management package needs energy data from the IoT connector, which is not quoted.
9ESG reporting builds on the Energy Management package, which is not quoted.
10The client portal shows request tracking; the quote has no helpdesk module.
11The discount of 4,671 is between 10 and 25 percent of the subtotal of 46,700; a sales manager must approve it.
12The discount of 11,675 is between 10 and 25 percent of the subtotal of 46,700; a sales manager must approve it.
13The discount of 11,676 is more than 25 percent of the subtotal of 46,700.
14The quote states a total of 1; the quoted items add up to 46,700.
15The quote includes migration of data from the customer current maintenance system; a delivery lead should scope it first.
16The quote covers no site; at least one site is needed.
17The quote registers 3,000 assets; the selected plan allows at most 2,000.
18The quote states a total of 1; the quoted items add up to 32,700.

  

  

    
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. Essential plan with several modules: An Essential plan for 3,000 assets with the client portal, predictive maintenance, ESG reporting and 100 sensor points

    
The agent's request. Please quote a SMART FM 360 Essential plan subscription for 1 site, 3,000 assets and 20 users, for office sites, with the client portal, predictive maintenance, ESG reporting and 100 sensor points, for a stated annual total of 29,200 euros. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Assets over the plan limit. The quote registers 3,000 assets; the selected plan allows at most 2,000.
    • 
      
  • Sensor points need the IoT connector. The quote lists 100 sensor points but no IoT connector.
    • 
      
  • Predictive maintenance needs IoT data. Predictive maintenance needs equipment data from the IoT connector, which is not quoted.
    • 
      
  • Predictive maintenance needs Advanced or Premium. Predictive maintenance is not available on the Essential plan in this model.
    • 
      
  • ESG reporting needs the Energy Management package. ESG reporting builds on the Energy Management package, which is not quoted.
    • 
      
  • Client portal needs request tracking. The client portal shows request tracking; the quote has no helpdesk module.
    • 
    

    
2. Essential plan with several modules: The agent resubmits after fixing the errors

    
The agent's request. Please quote a SMART FM 360 Advanced plan subscription for 1 site, 3,000 assets and 20 users, for office sites, with the helpdesk, the client portal, predictive maintenance, the Energy Management package, ESG reporting and the IoT connector with 100 sensor points, for a stated annual total of 47,200 euros. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Quote summary. 1 site(s), 3,000 assets, 20 users; subtotal 47200, net total 47,200 (illustrative prices).
    • 
    

    
3. IoT connector and predictive maintenance: An Essential plan with the IoT connector and predictive maintenance for two sites

    
The agent's request. Please quote a SMART FM 360 Essential plan subscription for 2 sites, 1,000 assets and 20 users, for office sites, with the helpdesk, predictive maintenance and the IoT connector with 100 sensor points, for a stated annual total of 30,700 euros. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Essential plan has no IoT connector. The IoT connector is not available on the Essential plan in this model.
    • 
      
  • Predictive maintenance needs Advanced or Premium. Predictive maintenance is not available on the Essential plan in this model.
    • 
    

    
4. IoT connector and predictive maintenance: The agent resubmits after fixing the errors

    
The agent's request. Please quote a SMART FM 360 Advanced plan subscription for 2 sites, 1,000 assets and 20 users, for office sites, with the helpdesk, predictive maintenance and the IoT connector with 100 sensor points, for a stated annual total of 42,700 euros. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Quote summary. 2 site(s), 1,000 assets, 20 users; subtotal 42700, net total 42,700 (illustrative prices).
    • 
    

    
5. Premium plan for four sites: A Premium plan for four sites with a deep discount and a stated total

    
The agent's request. Please quote a SMART FM 360 Premium plan subscription for 4 sites, 12,000 assets and 150 users, for industrial sites, with the helpdesk, the client portal, the mobile app, predictive maintenance, the Energy Management package and the IoT connector with 300 sensor points, and a discount of 44,520 euros, for a stated annual total of 148,400 euros. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Discount over the limit. The discount of 44,520 is more than 25 percent of the subtotal of 148,400.
    • 
      
  • Stated total does not match. The quote states a total of 148,400; the quoted items add up to 103,880.
    • 
    

    
6. Premium plan for four sites: The agent resubmits after fixing the errors

    
The agent's request. Please quote a SMART FM 360 Premium plan subscription for 4 sites, 12,000 assets and 150 users, for industrial sites, with the helpdesk, the client portal, the mobile app, predictive maintenance, the Energy Management package, data migration from the current system and the IoT connector with 300 sensor points, and a discount of 22,260 euros, for a stated annual total of 131,140 euros. It is ready to send.

    
Verdict: Needs approval.

    
    
      
  • Discount needs approval. The discount of 22,260 is between 10 and 25 percent of the subtotal of 153,400; a sales manager must approve it.
    • 
      
  • Data migration to scope. The quote includes migration of data from the customer current maintenance system; a delivery lead should scope it first.
    • 
      
  • Quote summary. 4 site(s), 12,000 assets, 150 users; subtotal 153400, net total 131,140 (illustrative prices).
    • 
    

  

  

    
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 annual subscription quote for a facility management platform: a plan, the number of sites, assets and users, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of these quotes and returns a verdict, every reason and the total it computed.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Please quote a SMART FM 360 Essential plan subscription for 1 site, 3,000 assets and 20 users, for office sites. It is ready to send. The rest of the request is on screen.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with six findings, all in one answer. The quote registers 3,000 assets; the selected plan allows at most 2,000. The quote lists 100 sensor points but no IoT connector. Predictive maintenance needs equipment data from the IoT connector, which is not quoted. The other three are on screen.
    6. 
      
  6. The validator returned six 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 limits that depend on the plan, a rules-based CPQ is error-prone for this.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the plan to advanced, the helpdesk to yes, the IoT connector to yes, the Energy Management package to yes and the total as stated on the quote to 47,200.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. This time the validator clears it.
    12. 
      
  12. All six earlier findings are cleared.
    13. 
      
  13. Six 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.