Predictika · Security screening quotes

An AI sales agent's security screening subscription quote, checked before it goes out

An AI sales agent prepares a subscription quote for AI-powered weapons screening at a venue: entrances, Evolv Express units for people, Evolv eXpedite units for bags, sales model, initial term and expected visitor flow. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the Evolv product line as described in its public annual report and returns a verdict, every reason, a line-item quote and the figures it computed.

Scope: Evolv Express (people screening) and Evolv eXpedite (bag screening) on a pure subscription or a purchase subscription: entrances, throughput, initial term, volume and term discounts, one-time charges. See everything this validator covers

This validator models security screening subscription quotes for the products below, not just the scenarios shown.

  • Products — Evolv Express (screens people for concealed threats) and Evolv eXpedite (autonomous bag screening; can be used alone or beside Evolv Express), with Evolv Insights analytics, the management tablet and on-site support included in the subscription. Two sales models: a pure subscription where the customer leases the hardware, and a purchase subscription where the customer buys the hardware and pays a subscription to operate it. These are real Evolv names and models.
  • Rules — every entrance needs a unit, the peak visitor flow and the bag flow have to fit the units, the subscription is a multi-year commitment (four years is the typical initial term), outdoor checkpoints need weather protection, and the first-year amount the agent states is compared with the computed one. The throughput per unit, prices, discounts and thresholds are typical values for this kind of subscription, not Evolv's.
  • Illustrative items* — the weather canopy and the premier support option are not Evolv products as far as this validator knows; they are shown to illustrate options.

Any screening quote for these two products that touches these rules is in scope — not only the scenarios pictured here. Not covered: other Evolv products and services, international pricing, reseller margins, financing, and taxes. Nothing here is an Evolv price, specification or sales policy.

The AI sales agentBuilds the screening subscription quote and says it is ready.
Predictika validatorChecks every rule at once and returns the verdict, each finding, the line-item quote 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
Stated first-year amounts that must equal what the pricing givesOnly with care
A stated figure is a free-entry field; a rule can compare it with a computed total, but the total mixes subscription, discounts and one-time charges that have to be kept in step.
The stated amount travels with the quote and is compared with the computed first-year amount on every call.
A quote that mixes annual subscription, tiered discounts, hardware purchase and optionsOnly with care
Volume and term discounts, a sales-model price table and one-time lines are chained price rules; the order and rounding are easy to get wrong.
Every line is computed in the same pass and the line items reconcile to the total.
Units that must cover every entrance, the peak people flow and the bag flow togetherOnly with workarounds
Entrances, units, visitor flow and bag share sit on different fields, so it needs cross-field rules that interact and are easy to leave out.
Entrances, units, flow and bags are in one request and checked together.
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 quote has 0 Evolv Express and Evolv eXpedite units in total; at least 1 is needed.
2The quote lists 0 entrances to screen; at least 1 is needed.
3The quote has 1 screening units for 2 entrances; each entrance needs at least one unit (modeled).
4A peak of 2,401 visitors an hour is above the 2,400 an hour the Evolv Express units can screen (modeled at 1,200 an hour for each unit).
5810 bags an hour is above the 800 an hour the Evolv eXpedite units can screen (modeled at 800 an hour for each unit).
6101 percent of visitors carrying bags is outside 0 to 100 percent.
7The subscription is a multi-year commitment; a term of 1 year is below the 2 year minimum modeled.
8The initial term of 2 years differs from the typical four years; a person should confirm the term.
9The checkpoints are outdoors and the quote has fewer weather canopies than its 2 Evolv Express units; a person should confirm the weather protection.
10The quote has more Evolv eXpedite units (2) than Evolv Express units (1); a person should confirm the checkpoint design.
11A first-year amount of $4,527,840 is at or above $2,000,000 and needs a person to confirm.
12The quote states a first-year amount of $116,800; the pricing gives $117,800.

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. Capacity: School campus with too few units for its peak flow and bags

The agent's request. Please quote a pure subscription (leased hardware) for a school campus with 3 entrances: 2 Evolv Express units and 1 Evolv eXpedite unit, on a 4 year initial term, with a peak flow of 3,000 visitors an hour and 40 percent of visitors carrying bags. The quote states a first-year amount of $154,800. It is ready to send.

Verdict: Blocked.

  • People throughput above capacity. A peak of 3,000 visitors an hour is above the 2,400 an hour the Evolv Express units can screen (modeled at 1,200 an hour for each unit).
  • Bag throughput above capacity. 1,200 bags an hour is above the 800 an hour the Evolv eXpedite units can screen (modeled at 800 an hour for each unit).

2. Capacity: The agent resubmits after fixing the errors

The agent's request. Please quote a pure subscription (leased hardware) for a school campus with 3 entrances: 3 Evolv Express units and 2 Evolv eXpedite units, on a 4 year initial term, with a peak flow of 3,000 visitors an hour and 40 percent of visitors carrying bags. The quote states a first-year amount of $253,800. It is ready to send.

Verdict: Allowed.

  • Quote summary. First-year amount of $253,800, all in subscription; $1,015,200 over the 4 year term.

3. Term and weather protection: Stadium purchase subscription on a one year term

The agent's request. Please quote a purchase subscription (purchased hardware) for a stadium with 6 entrances: 8 Evolv Express units and 4 Evolv eXpedite units, on a 1 year initial term, with a peak flow of 9,000 visitors an hour and 30 percent of visitors carrying bags, with the checkpoints outdoors. The quote states a first-year amount of $1,243,560. It is ready to send.

Verdict: Blocked.

  • Term shorter than a multi-year commitment. The subscription is a multi-year commitment; a term of 1 year is below the 2 year minimum modeled.
  • Outdoor checkpoint without weather protection. The checkpoints are outdoors and the quote has fewer weather canopies than its 8 Evolv Express units; a person should confirm the weather protection.

4. Term and weather protection: The agent resubmits after fixing the errors

The agent's request. Please quote a purchase subscription (purchased hardware) for a stadium with 6 entrances: 8 Evolv Express units and 4 Evolv eXpedite units, on a 4 year initial term, with a peak flow of 9,000 visitors an hour and 30 percent of visitors carrying bags, with the checkpoints outdoors and 8 weather canopies. The quote states a first-year amount of $1,259,960. It is ready to send.

Verdict: Allowed.

  • Quote summary. First-year amount of $1,259,960 ($258,960 a year in subscription, $1,001,000 one time); $2,036,840 over the 4 year term.

5. Entrance coverage: House of worship with two units for four entrances

The agent's request. Please quote a pure subscription (leased hardware) for a house of worship with 4 entrances: 2 Evolv Express units, on a 4 year initial term, with a peak flow of 1,800 visitors an hour. The quote states a first-year amount of $117,800. It is ready to send.

Verdict: Blocked.

  • Not every entrance has a unit. The quote has 2 screening units for 4 entrances; each entrance needs at least one unit (modeled).

6. Entrance coverage: The agent resubmits after fixing the errors

The agent's request. Please quote a pure subscription (leased hardware) for a house of worship with 4 entrances: 4 Evolv Express units, on a 4 year initial term, with a peak flow of 1,800 visitors an hour. The quote states a first-year amount of $223,200. It is ready to send.

Verdict: Allowed.

  • Quote summary. First-year amount of $223,200, all in subscription; $892,800 over the 4 year term.

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 subscription quote for AI-powered weapons screening at a venue: entrances, Evolv Express units for people, Evolv eXpedite units for bags, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the Evolv product line as described in its public annual report and returns a verdict, every reason, a line-item quote and the figures it computed.
  2. I will start with the first request by the agent.
  3. The agent says. Please quote a pure subscription (leased hardware) for a school campus. The quote states a first-year amount of $154,800. The rest of the request is on screen.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with two findings, all in one answer. A peak of 3,000 visitors an hour is above the 2,400 an hour the Evolv Express units can screen (modeled at 1,200 an hour for each unit). 1,200 bags an hour is above the 800 an hour the Evolv eXpedite units can screen (modeled at 800 an hour for each unit).
  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. What this shows: for units that must cover every entrance, the peak people flow and the bag flow together, a rules-based CPQ can do this only with workarounds.
  8. Now the agent resubmits.
  9. The corrected request. It changes the Evolv Express units to 3, the evolv eXpedite units to 2 and the stated first-year amount to $253,800.
  10. It calls the validator again.
  11. This time the validator clears it.
  12. The validator also returns the line-item quote. It starts with Evolv Express people screening and Evolv eXpedite bag screening; the other line is on screen.
  13. Both earlier findings are cleared, and the validator's total, $253,800.00, matches the quote.
  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.