Predictika · Hospitality point-of-sale quotes

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

An AI sales agent prepares a quote for an Agilysys InfoGenesis point-of-sale system for a hotel, resort, casino, club or venue: the terminals, IG Flex handhelds and IG Kiosks, the kitchen display screens and digital menu boards, IG OnDemand and IG Quick Pay, Agilysys Pay or a third-party gateway, the property management and casino interfaces, the deployment, the support tier and a discount. Before the quote goes out, the agent sends it to Predictika, which checks it against a declarative model of what the product line allows and returns a verdict, every reason and the totals it computed.

Scope: InfoGenesis POS quotes: ordering devices per revenue center, payments, cloud or on-premise deployment, PMS and casino interfaces, support tier, discount and the stated total. See everything this validator covers

This validator models InfoGenesis POS quotes, not just the scenarios shown below.

  • Devices and support — IG terminals, IG Flex handhelds and IG Kiosks counted against the revenue centers, and a Premium or Enterprise 24x7 support tier once the quote passes 25 devices.
  • Payments — self-service ordering (IG Kiosk, IG OnDemand, IG Quick Pay) needs Agilysys Pay or a payment gateway, and a third-party gateway is confirmed by a person.
  • Deployment and interfaces — IG OnDemand only with cloud-hosted InfoGenesis, room charge posting only with a property management system, and the casino interface only for a casino.
  • Discount and totals — a discount above 15 percent of the subtotal that needs a sales manager, one above 30 percent that is blocked, and the total the quote states against the computed one.

Any InfoGenesis POS quote that touches these rules is in scope — not only the scenarios pictured here. Not covered: services, training and hardware leasing. Product names follow Agilysys's public product pages as Predictika read them. Compatibility and quantity rules, support tiers, approval thresholds and all prices are modeled from comparable hospitality POS products and are illustrative, not published by Agilysys.

The AI sales agentBuilds the POS quote from the conversation with the property and says it is ready to send.
Predictika validatorChecks every rule at once and returns the verdict, each finding, and the computed figures.

6 scenarios in 2 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
Support tier that depends on the device countOnly with care
The devices are spread over terminals, handhelds and kiosks, so the rule has to add them before it can pick the tier.
The devices are added inside the model and the tier is checked on every call.
Self-service ordering that needs a payment solutionOnly with workarounds
Kiosks, OnDemand and Quick Pay each need Agilysys Pay or a gateway, so one rule per product has to look at two other fields.
Every self-service product is checked against the payment fields in the same pass.
Products that only exist in one deployment or venueOnly with care
IG OnDemand is cloud only and the casino interface is for casinos, so each needs a rule that looks up the deployment or the venue.
The deployment, the venue and every product are in one request and checked together.
Room charge that needs a property management systemOnly with care
Room charge depends on either a quoted PMS interface or an existing PMS, so the rule must read both.
Both fields are read together and the finding names what is missing.
A discount and a stated total reconciled with the computed onesOnly with workarounds
The discount level sets approval or block against the subtotal, and a separate calculation is needed to compare the stated total with the computed one.
The subtotal, the discount and the net total are computed inside the model 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 person 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 31 ordering device; 1 revenue center supports at most 30 in this model.
2More than 25 ordering devices (26) need Premium or Enterprise 24x7 support, not Standard.
3IG Kiosk, IG OnDemand and IG Quick Pay take payment from the guest; the quote has neither Agilysys Pay nor a payment gateway.
4The customer uses a third-party payment gateway; a person should confirm it is supported for the quoted deployment.
5IG OnDemand is quoted with an on-premise deployment; this model offers it only with cloud-hosted InfoGenesis.
6Room charge posting needs a property management system; the quote has no Agilysys PMS interface and no existing PMS.
7The casino management system interface is quoted for a venue that is not a casino.
8The discount of $4,126 is between 15 and 30 percent of the subtotal of $27,500; a sales manager must approve it.
9The discount of $8,251 is more than 30 percent of the subtotal of $27,500.
10The quote has no IG terminals, IG Flex handhelds or IG Kiosks; the order needs at least one ordering device.
11The quote states a total of $1; the quoted items add up to 27500.

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. Resort quote with kiosks, OnDemand, room charge and a casino link: Resort POS quote with kiosks, OnDemand, room charge and a discount

The agent's request. Please quote an InfoGenesis POS system for a hotel or resort with 2 revenue centers, on premise, with 24 IG terminals, 12 IG Flex handhelds, 4 IG Kiosks and 4 IG KDS screens. The quote also includes IG OnDemand, room charge and the casino management system interface. Support is Standard. The sales rep offers a discount of $24,360 and the quote states a total of $45,240. It is ready to send.

Verdict: Blocked.

  • Support tier too low for the device count. More than 25 ordering devices (40) need Premium or Enterprise 24x7 support, not Standard.
  • Self-service ordering needs a payment solution. IG Kiosk, IG OnDemand and IG Quick Pay take payment from the guest; the quote has neither Agilysys Pay nor a payment gateway.
  • IG OnDemand needs cloud deployment. IG OnDemand is quoted with an on-premise deployment; this model offers it only with cloud-hosted InfoGenesis.
  • Room charge needs a PMS. Room charge posting needs a property management system; the quote has no Agilysys PMS interface and no existing PMS.
  • Casino system link only for casinos. The casino management system interface is quoted for a venue that is not a casino.
  • Discount over the limit. The discount of $24,360 is more than 30 percent of the subtotal of $69,600.

2. Resort quote with kiosks, OnDemand, room charge and a casino link: The agent resubmits after fixing the errors

The agent's request. Please quote an InfoGenesis POS system for a hotel or resort with 2 revenue centers, cloud hosted, with 24 IG terminals, 12 IG Flex handhelds, 4 IG Kiosks and 4 IG KDS screens. The quote also includes IG OnDemand, Agilysys Pay and room charge. Support is Premium. The sales rep offers a discount of $24,430 and the quote states a total of $45,370. It is ready to send.

Verdict: Blocked.

  • Room charge needs a PMS. Room charge posting needs a property management system; the quote has no Agilysys PMS interface and no existing PMS.
  • Discount over the limit. The discount of $24,430 is more than 30 percent of the subtotal of $69,800.

3. Resort quote with kiosks, OnDemand, room charge and a casino link: The agent resubmits after fixing the errors

The agent's request. Please quote an InfoGenesis POS system for a hotel or resort with 2 revenue centers, cloud hosted, with 24 IG terminals, 12 IG Flex handhelds, 4 IG Kiosks and 4 IG KDS screens. The quote also includes IG OnDemand, Agilysys Pay, the PMS interface and room charge. Support is Premium. The sales rep offers a discount of $8,616 and the quote states a total of $63,184. It is ready to send.

Verdict: Allowed.

  • Quote summary. 40 ordering devices across 2 revenue centers; subtotal $71,800, net total $63,184 (modeled, illustrative prices).

4. Stadium quote with many devices: Stadium POS quote with one revenue center and Quick Pay

The agent's request. Please quote an InfoGenesis POS system for a stadium or venue with 1 revenue center, cloud hosted, with 22 IG terminals, 12 IG Flex handhelds, 6 IG KDS screens and 8 digital menu boards. The quote also includes IG Quick Pay and a third-party payment gateway. Support is Standard. The sales rep offers no discount and the quote states a total of $51,300. It is ready to send.

Verdict: Blocked.

  • Too many devices for the revenue centers. The quote has 34 ordering devices; 1 revenue center supports at most 30 in this model.
  • Support tier too low for the device count. More than 25 ordering devices (34) need Premium or Enterprise 24x7 support, not Standard.
  • Third-party gateway to confirm. The customer uses a third-party payment gateway; a person should confirm it is supported for the quoted deployment.

5. Stadium quote with many devices: The agent resubmits after fixing the errors

The agent's request. Please quote an InfoGenesis POS system for a stadium or venue with 2 revenue centers, cloud hosted, with 22 IG terminals, 12 IG Flex handhelds, 6 IG KDS screens and 8 digital menu boards. The quote also includes IG Quick Pay and a third-party payment gateway. Support is Premium. The sales rep offers no discount and the quote states a total of $56,840. It is ready to send.

Verdict: Needs approval.

  • Third-party gateway to confirm. The customer uses a third-party payment gateway; a person should confirm it is supported for the quoted deployment.
  • Quote summary. 34 ordering devices across 2 revenue centers; subtotal $56,840, net total $56,840 (modeled, illustrative prices).

6. Stadium quote with many devices: The agent resubmits after fixing the errors

The agent's request. Please quote an InfoGenesis POS system for a stadium or venue with 2 revenue centers, cloud hosted, with 22 IG terminals, 12 IG Flex handhelds, 6 IG KDS screens and 8 digital menu boards. The quote also includes IG Quick Pay and Agilysys Pay. Support is Premium. The sales rep offers no discount and the quote states a total of $58,040. It is ready to send.

Verdict: Allowed.

  • Quote summary. 34 ordering devices across 2 revenue centers; subtotal $58,040, net total $58,040 (modeled, 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 a quote for an Agilysys InfoGenesis point-of-sale system for a hotel, resort, casino, club or venue: the terminals, IG Flex handhelds and IG Kiosks, the kitchen display screens and digital menu boards, and more. Before the quote goes out, the agent sends it to Predictika, which checks it against a declarative model of what the product line allows and returns a verdict, every reason and the totals it computed.
  2. I will start with the first request by the agent.
  3. The agent says. Please quote an InfoGenesis POS system for a hotel or resort with 2 revenue centers, on premise, with 24 IG terminals. The quote also includes IG OnDemand, room charge and the casino management system interface. The rest of the request is on screen. The sales rep offers a discount of $24,360 and the quote states a total of $45,240.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with six findings, all in one answer. More than 25 ordering devices (40) need Premium or Enterprise 24x7 support, not Standard. IG Kiosk, IG OnDemand and IG Quick Pay take payment from the guest; the quote has neither Agilysys Pay nor a payment gateway. IG OnDemand is quoted with an on-premise deployment; this model offers it only with cloud-hosted InfoGenesis. The other three are on screen.
  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. What this shows: for self-service ordering that needs a payment solution, a rules-based CPQ can do this only with workarounds.
  8. Now the agent resubmits.
  9. The corrected request. It changes the deployment to cloud, the Agilysys Pay to yes, the casino management interface to no, the support tier to premium, the discount to $24,430 and the total stated on the quote to $45,370.
  10. It calls the validator again.
  11. Still blocked, with two findings, all in one answer. Room charge posting needs a property management system; the quote has no Agilysys PMS interface and no existing PMS. The discount of $24,430 is more than 30 percent of the subtotal of $69,800.
  12. Four findings cleared. Still blocking: room charge needs a PMS and discount over the limit.
  13. The agent resubmits once more.
  14. The revised request. It changes the PMS interface to yes, the discount to $8,616 and the total stated on the quote to $63,184.
  15. It calls the validator once more.
  16. This time the validator clears it.
  17. Both earlier findings are cleared.
  18. Six problems caught in one call, fixed in two passes, and a clean $63,184 quote. That is the value of Predictika's validator: catching mistakes before they reach the customer. Now you can try the other scenarios yourself.