Predictika · Cloud contact center quotes

An AI sales agent's cloud contact center quote, checked before it goes out

An AI sales agent drafts a quote for a cloud contact center: the plan, the channel, the number of agents, the term in months, the voice minutes per agent and the workforce and AI add-ons. Before the quote goes out, the agent sends it to Predictika, which checks it against a declarative model of the plan and channel limits, add-on availability and discount authority, compares the net total the agent states with the one it computes, and reports every problem it finds in one pass.

Scope: Five9 style cloud contact center quotes: three plans, three channels, agent count, term, voice minutes, workforce and AI add-ons and discounts. See everything this validator covers

This validator models Five9 style cloud contact center quotes: three plans, three channels, the number of agents, the term in months, voice minutes per agent, the workforce and AI add-ons and discounts. It handles any quote made of these plans and channels, not just the scenarios shown below.

  • Plans, channels and agent counts — Core, Premium and Ultimate plans and the voice, digital and omnichannel channels. Each plan has a minimum number of agents and the plan and the channel each cap the count; the tighter cap applies.
  • Add-ons and voice minutes — The workforce and AI add-ons are only available on Premium and Ultimate. Voice minutes need a channel with voice, are limited to 10,000 per agent, and above 3,000 need a carrier review.
  • Term — A term of 12 to 60 months, with a finance review for the price lock when it is longer than 36 months.
  • Discounts and order size — A volume discount from 250 agents, a term discount from 24 months and an extra discount: a rep can give up to 12 percent in total, a sales director must approve above that, and 20 percent is the limit. An order above USD 1,500,000 needs a deal desk review, and both add-ons above 2,000 agents need an implementation review.
  • The stated net total — A check that the net total the agent states matches the contract value the validator computes.

Any contact center quote that touches these rules is in scope — not only the scenarios pictured here. Not covered: other Five9 products, professional services, real list prices, carrier charges and overage rates, partner pricing, tax or multi-currency quoting.

The AI sales agentBuilds the contact center 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
Agent cap from the tighter of plan and channelOnly with care
A cap per plan and per channel that has to be combined; usually two rules that must be kept consistent.
Both caps are catalog data and the lower one is applied on every call.
Add-ons that depend on the planOnly with care
Option rules per add-on and plan, extended for every new plan or add-on.
The plan lists which add-ons it has; the check follows from the choices.
Discount stacking and approval bandsOnly with workarounds
Volume, term and extra discounts add up across rules and approval levels, and the total is rarely checked in one place.
The three discounts are added once and compared with both the rep authority and the limit.
Term, voice minutes and review bandsOnly with care
Ranges with a review band inside them, usually split over several validation rules.
Both the hard range and the review band are checked together.
The total the agent statesOnly with workarounds
Comparing a stated total with a computed one means a separate rule per quote layout, and price rules rarely run on stated figures.
The stated net total is a field in the request and is checked against the computed total.
Every problem returned 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: 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.

1A term of 48 months is longer than 36 months; finance must approve the price lock.
24,500 voice minutes per agent are above 3,000; a carrier review must confirm capacity.
3Total discount of 14 percent is above the 12 percent a rep can give; sales director must approve.
4Workforce and AI add-ons above 2,000 agents need an implementation review.
5Order value of $23,870,160 is above $1,500,000 and needs a deal desk review.
6300 agents are above the 250 agents the Core plan and the Voice channel allow together.
7The workforce add-on is not available on the Core plan.
8The AI add-on is not available on the Core plan.
9Voice minutes cannot be included with the Digital channel.
1030 agents are below the 50 agent minimum of the Ultimate plan.
11A term of 6 months is outside the 12 to 60 months allowed.
12Total discount of 22 percent exceeds the 20 percent limit.
1312,000 voice minutes per agent are outside the 0 to 10,000 allowed.
14The quoted net total of $160,920 does not match the $178,800 the validator computed.

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. Add-ons: The total is right; the plan does not offer the add-on

The agent's request. This is for a contact center operator that wants AI features on 50 agents. The Core plan for 50 agents on a 12 months term with voice minutes included and the AI add-on. Net total $82,200. It is ready to send.

Verdict: Blocked.

  • AI Add-on. The AI add-on is not available on the Core plan.

2. Add-ons: The agent resubmits after fixing the errors

The agent's request. This is for a contact center operator that wants AI features on 50 agents. The Premium plan for 50 agents on a 12 months term with voice minutes included and the AI add-on. Net total $100,200. It is ready to send.

Verdict: Allowed.

  • Price summary. Estimated price: $100,200 total for 50 agents over 12 months; $167 per agent per month; $100,200 before discount; 0 percent total discount.

3. Agent limits: The total is right; the plan cannot cover 300 agents

The agent's request. This is for a contact center operator that is buying the Core plan for 300 agents. The Core plan for 300 agents on a 12 months term with voice minutes included. Net total $411,264. It is ready to send.

Verdict: Blocked.

  • Agent Count Limit. 300 agents are above the 250 agents the Core plan and the Voice channel allow together.

4. Agent limits: The agent resubmits after fixing the errors

The agent's request. This is for a contact center operator that is buying the Core plan for 200 agents. The Core plan for 200 agents on a 12 months term with voice minutes included. Net total $285,600. It is ready to send.

Verdict: Allowed.

  • Price summary. Estimated price: $285,600 total for 200 agents over 12 months; $119 per agent per month; $285,600 before discount; 0 percent total discount.

5. The total the agent states: The agent's own total is checked too

The agent's request. This is for a contact center operator that is buying the Premium plan for 100 agents. The Premium plan for 100 agents on a 12 months term with voice minutes included. Net total $160,920. It is ready to send.

Verdict: Blocked.

  • Quoted Net Total. The quoted net total of $160,920 does not match the $178,800 the validator computed.

6. The total the agent states: The agent resubmits after fixing the errors

The agent's request. This is for a contact center operator that is buying the Premium plan for 100 agents. The Premium plan for 100 agents on a 12 months term with voice minutes included. Net total $178,800. It is ready to send.

Verdict: Allowed.

  • Price summary. Estimated price: $178,800 total for 100 agents over 12 months; $149 per agent per month; $178,800 before discount; 0 percent total discount.

7. Review by a person: Valid, but not final without a person

The agent's request. This is for a contact center operator that has asked for a large discount on 200 agents. The Premium plan for 200 agents on a 12 months term with voice minutes included, with an extra 14 percent discount. Net total $307,536. It is ready to send.

Verdict: Needs approval.

  • Discount Approval. Total discount of 14 percent is above the 12 percent a rep can give; sales director must approve.
  • Price summary. Estimated price: $307,536 total for 200 agents over 12 months; $149 per agent per month; $357,600 before discount; 14 percent total discount.

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 drafts a quote for a cloud contact center: the plan, the channel, the number of agents, and more. Before the quote goes out, the agent sends it to Predictika, which checks it against a declarative model of the plan and channel limits, add-on availability and discount authority, compares the net total the agent states with the one it computes, and reports every problem it finds in one pass.
  2. I will start with the first request by the agent.
  3. The agent says. This is for a contact center operator that wants AI features on 50 agents. The Core plan for 50 agents on a 12 months term with voice minutes included and the AI add-on. The rest of the request is on screen. Net total $82,200.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with one finding, all in one answer. The AI add-on is not available on the core plan.
  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. What this shows: for add-ons that depend on the plan, a rules-based CPQ is error-prone for this.
  8. Now the agent resubmits.
  9. The corrected request. It changes the plan to premium plan and the net total stated on the quote to $100,200.
  10. It calls the validator again.
  11. This time the validator clears it.
  12. The validator also returns the line-item quote, on screen.
  13. The earlier finding is cleared, and the validator's total, $100,200, matches the quote.
  14. One problem caught in one call, fixed in one pass, and a clean $100,200 quote. That is the value of Predictika's validator: catching mistakes before they reach the customer. Now you can try the other scenarios yourself.