Predictika · Workforce services quotes

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

An AI sales agent prepares a quote for workforce services: temporary staffing, temp-to-hire, direct hire, IT contract, recruitment outsourcing or managed services, with the headcount, weeks, hours, pay, markup or fee and the total it states in dollars. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the quoting rules and returns a verdict, every reason and the total it computed.

Scope: ManpowerGroup workforce services quotes: Manpower temporary staffing, temp-to-hire and direct hire, Experis IT contract, Talent Solutions recruitment outsourcing and TAPFIN managed services, with headcount, assignment length, hours, pay, markup, fees, guarantees and the stated total. See everything this validator covers

This validator models workforce quotes of this kind, not just the scenarios shown below.

  • Services — six services, each with its own inputs: a bill rate for temporary and contract staff, a percentage of salary for direct hire, a fee per hire for recruitment outsourcing and a management fee for managed services.
  • Ranges and options — headcount, assignment length, hours per week, pay rate, markup, salary, fee, replacement guarantee, hires per year and annual spend, each with its own limits.
  • Price and review — overtime, long assignments, large headcounts, early conversion, high markups and low fees that need a person, and the stated total compared with the computed one.

Any workforce quote that touches these rules is in scope — not only the scenarios pictured here. The brand and service names are ManpowerGroup's public names; every limit, rate and approval threshold is modeled from comparable staffing practice and not published by ManpowerGroup, so the amounts on this page are illustrative.

The AI sales agentBuilds the workforce 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
Different inputs for each serviceOnly with care
Temporary staffing is priced by pay rate and markup, direct hire by salary and fee, recruitment by hires and fee per hire, so every service has its own fields and ranges.
The service decides which fields apply and each range is checked on every call.
Ranges and options per serviceOnly with workarounds
Pay, markup, guarantees and minimum assignment lengths differ between temp, Experis, direct hire, recruitment and managed services.
Each limit is its own rule and all of them are evaluated together.
Approvals for unusual termsOnly with care
Overtime, assignments over 26 weeks, headcounts over 100, early conversion, markups over 75 percent and low fees each need a person.
Every approval condition is evaluated on every call and returned with the rest.
A total built from many partsOnly with workarounds
The total is hours times bill rate for temporary staff, a percentage of salary for direct hire, hires times a fee for recruitment, so it must be computed before it can be compared with the total stated.
The total is computed on every call and compared with the total stated in the quote.
Every problem returned in one answerOnly with workarounds
Rules tend to fire as a step is saved or 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 0 people; this quote covers 1 to 500.
2The quote has 501 people; this quote covers 1 to 500.
3A request for 101 people is a volume engagement; a person should confirm the staffing plan and pricing.
4The quote has an assignment of 0 weeks; 1 to 52 weeks is offered.
5The quote has an assignment of 53 weeks; 1 to 52 weeks is offered.
6An assignment of 27 weeks is longer than 26 weeks; a person should confirm the extension terms.
7An Experis IT contract assignment is quoted for at least 4 weeks; the quote has 3 weeks.
8The quote has 9 hours per week; 10 to 48 hours is offered.
941 hours per week includes overtime, which is billed at a higher rate; a person should confirm it.
10The quote has 49 hours per week; 10 to 48 hours is offered.
11The quote has a pay rate of 11 dollars per hour; this service is quoted from 12 to 60 dollars per hour.
12The quote has a pay rate of 61 dollars per hour; this service is quoted from 12 to 60 dollars per hour.
13The quote has a pay rate of 39 dollars per hour; this service is quoted from 40 to 180 dollars per hour.
14The quote has a markup of 29 percent; this service is quoted from 30 to 90 percent.
15The quote has a markup of 34 percent; this service is quoted from 35 to 90 percent.
16A markup of 76 percent is above 75 percent; a person should confirm it with the client.
17The quote has a markup of 91 percent; this service is quoted from 30 to 90 percent.
18A planned conversion to permanent staff is only quoted on temp-to-hire; this service has a conversion planned after 520 hours.
19A conversion to permanent staff after 400 hours is before the 520 hours at which the conversion fee is waived; a person should confirm the fee.
20The quote has a first-year salary of 29 thousand dollars; direct hire is quoted for 30 to 300 thousand dollars.
21The quote has a first-year salary of 301 thousand dollars; direct hire is quoted for 30 to 300 thousand dollars.
22The quote has a direct hire fee of 14 percent of first-year salary; 15 to 25 percent is offered.
23The quote has a direct hire fee of 26 percent of first-year salary; 15 to 25 percent is offered.
24The quote has a replacement guarantee of 45 days; 30, 60 or 90 days is offered.
25A 90 day guarantee at a fee of 19 percent is below the 20 percent normally needed for it; a person should confirm it.
26The quote has 49 hires a year; recruitment process outsourcing is quoted for 50 to 5,000 hires a year.
27The quote has 5,001 hires a year; recruitment process outsourcing is quoted for 50 to 5,000 hires a year.
28The quote has a fee of 1,499 dollars per hire; 1,500 to 12,000 dollars is offered.
29The quote has a fee of 12,001 dollars per hire; 1,500 to 12,000 dollars is offered.
30A fee of 2,000 dollars per hire on under 500 hires a year is below the usual rate for that volume; a person should confirm it.
31The quote has an annual contingent spend of 4,999 thousand dollars; managed services are quoted for 5 million to 2 billion dollars.
32The quote has an annual contingent spend of 2,000,001 thousand dollars; managed services are quoted for 5 million to 2 billion dollars.
33The quote has a management fee of 9 tenths of a percent of spend; 10 to 40 tenths (1.0 to 4.0 percent) is offered.
34The quote has a management fee of 41 tenths of a percent of spend; 10 to 40 tenths (1.0 to 4.0 percent) is offered.
35A management fee of 12 tenths of a percent is below 1.5 percent; a person should confirm it.
36The quote states a total of 139,199 dollars; the modeled rates give 139,200 dollars.
37The quote states a total of 34,100 dollars; the modeled rates give 34,000 dollars.
3844 hours per week includes overtime, which is billed at a higher rate; a person should confirm it.
39A request for 150 people is a volume engagement; a person should confirm the staffing plan and pricing.
40A markup of 80 percent is above 75 percent; a person should confirm it with the client.

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. Temporary staffing: A large temporary order with overtime, a long assignment, pay and markup below the offered range, a conversion planned and a wrong total

The agent's request. Please quote temporary staffing for 150 people for 30 weeks at 44 hours a week, paid 11 dollars an hour with a 28 percent markup, with a conversion to permanent staff after 520 hours. The quote states a total of 60,000 dollars. It is ready to send.

Verdict: Blocked.

  • Pay rate out of range. The quote has a pay rate of 11 dollars per hour; this service is quoted from 12 to 60 dollars per hour.
  • Markup outside the offered range. The quote has a markup of 28 percent; this service is quoted from 30 to 90 percent.
  • Conversion planned on a temporary assignment. A planned conversion to permanent staff is only quoted on temp-to-hire; this service has a conversion planned after 520 hours.
  • Stated total does not match. The quote states a total of 60,000 dollars; the modeled rates give 2,787,840 dollars.
  • Overtime hours. 44 hours per week includes overtime, which is billed at a higher rate; a person should confirm it.
  • Long assignment. An assignment of 30 weeks is longer than 26 weeks; a person should confirm the extension terms.
  • Large headcount. A request for 150 people is a volume engagement; a person should confirm the staffing plan and pricing.

2. Temporary staffing: The agent resubmits after fixing the errors

The agent's request. Please quote temporary staffing for 100 people for 26 weeks at 40 hours a week, paid 20 dollars an hour with a 45 percent markup. The quote states a total of 3,016,000 dollars. It is ready to send.

Verdict: Allowed.

  • Quote summary. Estimated total of 3,016,000 dollars for this engagement.

3. Direct hire: A direct hire quote with a salary, fee and guarantee that are not offered, and a wrong total

The agent's request. Please quote direct hire of 2 people at a first-year salary of 29 thousand dollars, a fee of 14 percent and a 45 day replacement guarantee. The quote states a total of 15,000 dollars. It is ready to send.

Verdict: Blocked.

  • Salary out of range. The quote has a first-year salary of 29 thousand dollars; direct hire is quoted for 30 to 300 thousand dollars.
  • Direct hire fee out of range. The quote has a direct hire fee of 14 percent of first-year salary; 15 to 25 percent is offered.
  • Guarantee period not offered. The quote has a replacement guarantee of 45 days; 30, 60 or 90 days is offered.
  • Stated total does not match. The quote states a total of 15,000 dollars; the modeled rates give 8,120 dollars.

4. Direct hire: The agent resubmits with a higher salary and fee, approved

The agent's request. Please quote direct hire of 2 people at a first-year salary of 85 thousand dollars, a fee of 19 percent and a 90 day replacement guarantee, which a manager has approved. The quote states a total of 32,300 dollars. It is ready to send.

Verdict: Needs approval.

  • Long guarantee at a low fee. A 90 day guarantee at a fee of 19 percent is below the 20 percent normally needed for it; a person should confirm it.
  • Quote summary. Estimated total of 32,300 dollars for this engagement.

5. Recruitment outsourcing: A recruitment outsourcing quote with too few hires, a fee per hire below the range and a wrong total

The agent's request. Please quote recruitment process outsourcing for 49 hires a year at 1,499 dollars per hire. The quote states a total of 70,000 dollars. It is ready to send.

Verdict: Blocked.

  • RPO hires per year out of range. The quote has 49 hires a year; recruitment process outsourcing is quoted for 50 to 5,000 hires a year.
  • RPO fee per hire out of range. The quote has a fee of 1,499 dollars per hire; 1,500 to 12,000 dollars is offered.
  • Stated total does not match. The quote states a total of 70,000 dollars; the modeled rates give 73,451 dollars.

6. Recruitment outsourcing: The agent resubmits after fixing the errors

The agent's request. Please quote recruitment process outsourcing for 500 hires a year at 2,000 dollars per hire. The quote states a total of 1,000,000 dollars. It is ready to send.

Verdict: Allowed.

  • Quote summary. Estimated total of 1,000,000 dollars for this engagement.

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 workforce services: temporary staffing, temp-to-hire, direct hire, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the quoting rules and returns a verdict, every reason and the total it computed.
  2. I will start with the first request by the agent.
  3. The agent says. Please quote temporary staffing for 150 people for 30 weeks at 44 hours a week, paid 11 dollars an hour with a 28 percent markup. The quote states a total of 60,000 dollars. The rest of the request is on screen.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with four findings and three approvals, all in one answer. The quote has a pay rate of 11 dollars per hour; this service is quoted from 12 to 60 dollars per hour. The quote has a markup of 28 percent; this service is quoted from 30 to 90 percent. A planned conversion to permanent staff is only quoted on temp-to-hire; this service has a conversion planned after 520 hours. The other one is on screen.
  6. The validator returned four blocking findings and three approvals 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 and against the stated total.
  7. What this shows: for ranges and options per service, a rules-based CPQ can do this only with workarounds.
  8. Now the agent resubmits.
  9. The corrected request. It changes the people to 100, the weeks to 26, the hours per week to 40, the pay rate to 20 and the stated total to 3,016,000. Two more changes are on screen.
  10. It calls the validator again.
  11. This time the validator clears it.
  12. All seven earlier findings are cleared.
  13. Seven 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.