Predictika · Contract compression quotes

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

An AI sales agent prepares a contract compression quote for a fleet of gas-engine, electric motor or rotary screw units with treating and cooling add-ons. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of unit sizing, application limits, term and utilities, and returns a verdict, every reason and the monthly fee it computed.

Scope: Contract compression: Caterpillar G3600 A4 gas-engine units, electric motor units and rotary screw units, with amine treating, gas dehydration and gas cooling add-ons. See everything this validator covers

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

  • Units and applications — the G3606, G3608, G3612 and G3616 A4 gas-engine units, electric motor units and rotary screw units, against seven applications from multi-well gas lift to enhanced oil recovery.
  • Sizing, pressure and term — horsepower per unit, discharge pressure, primary term, fuel gas supplied by the customer and grid power at the site.
  • Services and price — amine treating, gas dehydration and gas cooling, a discount, and the stated monthly fee against the fee the validator computes.

Any contract compression quote that touches these rules is in scope — not only the scenarios pictured here. The engine maximum ratings follow Caterpillar's published figures and the term, fuel-gas and application facts follow Kodiak's public filings; the other limits, the approval thresholds and every rate are modeled and not published by Kodiak, and the dollar rates are illustrative. Not covered: Power Solutions, Turnkey Services, Compressor Stations and Aftermarket Services.

The AI sales agentBuilds the contract compression 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
Limits that depend on the unit type and the applicationOnly with care
Horsepower, pressure and screw-unit eligibility each change with the driver and the application, so every limit needs its own lookup rule.
The unit, application, horsepower and pressure are fields of one request and are checked together on every call.
A longer term for larger unitsOnly with care
The minimum term depends on the horsepower per unit, so a term rule has to sit beside the sizing rules.
The term and the horsepower are checked against each other on every call.
Utilities that depend on the driverOnly with care
Gas-engine units need customer fuel gas and electric and screw units need grid power, a different test for each driver.
The driver and the utilities are in one request and checked together on every call.
A stated monthly fee that must match the computed feeOnly with workarounds
The fee is built from units, horsepower, rate, add-ons and discount, so a separate rule must recompute it and compare it with the stated figure.
The stated fee is a field of the request and is compared with the computed fee on every call.
Every problem returned in one answerOnly with workarounds
Rules tend to fire as a step is saved or 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 asks 2,100 HP per unit; this unit type tops out at 2,065 HP.
2The quote asks 1,500 HP per unit; this unit type is sized from 2,060 HP.
3Electric motor and rotary screw units need grid power at the site; the quote has none.
4The quote asks 3,500 HP per unit; this unit type tops out at 3,000 HP.
5Rotary screw units serve only low-pressure gathering, vapor recovery and wellhead gas lift.
6The quote asks 500 psi discharge; this unit and application allow 350 psi.
7The quote asks 3,500 psi discharge; this unit and application allow 3,000 psi.
8The quote asks 9,500 psi discharge; this unit and application allow 9,000 psi.
9The primary term is 6 months; the minimum is 12.
10Units above 1,000 HP are contracted for 36 months or more; the quote has 24 months.
11Gas-engine units run on fuel gas supplied by the customer; the quote has none.
12Amine treating and gas dehydration are offered only with gas gathering or gas processing.
13Sour gas without amine treating needs an engineering review of the compression package.
14A discount above 10 percent needs a manager to sign off.
15The quote has a 25 percent discount; the maximum is 20.
16The quote states a monthly fee of 170,000 dollars; the quoted units and services give a different figure.
17An order of more than 20 units needs a fleet-capacity review.
18The primary term is over 84 months; a person should confirm the long term.
19The quote asks 1,200 HP per unit; this application is limited to 600 HP per unit.

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. Gas-engine sizing, pressure and term: Four gas-engine units sized, priced and contracted beyond their limits, with no fuel gas and a wrong monthly fee

The agent's request. Please quote 4 G3606 A4 gas-engine units of 2,400 HP each for gas gathering, at 3,500 psi discharge on a 24-month term, and a 25 percent discount. The customer does not supply fuel gas. The monthly fee is 150,000 dollars. It is ready to send.

Verdict: Blocked.

  • Unit horsepower above the driver maximum. The quote asks 2,400 HP per unit; this unit type tops out at 2,065 HP.
  • Discharge pressure above the limit. The quote asks 3,500 psi discharge; this unit and application allow 3,000 psi.
  • Large unit needs a longer term. Units above 1,000 HP are contracted for 36 months or more; the quote has 24 months.
  • Customer fuel gas missing. Gas-engine units run on fuel gas supplied by the customer; the quote has none.
  • Discount above the limit. The quote has a 25 percent discount; the maximum is 20.
  • Stated monthly fee does not match. The quote states a monthly fee of 150,000 dollars; the quoted units and services give a different figure.

2. Gas-engine sizing, pressure and term: The agent resubmits after fixing the errors

The agent's request. Please quote 4 G3612 A4 gas-engine units of 2,400 HP each for gas gathering, at 2,800 psi discharge on a 36-month term. The customer supplies fuel gas. The monthly fee is 163,200 dollars. It is ready to send.

Verdict: Allowed.

  • Fleet summary. 4 unit(s) at 2,400 HP each, 9,600 HP in total, gross monthly fee 163,200 dollars before a 0 percent discount (illustrative rates).

3. Electric units, power and treating: Three electric motor units with no grid power, an add-on that does not fit the application and a wrong monthly fee

The agent's request. Please quote 3 electric motor units of 3,400 HP each for multi-well gas lift, at 1,500 psi discharge on a 60-month term, with gas dehydration. Grid power is not available at the site. The monthly fee is 150,000 dollars. It is ready to send.

Verdict: Blocked.

  • Unit horsepower above the driver maximum. The quote asks 3,400 HP per unit; this unit type tops out at 3,000 HP.
  • Grid power missing. Electric motor and rotary screw units need grid power at the site; the quote has none.
  • Treating on a non-midstream application. Amine treating and gas dehydration are offered only with gas gathering or gas processing.
  • Stated monthly fee does not match. The quote states a monthly fee of 150,000 dollars; the quoted units and services give a different figure.

4. Electric units, power and treating: The agent resubmits after fixing the errors

The agent's request. Please quote 3 electric motor units of 2,800 HP each for gas processing, at 1,500 psi discharge on a 60-month term, with gas dehydration. Grid power is available at the site. The monthly fee is 132,000 dollars. It is ready to send.

Verdict: Allowed.

  • Fleet summary. 3 unit(s) at 2,800 HP each, 8,400 HP in total, gross monthly fee 132,000 dollars before a 0 percent discount (illustrative rates).

5. Rotary screw units: Six rotary screw units on a high-pressure application with a short term

The agent's request. Please quote 6 rotary screw units of 700 HP each for gas gathering, at 500 psi discharge on a 6-month term. Grid power is available at the site. The monthly fee is -1 dollars. It is ready to send.

Verdict: Blocked.

  • Unit horsepower above the driver maximum. The quote asks 700 HP per unit; this unit type tops out at 600 HP.
  • Rotary screw unit on a high-pressure application. Rotary screw units serve only low-pressure gathering, vapor recovery and wellhead gas lift.
  • Discharge pressure above the limit. The quote asks 500 psi discharge; this unit and application allow 350 psi.
  • Term too short. The primary term is 6 months; the minimum is 12.

6. Rotary screw units: The agent resubmits after fixing the errors

The agent's request. Please quote 6 rotary screw units of 550 HP each for low-pressure gathering, at 300 psi discharge on a 24-month term. Grid power is available at the site. The monthly fee is 72,600 dollars. It is ready to send.

Verdict: Allowed.

  • Fleet summary. 6 unit(s) at 550 HP each, 3,300 HP in total, gross monthly fee 72,600 dollars before a 0 percent discount (illustrative rates).

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 contract compression quote for a fleet of gas-engine, electric motor or rotary screw units with treating and cooling add-ons. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of unit sizing, application limits, term and utilities, and returns a verdict, every reason and the monthly fee it computed.
  2. I will start with the first request by the agent.
  3. The agent says. Please quote 4 G3606 A4 gas-engine units of 2,400 HP each for gas gathering, at 3,500 psi discharge on a 24-month term, and a 25 percent discount. The customer does not supply fuel gas. The rest of the request is on screen. The monthly fee is 150,000 dollars.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with six findings, all in one answer. The quote asks 2,400 HP per unit; this unit type tops out at 2,065 HP. The quote asks 3,500 psi discharge; this unit and application allow 3,000 psi. Units above 1,000 HP are contracted for 36 months or more; the quote has 24 months. 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 a stated monthly fee that must match the computed fee, a rules-based CPQ can do this only with workarounds.
  8. Now the agent resubmits.
  9. The corrected request. It changes the unit type to G3612 a4 gas-engine, the discharge pressure to 2,800, the term to 36 months, the customer fuel gas to yes, the discount to 0 percent and the monthly fee stated on the quote to 163,200.
  10. It calls the validator again.
  11. This time the validator clears it.
  12. All six earlier findings are cleared.
  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.