Predictika · CPQ subscription quotes

An AI sales agent's Advantage CPQ subscription quote, checked before it goes out

An AI sales agent prepares a subscription quote for Conga Advantage CPQ: the Accelerate or Transform edition, Admin, User and Approver seats, add-ons, quote size, create volume, storage, sandboxes and term. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of how the editions and add-ons work and returns a verdict, every reason and the seat figures it computed.

Scope: Conga Advantage CPQ, Accelerate and Transform editions: seats, add-ons, quote size, quote and cart creates, storage, AiMe actions, sandboxes and term. See everything this validator covers

This validator models Conga Advantage CPQ subscription quotes as described on the public Conga service descriptions page, not just the scenarios shown underneath.

  • Editions and add-ons — Promotions, Rebate Set Up and Order Management are add-ons on Accelerate and included in Transform; Digital Commerce Transactions, Partner Commerce users and Full Sandbox are add-ons on both.
  • Seats — Admin, User and Approver / Read Only seats; at least one Admin and one User seat; Approver and Read Only seats do not count toward the allowances; the seat total a quote states against the seat lines.
  • Volumes and storage — performance quoting up to 1,000 lines (Accelerate) or 10,000 lines (Transform), 300 quote and cart creates per user a year (pooled, with the CPQ High Volume add-on for more), and 40 MB of data and 4 GB of file storage per Admin or User seat.
  • AiMe actions, sandboxes and term — 120 AiMe actions a year for Admin and User seats, one production and two partial sandboxes, and a subscription term of 1 to 5 years.
  • Approvals — AiMe actions above the included 120, more than 250 seats, and Digital Commerce quoted without implementation services go to a person.

Any Advantage CPQ quote that touches these rules is in scope — not only the scenarios pictured here. Not covered: Conga CLM, Smart CPQ, Revenue Lifecycle Cloud CPQ, billing and other Conga products. This validator models no prices, because Conga publishes none, so the page shows no price build-up.

The AI sales agentBuilds the Advantage CPQ subscription quote from the conversation with the customer 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
Add-ons that are included in one editionOnly with care
Promotions, Rebate Set Up and Order Management are included in Transform but sold separately on Accelerate, so each needs a rule keyed to the edition so an included add-on is not quoted twice.
The edition and every add-on are in one request and checked together on every call.
Allowances that depend on seats and add-onsOnly with care
Quote size, creates and storage limits depend on the edition, the seat count and the add-ons, so each limit needs its own rule that reads several fields.
The edition, the seats and the volumes the customer needs are in one request and compared with the allowances on every call.
Add-ons the customer needs but the quote lacksOnly with care
Partner users need Partner Commerce and a needed sandbox needs the Full Sandbox add-on, which is a separate rule for each pair of fields.
What the customer needs and what is quoted are fields of the same request and are checked together.
A stated seat total that must match the seat linesOnly with workarounds
The total is built from three seat types, so a roll-up field and a separate rule are needed to compare it with the figure the quote states.
The stated total is a field of the request and is compared with the sum of the seat lines in the same pass.
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 needs at least 1 Admin seat and 1 User seat; it has 0 Admin and 20 User.
2The customer needs 3,000 quote/cart creates a year; 300 per Admin/User seat is included and the CPQ High Volume add-on is not quoted.
3The customer needs 500 MB of data storage; 40 MB per Admin/User seat is included.
4The customer needs 50 GB of file storage; 4 GB per Admin/User seat is included.
5Promotions, Rebate Setup and Order Management are included in Transform; they should not be quoted as add-ons.
6The customer needs quotes of 1,001 lines; the quoted edition and add-ons allow up to 1,000.
7The customer needs a full sandbox; it is an add-on and is not on the quote.
8The quote has 50 partner users and no Partner Commerce add-on.
9The subscription term is 0 years; this model allows 1 to 5 years.
10The quote states 25 seats in total; the seat lines add up to 27.
11The customer needs 121 AiMe actions a year; 120 are included. A person should confirm how the extra actions are provided.
12The quote has 257 seats; more than 250 needs a sales review.
13Digital Commerce Transactions are quoted without implementation services; a person should confirm who sets them up.

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. Quote size and partner users: An Accelerate quote with Promotions, large quotes and 40 partner users

The agent's request. Please quote Conga Advantage CPQ Accelerate for 2 Admin, 20 User and 5 Approver / Read Only seats on a 3-year term. It includes Promotions. The customer needs quotes of up to 3,000 lines, 3,000 quote and cart creates a year and 40 partner users. It is ready to send.

Verdict: Blocked.

  • Performance quoting limit exceeded. The customer needs quotes of 3,000 lines; the quoted edition and add-ons allow up to 1,000.
  • Partner users without Partner Commerce. The quote has 40 partner users and no Partner Commerce add-on.

2. Quote size and partner users: The agent resubmits after fixing the errors

The agent's request. Please quote Conga Advantage CPQ Transform for 2 Admin, 20 User and 5 Approver / Read Only seats on a 3-year term. It includes Partner Commerce. The customer needs quotes of up to 3,000 lines, 3,000 quote and cart creates a year and 40 partner users. It is ready to send.

Verdict: Allowed.

  • Seat summary. 22 Admin/User seat(s) and 27 seat(s) in total; quote performance limit 10,000 lines.

3. Included add-ons and sandbox: A Transform quote with Promotions still quoted as an add-on and a full sandbox the customer needs

The agent's request. Please quote Conga Advantage CPQ Transform for 2 Admin, 20 User and 5 Approver / Read Only seats on a 3-year term. It includes Promotions. The customer needs quotes of up to 800 lines, 3,000 quote and cart creates a year and a full sandbox. It is ready to send.

Verdict: Blocked.

  • Add-on already included in Transform. Promotions, Rebate Setup and Order Management are included in Transform; they should not be quoted as add-ons.
  • Full sandbox needed but not quoted. The customer needs a full sandbox; it is an add-on and is not on the quote.

4. Included add-ons and sandbox: The agent resubmits after fixing the errors

The agent's request. Please quote Conga Advantage CPQ Transform for 2 Admin, 20 User and 5 Approver / Read Only seats on a 3-year term. It includes a Full Sandbox. The customer needs quotes of up to 800 lines, 3,000 quote and cart creates a year, a full sandbox and 120 AiMe actions a year. It is ready to send.

Verdict: Allowed.

  • Seat summary. 22 Admin/User seat(s) and 27 seat(s) in total; quote performance limit 10,000 lines.

5. Seat total and create volume: A quote whose stated seat total does not match the seat lines, for a high create volume

The agent's request. Please quote Conga Advantage CPQ Accelerate for 2 Admin, 20 User and 5 Approver / Read Only seats on a 3-year term. The customer needs quotes of up to 800 lines and 12,000 quote and cart creates a year. The quote states 30 seats in total. It is ready to send.

Verdict: Blocked.

  • Quote and cart creates exceed the pooled allowance. The customer needs 12,000 quote/cart creates a year; 300 per Admin/User seat is included and the CPQ High Volume add-on is not quoted.
  • Stated seat total does not match. The quote states 30 seats in total; the seat lines add up to 27.

6. Seat total and create volume: The agent resubmits after fixing the errors

The agent's request. Please quote Conga Advantage CPQ Accelerate for 2 Admin, 20 User and 5 Approver / Read Only seats on a 3-year term. It includes CPQ High Volume. The customer needs quotes of up to 800 lines and 12,000 quote and cart creates a year. The quote states 27 seats in total. It is ready to send.

Verdict: Allowed.

  • Seat summary. 22 Admin/User seat(s) and 27 seat(s) in total; quote performance limit 1,000 lines.

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 Conga Advantage CPQ: the Accelerate or Transform edition, Admin, User and Approver seats, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of how the editions and add-ons work and returns a verdict, every reason and the seat figures it computed.
  2. I will start with the first request by the agent.
  3. The agent says. Please quote Conga Advantage CPQ Accelerate for 2 Admin, 20 User and 5 Approver / Read Only seats on a 3-year term. It includes Promotions. 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. The customer needs quotes of 3,000 lines; the quoted edition and add-ons allow up to 1,000. The quote has 40 partner users and no Partner Commerce add-on.
  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 add-ons the customer needs but the quote lacks, a rules-based CPQ is error-prone for this.
  8. Now the agent resubmits.
  9. The corrected request. It changes the edition to transform. It sets the Partner Commerce to quoted. It removes the promotions.
  10. It calls the validator again.
  11. This time the validator clears it.
  12. Both earlier findings are cleared.
  13. 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.