Predictika · Integration platform subscription quotes

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

An AI sales agent prepares an annual subscription quote for an integration and automation platform, with the edition, the term, the tasks a year, the collaborators and recipes, the environments and on-prem agent groups, the add-ons, the recipe concurrency, the discount and the annual total the quote states. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the edition and add-on rules and returns a verdict, every reason and the annual total it computed.

Scope: Integration platform subscription quotes: the Standard, Business, Enterprise and Workato One editions, add-ons, workspace limits, task minimums, high-volume recipes, terms, discounts and the annual total the quote states. See everything this validator covers

This validator models Workato platform subscription quotes, not just the scenarios shown below.

  • Editions and add-ons — which add-ons each edition can buy: Workbot, Recipe IQ, Insights, multiple environments, enterprise security, premium connectors, on-prem agent groups, high-volume recipes and Agent Studio.
  • Limits and minimums — the workspace limits on collaborators, recipes, on-prem groups and agents, the task minimum of each edition, the one-to-three-year term and the discount ceiling.
  • Price and referrals — the annual total stated against the annual total computed, and a person's review for larger discounts, recipe concurrency above the default and very large task volumes.

Any platform subscription quote that touches these rules is in scope — not only the scenarios pictured here. Not covered: embedded integration, the self-service plans, support tiers and professional services. The edition and add-on names and the workspace limits follow Workato's public documentation; which add-ons each edition may buy, the task minimums, the term, the discount thresholds, the review thresholds and every price are modeled from comparable integration platforms and are not published by Workato, so every figure here is illustrative.

The AI sales agentBuilds the subscription 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
Add-ons that depend on the editionOnly with care
Workbot, premium connectors, on-prem agents, Agent Studio and the security add-on are each allowed on some editions and not others, so every add-on rule must test the edition.
The edition and every add-on are fields of one request and are checked together on every call.
Workspace limits that apply to every editionOnly with care
Collaborators, recipes, on-prem groups and agents per group each have a limit, so each limit is its own rule.
Each limit is a separate finding, and all of them are returned together.
Volume rules that depend on the editionOnly with workarounds
High-volume recipes need a higher edition and at least five million tasks, and each edition has a task minimum, so two quantity rules must read the edition.
The edition and both task counts are compared on every call.
A stated annual total that must match the price build-upOnly with workarounds
The total chains the edition, the tasks, the add-ons and the discount, so a separate rule must recompute it and compare it with the stated figure.
The stated total is a field of the request and is compared with the computed total on every call.
Referrals for discounts, concurrency and volumeOnly with workarounds
A review depends on the discount, the concurrency and the task volume together, on top of the blocking rules.
The referrals are separate findings returned together with the blocking ones.

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 101 collaborators; a workspace allows 100.
2The customer needs 5,001 recipes; a workspace allows 5,000.
3The quote has 21 on-prem agent groups; a workspace allows 20.
4The quote has 11 agents in a group; a group allows 10.
5On-prem agents are not offered with the Standard edition.
62 environments are quoted; Standard and Business need the multi-environment add-on for more than one.
7The multi-environment add-on is not offered with the Standard edition.
8Agent Studio is included only with Workato One.
9Workbot for Slack and Teams is not offered with the Standard edition.
10Premium connectors are not offered with the Standard edition.
11High-volume recipes need Business or higher and at least 5 million tasks a year; the quote has 4 million.
12High-volume recipes need Business or higher and at least 5 million tasks a year; the quote has 6 million.
13The quote has 4 million tasks a year; this edition needs at least 5 million.
14The enterprise security add-on is sold only with Business; Enterprise and Workato One include it and Standard does not offer it.
15The quote has a 4 year term; terms run one to three years.
16A discount of 25 percent needs sales leadership approval.
17The quote has a 35 percent discount; the ceiling is 30 percent.
18The quote states an annual total of 150,000 dollars; the quoted items give 206,100 dollars.
19The customer needs recipe concurrency of 31; the standard limit is 30 and a higher limit must be requested from Customer Success.
20The quote covers 50 million tasks a year or more; a deal desk review is needed.
21The quote states an annual total of 100,000 dollars; the quoted items give 48,000 dollars.

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. Edition and add-ons: A Standard quote with Workbot, premium connectors, on-prem agents, Agent Studio and 120 collaborators

The agent's request. Please quote the Standard edition for 1 year with 2 million tasks a year, 120 collaborators and 800 recipes, in 3 environments, with Workbot, Agent Studio, 2 premium connectors, 2 on-prem agent groups of up to 2 agents and high-volume recipes for 3 million tasks. The recipe concurrency needed is 20 and the discount is 10 percent. The annual total stated on the quote is 187,800 dollars. It is ready to send.

Verdict: Blocked.

  • Collaborators over the workspace limit. The quote needs 120 collaborators; a workspace allows 100.
  • On-prem agent not in this edition. On-prem agents are not offered with the Standard edition.
  • Several environments need the add-on. 3 environments are quoted; Standard and Business need the multi-environment add-on for more than one.
  • Agent Studio only with Workato One. Agent Studio is included only with Workato One.
  • Workbot not on Standard. Workbot for Slack and Teams is not offered with the Standard edition.
  • Premium connectors not on Standard. Premium connectors are not offered with the Standard edition.
  • High-volume recipe rules. High-volume recipes need Business or higher and at least 5 million tasks a year; the quote has 3 million.
  • Stated annual total does not match. The quote states an annual total of 187,800 dollars; the quoted items give 120,600 dollars.

2. Edition and add-ons: The agent resubmits after fixing the errors

The agent's request. Please quote the Workato One edition for 1 year with 8 million tasks a year, 100 collaborators and 800 recipes, in 3 environments, with Workbot, Agent Studio, 2 premium connectors, 2 on-prem agent groups of up to 2 agents and high-volume recipes for 6 million tasks. The recipe concurrency needed is 20 and the discount is 10 percent. The annual total stated on the quote is 307,800 dollars. It is ready to send.

Verdict: Allowed.

  • Price summary. Annual total 307,800 dollars (list 342,000 dollars before discount), contract total 307,800 dollars over 1 year(s).

3. Term, environments and discount: A Business quote on a four-year term with two environments and a 35 percent discount

The agent's request. Please quote the Business edition for 4 years with 3 million tasks a year, 40 collaborators and 500 recipes, in 2 environments, with Insights, the enterprise security add-on and 2 on-prem agent groups of up to 12 agents. The recipe concurrency needed is 35 and the discount is 35 percent. The annual total stated on the quote is 91,100 dollars. It is ready to send.

Verdict: Blocked.

  • On-prem agents per group over the limit. The quote has 12 agents in a group; a group allows 10.
  • Several environments need the add-on. 2 environments are quoted; Standard and Business need the multi-environment add-on for more than one.
  • Term over three years. The quote has a 4 year term; terms run one to three years.
  • Discount over the ceiling. The quote has a 35 percent discount; the ceiling is 30 percent.
  • Stated annual total does not match. The quote states an annual total of 91,100 dollars; the quoted items give 100,100 dollars.
  • Recipe concurrency above default. The customer needs recipe concurrency of 35; the standard limit is 30 and a higher limit must be requested from Customer Success.

4. Term, environments and discount: The agent resubmits after fixing the errors

The agent's request. Please quote the Business edition for 3 years with 3 million tasks a year, 40 collaborators and 500 recipes, in 2 environments, with Insights, the multi-environment add-on, the enterprise security add-on and 2 on-prem agent groups of up to 10 agents. The recipe concurrency needed is 35 and the discount is 25 percent. The annual total stated on the quote is 130,500 dollars. It is ready to send.

Verdict: Needs approval.

  • Discount needs approval. A discount of 25 percent needs sales leadership approval.
  • Recipe concurrency above default. The customer needs recipe concurrency of 35; the standard limit is 30 and a higher limit must be requested from Customer Success.
  • Price summary. Annual total 130,500 dollars (list 174,000 dollars before discount), contract total 391,500 dollars over 3 year(s).

5. Task minimum and workspace limits: An Enterprise quote with four million tasks, the security add-on and 22 on-prem agent groups

The agent's request. Please quote the Enterprise edition for 2 years with 4 million tasks a year, 80 collaborators and 5,200 recipes, in 3 environments, with Workbot, the enterprise security add-on and 22 on-prem agent groups of up to 4 agents. The recipe concurrency needed is 25 and the discount is 10 percent. The annual total stated on the quote is 491,100 dollars. It is ready to send.

Verdict: Blocked.

  • Recipes over the workspace limit. The customer needs 5,200 recipes; a workspace allows 5,000.
  • On-prem groups over the limit. The quote has 22 on-prem agent groups; a workspace allows 20.
  • Tasks below the edition minimum. The quote has 4 million tasks a year; this edition needs at least 5 million.
  • Enterprise security add-on only on Business. The enterprise security add-on is sold only with Business; Enterprise and Workato One include it and Standard does not offer it.
  • Stated annual total does not match. The quote states an annual total of 491,100 dollars; the quoted items give 441,000 dollars.

6. Task minimum and workspace limits: The agent resubmits after fixing the errors

The agent's request. Please quote the Enterprise edition for 2 years with 6 million tasks a year, 80 collaborators and 5,000 recipes, in 3 environments, with Workbot and 20 on-prem agent groups of up to 4 agents. The recipe concurrency needed is 25 and the discount is 10 percent. The annual total stated on the quote is 431,100 dollars. It is ready to send.

Verdict: Allowed.

  • Price summary. Annual total 431,100 dollars (list 479,000 dollars before discount), contract total 862,200 dollars over 2 year(s).

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 an annual subscription quote for an integration and automation platform, with the edition, the term. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the edition and add-on rules and returns a verdict, every reason and the annual total it computed.
  2. I will start with the first request by the agent.
  3. The agent says. Please quote the Standard edition for 1 year with 2 million tasks a year, 120 collaborators and 800 recipes, in 3 environments. The recipe concurrency needed is 20 and the discount is 10 percent. The rest of the request is on screen. The annual total stated on the quote is 187,800 dollars.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with eight findings, all in one answer. The quote needs 120 collaborators; a workspace allows 100. On-prem agents are not offered with the Standard edition. 3 environments are quoted; Standard and Business need the multi-environment add-on for more than one. The other five are on screen.
  6. The validator returned eight 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 and against the stated total.
  7. What this shows: for a stated annual total that must match the price build-up, a rules-based CPQ can do this only with workarounds.
  8. Now the agent resubmits.
  9. The corrected request. It changes the edition to Workato One, the tasks a year to 8 millions, the high-volume recipe tasks to 6 millions, the collaborators to 100 and the annual total stated on the quote to 307,800 dollars.
  10. It calls the validator again.
  11. This time the validator clears it.
  12. All eight earlier findings are cleared.
  13. Eight 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.