Predictika · Protein analysis consumables

An AI sales agent's Simple Western module order, checked before it goes out

An AI sales agent prepares an order for Simple Western separation modules and a detection module for a lab's Jess, Abby, Wes, Peggy Sue or Sally Sue instrument. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published product information and returns a verdict, every reason and the figures it computed.

Scope: Simple Western separation modules and detection modules for the Jess, Abby, Wes, Peggy Sue and Sally Sue: chemiluminescence or fluorescence, cartridge format, detection module and data points. See everything this validator covers

This validator models orders for Simple Western separation and detection modules, not just the scenarios shown below.

  • Instrument and module family — the Jess, Abby and Wes take 13 or 25 capillary cartridges (2 or 8 cartridges per module: 26, 104, 50 or 200 data points); the Peggy Sue and Sally Sue take modules of 5 boxes of 96 capillaries (480 data points).
  • Fluorescence and detection — fluorescence separation and detection modules are for the Jess; a fluorescence detection module must be used with a fluorescence separation module, while a fluorescence separation module also works with a chemiluminescence detection module. A detection module is sold separately, so every order needs one.
  • Range and data points — the 2-40, 12-230 and 66-440 kDa ranges; a 2-40 kDa module for a Peggy Sue or Sally Sue goes to a person to confirm, because the pages read list only 12-230 and 66-440 kDa for them. The data points the order states are compared with the modules and cartridge format ordered.

Any Simple Western module order that touches these rules is in scope — not only the scenarios pictured here. Not covered: prices (no price list is modeled, so this validator produces no price build-up or line-item quote), the Leo and its 600-capillary modules, the goat, human IgG, biotin, no-secondary, mouse IR and near-infrared detection modules, total protein and RePlex modules, charge-based assays, and assay kits.

The AI sales agentBuilds the module order 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
A fluorescence module quoted for an instrument that cannot run itOnly with care
The rule depends on the instrument on one line and the module type on another, so it needs a validation rule for each pairing.
The instrument, the separation module and the detection module are in one request and compared on every call.
A cartridge format that does not fit the instrumentOnly with care
A product rule per instrument family that lists the cartridge formats it takes, kept in step with the catalog.
The instrument and the cartridge format are checked together on every call.
A detection module that is missing, or does not match the separation moduleOnly with care
A required-item rule per kit; it works, but each pairing of fluorescence and chemiluminescence needs its own rule.
Every choice is in one request, so the missing or mismatched module is found whichever order the choices arrive.
Stated data points that must equal modules times cartridge formatOnly with workarounds
A stated figure is a free-entry field; a rule can compare it with a computed count, but the count depends on the cartridge format and has to be kept in step with the catalog.
The stated count travels with the order and is compared with the computed count on every call.
Every problem returned in one answerOnly with workarounds
Rules tend to fire as the order 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 separation module does not include a detection module; a detection module is sold separately and the order has none.
2A fluorescence detection module must be used with a fluorescence separation module.
3Fluorescence separation and detection modules are for the Jess (and Leo, which is not quoted here); the order uses another instrument.
4The Jess, Abby and Wes modules come in 13 or 25 capillary cartridges; the Peggy Sue and Sally Sue modules come as 5 boxes of 96 capillaries; the format ordered does not fit the instrument.
5The product pages read list 12-230 kDa and 66-440 kDa separation modules for the Peggy Sue and Sally Sue; the 2-40 kDa range should be confirmed with Bio-Techne.
6The order states 90 data points; the modules and cartridge format ordered give 100.
7The order states 101 data points; the modules and cartridge format ordered give 100.
8The order states 0 data points; the modules and cartridge format ordered give 100.
9The order states 50 data points; the modules and cartridge format ordered give 150.
10The order has 0 separation modules; at least 1 is needed.
11The order states 1 data point; the modules and cartridge format ordered give 960.
12The order states 7 data points; the modules and cartridge format ordered give 200.

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. Instrument and fluorescence: Fluorescence modules quoted for a Wes

The agent's request. Please quote 3 12-230 kDa fluorescence separation modules (8 cartridges of 25 capillaries, each) for a Wes, with the anti-rabbit IR fluorescence detection module. The order states 600 data points in total. It is ready to send.

Verdict: Blocked.

  • Fluorescence needs a Jess. Fluorescence separation and detection modules are for the Jess (and Leo, which is not quoted here); the order uses another instrument.

2. Instrument and fluorescence: The agent resubmits after fixing the errors

The agent's request. Please quote 3 12-230 kDa fluorescence separation modules (8 cartridges of 25 capillaries, each) for a Jess, with the anti-rabbit IR fluorescence detection module. The order states 600 data points in total. It is ready to send.

Verdict: Allowed.

  • Order summary. 3 separation modules with 600 data points in total.

3. Peggy Sue kit and detection: A Peggy Sue order with 25 capillary cartridges, a 2-40 kDa range and no detection module

The agent's request. Please quote 3 2-40 kDa chemiluminescence separation modules (8 cartridges of 25 capillaries, each) for a Peggy Sue, with no detection module. The order states 600 data points in total. It is ready to send.

Verdict: Blocked.

  • Detection module missing. The separation module does not include a detection module; a detection module is sold separately and the order has none.
  • Cartridge format does not fit the instrument. The Jess, Abby and Wes modules come in 13 or 25 capillary cartridges; the Peggy Sue and Sally Sue modules come as 5 boxes of 96 capillaries; the format ordered does not fit the instrument.
  • Range for Peggy Sue or Sally Sue to confirm. The product pages read list 12-230 kDa and 66-440 kDa separation modules for the Peggy Sue and Sally Sue; the 2-40 kDa range should be confirmed with Bio-Techne.

4. Peggy Sue kit and detection: The agent resubmits after fixing the errors

The agent's request. Please quote 3 2-40 kDa chemiluminescence separation modules (5 boxes of 96 capillaries, each) for a Peggy Sue, with the anti-mouse chemiluminescence detection module. The order states 1,440 data points in total. It is ready to send.

Verdict: Needs approval.

  • Range for Peggy Sue or Sally Sue to confirm. The product pages read list 12-230 kDa and 66-440 kDa separation modules for the Peggy Sue and Sally Sue; the 2-40 kDa range should be confirmed with Bio-Techne.
  • Order summary. 3 separation modules with 1,440 data points in total.

5. Peggy Sue kit and detection: The agent resubmits after fixing the errors

The agent's request. Please quote 3 12-230 kDa chemiluminescence separation modules (5 boxes of 96 capillaries, each) for a Peggy Sue, with the anti-mouse chemiluminescence detection module. The order states 1,440 data points in total. It is ready to send.

Verdict: Allowed.

  • Order summary. 3 separation modules with 1,440 data points in total.

6. Detection module and data points: A fluorescence detection module on a chemiluminescence separation module, with 500 data points stated

The agent's request. Please quote 3 66-440 kDa chemiluminescence separation modules (8 cartridges of 25 capillaries, each) for a Jess, with the anti-rabbit IR fluorescence detection module. The order states 500 data points in total. It is ready to send.

Verdict: Blocked.

  • Fluorescence detection needs a fluorescence separation module. A fluorescence detection module must be used with a fluorescence separation module.
  • Stated data points do not match. The order states 500 data points; the modules and cartridge format ordered give 600.

7. Detection module and data points: The agent resubmits after fixing the errors

The agent's request. Please quote 3 66-440 kDa fluorescence separation modules (8 cartridges of 25 capillaries, each) for a Jess, with the anti-rabbit IR fluorescence detection module. The order states 600 data points in total. It is ready to send.

Verdict: Allowed.

  • Order summary. 3 separation modules with 600 data points in total.

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 order for Simple Western separation modules and a detection module for a lab's Jess, Abby, Wes, Peggy Sue or Sally Sue instrument. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published product information and returns a verdict, every reason and the figures it computed.
  2. I will start with the first request by the agent.
  3. The agent says. Please quote 3 2-40 kDa chemiluminescence separation modules (8 cartridges of 25 capillaries, each) for a Peggy Sue, with no detection module. The order states 600 data points in total. The rest of the request is on screen.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with two findings and one approval, all in one answer. The separation module does not include a detection module; a detection module is sold separately and the order has none. The Jess, Abby and Wes modules come in 13 or 25 capillary cartridges; the Peggy Sue and Sally Sue modules come as 5 boxes of 96 capillaries; the format ordered does not fit the instrument.
  6. The validator returned two blocking findings and one approval 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 cartridge format that does not fit the instrument, a rules-based CPQ is error-prone for this.
  8. Now the agent resubmits.
  9. The corrected request. It changes the cartridge format to 5 boxes of 96 capillaries, the detection module to anti-mouse (chemiluminescence) and the data points the order states to 1,440.
  10. It calls the validator again.
  11. Not blocked, but held for a person.
  12. The two blocking findings are cleared; one approval remains for a person: range for Peggy Sue or Sally Sue to confirm.
  13. The agent resubmits once more.
  14. The revised request. It changes the size range to 12-230 kDa.
  15. It calls the validator once more.
  16. This time the validator clears it.
  17. The earlier finding is cleared, and the validator's figure matches the quote.
  18. Three problems caught in one call, fixed in two passes, 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.