Predictika · Dental sterilizer orders

An AI sales agent's dental sterilizer order, checked before it goes out

An AI sales agent prepares an order for a dental steam sterilizer for a practice, with a model, a sterilization cycle, a load, the longest instrument and the practice mains supply. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the product page rules and returns a verdict, every reason and the figures it computed.

Scope: W&H Lisa 17 and Lisa 22 dental steam sterilizers: load limits, usable chamber space, cycle time and mains supply. See everything this validator covers

This validator models orders for the two Lisa sterilizer sizes on the public W&H dental product page, not just the scenarios shown below.

  • Load limits — the maximum solid load (4.5 kg on the Lisa 17, 6 kg on the Lisa 22), porous load (1.5 kg and 2 kg) and container load (9 kg on both) against the load the practice plans to run.
  • Chamber space — the longest item against the usable chamber depth (312 mm on the Lisa 17, 400 mm on the Lisa 22) and the item width and height against 195 mm.
  • Supply and cycle time — a mains supply of 200 to 240 V AC at 50 or 60 Hz, and a cycle time stated on the order compared with the datasheet range for the selected model and cycle (B-Universal 134, B-Prion 134, B-Universal 121 or Fast Cycle).

Any order for these two sterilizers that touches these rules is in scope — not only the scenarios pictured here. Not covered: prices (W&H publishes no list prices on its product page, so this validator produces no price build-up or line-item quote), handpieces, treatment units and other W&H products, the Lisa Mini and the medical-line Lisa, accessories and their compatibility, and dealer terms.

The AI sales agentBuilds the sterilizer 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 load limit that differs by model and by load typeOnly with care
Each model has its own solid, porous and container limit, so each needs its own rule, and a new model adds more rules to maintain.
The model, the load type and the load are in one request and compared on every call.
A chamber depth that depends on the modelOnly with workarounds
The longest item must be compared with a value that depends on a different choice, so it takes a lookup that must be kept in step with the product page.
The model and the item length are in one request and the limit is worked out and compared on every call.
A stated cycle time that must sit in a range set by model and cycleOnly with workarounds
The range depends on two other choices, and the figure the agent states is free text or a separate field, so it takes an extra rule for every combination.
The stated figure is part of the request and is compared with the range for the chosen model and cycle 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 load of 4,501 g is above the 4,500 g maximum for this model and load type.
2The load of 6,001 g is above the 6,000 g maximum for this model and load type.
3The load of 1,501 g is above the 1,500 g maximum for this model and load type.
4The load of 2,001 g is above the 2,000 g maximum for this model and load type.
5The load of 9,001 g is above the 9,000 g maximum for this model and load type.
6The longest item is 313 mm; the usable chamber space of the selected model is 312 mm deep.
7The longest item is 401 mm; the usable chamber space of the selected model is 400 mm deep.
8The item cross-section of 196 mm is above the 195 mm usable chamber width and height.
9The mains supply of 199 V is outside the 200 to 240 V AC range.
10The mains supply of 241 V is outside the 200 to 240 V AC range.
11The mains frequency of 55 Hz is not 50 or 60 Hz.
12The quote states a cycle time of 42 minutes, but the datasheet range for the selected model and cycle is 21 to 41 minutes.
13The quote states a cycle time of 20 minutes, but the datasheet range for the selected model and cycle is 21 to 45 minutes.
14The quote states a cycle time of 62 minutes, but the datasheet range for the selected model and cycle is 36 to 61 minutes.
15The quote states a cycle time of 39 minutes, but the datasheet range for the selected model and cycle is 40 to 67 minutes.
16The quote states a cycle time of 21 minutes, but the datasheet range for the selected model and cycle is 13 to 20 minutes.
17The load of 5,000 g is above the 4,500 g maximum for this model and load type.
18The longest item is 350 mm; the usable chamber space of the selected model is 312 mm deep.
19The item cross-section of 200 mm is above the 195 mm usable chamber width and height.
20The mains supply of 110 V is outside the 200 to 240 V AC range.
21The quote states a cycle time of 10 minutes, but the datasheet range for the selected model and cycle is 21 to 41 minutes.

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. Prion cycle on the smaller model: A Lisa 17 on the prion cycle with a 5 kg solid load and a 350 mm item

The agent's request. Please quote a W&H Lisa 17 sterilizer for a solid load of 5,000 g on the B-Prion 134 cycle, with a longest item of 350 mm and a cross-section of 150 mm, on a 230 V, 50 Hz supply. The quote states a cycle time of 45 minutes. It is ready to send.

Verdict: Blocked.

  • Load above the maximum. The load of 5,000 g is above the 4,500 g maximum for this model and load type.
  • Item longer than the chamber. The longest item is 350 mm; the usable chamber space of the selected model is 312 mm deep.

2. Prion cycle on the smaller model: The agent resubmits after fixing the errors

The agent's request. Please quote a W&H Lisa 22 sterilizer for a solid load of 5,000 g on the B-Prion 134 cycle, with a longest item of 350 mm and a cross-section of 150 mm, on a 230 V, 50 Hz supply. The quote states a cycle time of 45 minutes. It is ready to send.

Verdict: Allowed.

  • Order summary. Load of 5,000 g and a longest item of 350 mm; the selected model takes up to 6,000 g of this load type and items up to 400 mm deep; the cycle runs 36 to 61 minutes.

3. Load, chamber, supply and cycle time: A Lisa 22 on the 121 degree cycle with a 2.5 kg porous load, a 420 mm item, a 110 V supply and a 75 minute cycle

The agent's request. Please quote a W&H Lisa 22 sterilizer for a porous load of 2,500 g on the B-Universal 121 cycle, with a longest item of 420 mm and a cross-section of 200 mm, on a 110 V, 60 Hz supply. The quote states a cycle time of 75 minutes. It is ready to send.

Verdict: Blocked.

  • Load above the maximum. The load of 2,500 g is above the 2,000 g maximum for this model and load type.
  • Item longer than the chamber. The longest item is 420 mm; the usable chamber space of the selected model is 400 mm deep.
  • Item too wide or tall for the chamber. The item cross-section of 200 mm is above the 195 mm usable chamber width and height.
  • Mains voltage outside 200 to 240 V. The mains supply of 110 V is outside the 200 to 240 V AC range.
  • Stated cycle time outside the datasheet range. The quote states a cycle time of 75 minutes, but the datasheet range for the selected model and cycle is 40 to 72 minutes.

4. Load, chamber, supply and cycle time: The agent resubmits after fixing the errors

The agent's request. Please quote a W&H Lisa 22 sterilizer for a porous load of 2,000 g on the B-Universal 121 cycle, with a longest item of 400 mm and a cross-section of 200 mm, on a 110 V, 60 Hz supply. The quote states a cycle time of 70 minutes. It is ready to send.

Verdict: Blocked.

  • Item too wide or tall for the chamber. The item cross-section of 200 mm is above the 195 mm usable chamber width and height.
  • Mains voltage outside 200 to 240 V. The mains supply of 110 V is outside the 200 to 240 V AC range.

5. Load, chamber, supply and cycle time: The agent resubmits after fixing the errors

The agent's request. Please quote a W&H Lisa 22 sterilizer for a porous load of 2,000 g on the B-Universal 121 cycle, with a longest item of 400 mm and a cross-section of 190 mm, on a 230 V, 60 Hz supply. The quote states a cycle time of 70 minutes. It is ready to send.

Verdict: Allowed.

  • Order summary. Load of 2,000 g and a longest item of 400 mm; the selected model takes up to 2,000 g of this load type and items up to 400 mm deep; the cycle runs 40 to 72 minutes.

6. Container load, supply frequency and fast cycle: A Lisa 17 fast cycle with a 9.5 kg container load, a 55 Hz supply and a 25 minute cycle

The agent's request. Please quote a W&H Lisa 17 sterilizer for a container load of 9,500 g on the Fast Cycle cycle, with a longest item of 300 mm and a cross-section of 180 mm, on a 230 V, 55 Hz supply. The quote states a cycle time of 25 minutes. It is ready to send.

Verdict: Blocked.

  • Load above the maximum. The load of 9,500 g is above the 9,000 g maximum for this model and load type.
  • Mains frequency not 50 or 60 Hz. The mains frequency of 55 Hz is not 50 or 60 Hz.
  • Stated cycle time outside the datasheet range. The quote states a cycle time of 25 minutes, but the datasheet range for the selected model and cycle is 13 to 20 minutes.

7. Container load, supply frequency and fast cycle: The agent resubmits after fixing the errors

The agent's request. Please quote a W&H Lisa 17 sterilizer for a container load of 9,000 g on the Fast Cycle cycle, with a longest item of 300 mm and a cross-section of 180 mm, on a 230 V, 50 Hz supply. The quote states a cycle time of 15 minutes. It is ready to send.

Verdict: Allowed.

  • Order summary. Load of 9,000 g and a longest item of 300 mm; the selected model takes up to 9,000 g of this load type and items up to 312 mm deep; the cycle runs 13 to 20 minutes.

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 a dental steam sterilizer for a practice, with a model, a sterilization cycle. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the product page rules 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 a W&H Lisa 22 sterilizer for a porous load of 2,500 g on the B-Universal 121 cycle, with a longest item of 420 mm and a cross-section of 200 mm. The quote states a cycle time of 75 minutes. The rest of the request is on screen.
  4. Before it goes out, the agent calls the validator.
  5. Blocked, with five findings, all in one answer. The load of 2,500 g is above the 2,000 g maximum for this model and load type. The longest item is 420 mm; the usable chamber space of the selected model is 400 mm deep. The item cross-section of 200 mm is above the 195 mm usable chamber width and height. The other two are on screen.
  6. The validator returned five 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 cycle time that must sit in a range set by model and cycle, a rules-based CPQ can do this only with workarounds.
  8. Now the agent resubmits.
  9. The corrected request. It changes the load to 2,000 g, the longest item to 400 mm and the stated cycle time as to 70 minutes.
  10. It calls the validator again.
  11. Still blocked, with two findings, all in one answer. The item cross-section of 200 mm is above the 195 mm usable chamber width and height. The mains supply of 110 V is outside the 200 to 240 V AC range.
  12. Three findings cleared. Still blocking: item too wide or tall for the chamber and mains voltage outside 200 to 240 V.
  13. The agent resubmits once more.
  14. The revised request. It changes the item width and height to 190 mm and the mains supply to 230 V.
  15. It calls the validator once more.
  16. This time the validator clears it.
  17. Both earlier findings are cleared, and the validator's figure matches the quote.
  18. Five 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.