Predictika · Ultrasensitive assay orders for Simoa analyzers

An AI sales agent's Simoa assay order, checked before it goes out

An AI sales agent prepares an order for a Simoa assay kit on an HD-X or SR-X analyzer: the kit, the sample type, the number of samples, the sample volume and the number of kits. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published assay menus and returns a verdict, every reason and the figures it computed.

Scope: Simoa HD-X and SR-X assay orders: Advantage, multiplex and Discovery kits, sample types, sample volume and kit quantity. See everything this validator covers

This validator models orders for 23 assay kits on the Simoa HD-X and SR-X analyzers, as listed on the public Quanterix HD-1/HD-X and SR-X assay menus (July 2021), not just the scenarios shown below.

  • Analyzer and assay menu — each kit must be on the menu of the selected analyzer. Some kits are on the HD-X menu only (for example Neurology 4-Plex E, the SARS-CoV-2 spike IgG kit, GM-CSF and the CA-125 Discovery kit), and catalog numbers can differ between analyzers (for example NF-light).
  • Sample types — each kit lists the sample types it is validated for (CSF, EDTA plasma, serum, and for MMP-9 on the SR-X menu, heparin plasma); an order with an unlisted sample type is blocked.
  • Sample volume and kits — the sample volume per sample must cover the menu volume for that kit, analyzer and sample type (multiplex neurology kits list a lower volume for CSF), the volume the order states must match the menu, and a Discovery kit processes up to 192 samples, so the number of kits must cover the planned samples.
  • Use and dilution — Simoa assays are for research use only; the menus list volumes for bench dilution and say on-instrument dilutions need more sample, so that choice goes to a person for approval.

Any order for these kits on the HD-X or SR-X that touches these rules is in scope — not only the scenarios pictured here. Not covered: prices (Quanterix does not publish a price list, so this validator produces no price build-up or line-item quote), kits and analyzers not named above (including the SP-X), Advantage kit sample capacity (not stated on the menus), mouse and other species kits, newer menu changes, and service plans.

The AI sales agentBuilds the assay 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 kit that is on one analyzer's menu but not the other'sOnly with care
A product rule per kit and analyzer. It works, but every menu change is another rule to maintain, and the HD-X and SR-X menus differ in kits and catalog numbers.		The analyzer and the kit are in one request and the pairing is checked against the menu on every call.
A sample type the kit is not listed forOnly with workarounds
The allowed sample types depend on the kit and on the analyzer together, so each kit needs its own cross-line rule.		Kit, analyzer and sample type are checked together, whatever order they arrive in.
Sample volume that depends on kit, analyzer and sample typeOnly with workarounds
The required volume changes with three choices at once (and is lower for CSF on multiplex kits); a lookup table and a comparison rule have to be built and kept current.		The required volume is computed from the menu data on every call and compared with the volume available and with the figure the order states.
Discovery kits that must cover the planned samplesOnly with care
A quantity check against a per-kit capacity, only for the Discovery class of kits; easy to miss for one product family.		Capacity is computed from the number of kits and compared with the planned samples, for Discovery kits only.
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 selected assay kit is not on the assay menu for the selected analyzer; the HD-X and SR-X assay menus differ.
2The sample type on the order is not listed for this assay on the selected analyzer menu.
3300 samples are planned, but the Discovery kits on the order process up to 192 samples (up to 192 samples per kit).
4193 samples are planned, but the Discovery kits on the order process up to 192 samples (up to 192 samples per kit).
5Each sample needs at least 32.5 microliters for this assay (menu volume at bench dilution), but only 30 microliters are available per sample.
6Each sample needs at least 25 microliters for this assay (menu volume at bench dilution), but only 24 microliters are available per sample.
7Each sample needs at least 32.5 microliters for this assay (menu volume at bench dilution), but only 6 microliters are available per sample.
8The order states 25 microliters per sample, but the assay menu lists 32.5 microliters for this assay, analyzer and sample type.
9The order states 32.5 microliters per sample, but the assay menu lists 25 microliters for this assay, analyzer and sample type.
10The order states 32.5 microliters per sample, but the assay menu lists 5 microliters for this assay, analyzer and sample type.
11Simoa assays are provided for research use only and are not for use in diagnostic procedures.
12The assay menu lists sample volumes for bench dilution and says on-instrument dilutions need higher volumes without giving the figure; a person must confirm the required volume with Quanterix.
13Each sample needs at least 18.2 microliters for this assay (menu volume at bench dilution), but only 10 microliters are available per sample.
14The order states 20 microliters per sample, but the assay menu lists 18.2 microliters for this assay, analyzer and sample type.

  

  

    
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. Neurology 4-Plex E: An SR-X order for the Neurology 4-Plex E kit on plasma

    
The agent's request. Please quote an order of the Neurology 4-Plex E kit on the Simoa SR-X for 96 EDTA plasma samples, with 1 kit and 50 microliters of sample available per sample, bench dilution, for research use. The order states that each sample needs 25 microliters. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Assay not on this analyzer's menu. The selected assay kit is not on the assay menu for the selected analyzer; the HD-X and SR-X assay menus differ.
    • 
    

    
2. Neurology 4-Plex E: The agent resubmits after fixing the errors

    
The agent's request. Please quote an order of the Neurology 4-Plex E kit on the Simoa HD-X for 96 EDTA plasma samples, with 1 kit and 50 microliters of sample available per sample, bench dilution, for research use. The order states that each sample needs 32.5 microliters. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. Catalog number 103,670; 96 samples planned; each sample needs 32.5 microliters.
    • 
    

    
3. Discovery kit for 300 serum samples: An HD-X order for 300 serum samples with one Discovery kit

    
The agent's request. Please quote an order of the alpha-Synuclein Discovery kit on the Simoa HD-X for 300 serum samples, with 1 kit and 15 microliters of sample available per sample, bench dilution, for research use. The order states that each sample needs 18.2 microliters. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Not enough Discovery kits. 300 samples are planned, but the Discovery kits on the order process up to 192 samples (up to 192 samples per kit).
    • 
      
  • Not enough sample volume. Each sample needs at least 18.2 microliters for this assay (menu volume at bench dilution), but only 15 microliters are available per sample.
    • 
    

    
4. Discovery kit for 300 serum samples: The agent resubmits after fixing the errors

    
The agent's request. Please quote an order of the alpha-Synuclein Discovery kit on the Simoa HD-X for 300 serum samples, with 2 kits and 15 microliters of sample available per sample, bench dilution, for research use. The order states that each sample needs 18.2 microliters. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Not enough sample volume. Each sample needs at least 18.2 microliters for this assay (menu volume at bench dilution), but only 15 microliters are available per sample.
    • 
    

    
5. Discovery kit for 300 serum samples: The agent resubmits after fixing the errors

    
The agent's request. Please quote an order of the alpha-Synuclein Discovery kit on the Simoa HD-X for 300 serum samples, with 2 kits and 25 microliters of sample available per sample, bench dilution, for research use. The order states that each sample needs 18.2 microliters. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. Catalog number 102,233; 300 samples planned; each sample needs 18.2 microliters.
    • 
    

    
6. pTau-231 on the SR-X: An SR-X pTau-231 order on plasma for diagnostic use

    
The agent's request. Please quote an order of the pTau-231 Advantage kit on the Simoa SR-X for 192 EDTA plasma samples, with 1 kit and 40 microliters of sample available per sample, bench dilution, for diagnostic use. The order states that each sample needs 25 microliters. It is ready to send.

    
Verdict: Blocked.

    
    
      
  • Sample type not listed for this assay. The sample type on the order is not listed for this assay on the selected analyzer menu.
    • 
      
  • Research use only. Simoa assays are provided for research use only and are not for use in diagnostic procedures.
    • 
    

    
7. pTau-231 on the SR-X: The agent resubmits after fixing the errors

    
The agent's request. Please quote an order of the pTau-231 Advantage kit on the Simoa SR-X for 192 CSF samples, with 1 kit and 40 microliters of sample available per sample, bench dilution, for research use. The order states that each sample needs 25 microliters. It is ready to send.

    
Verdict: Allowed.

    
    
      
  • Order summary. Catalog number 102,292; 192 samples planned; each sample needs 25 microliters.
    • 
    

  

  

    
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 Simoa assay kit on an HD-X or SR-X analyzer: the kit, the sample type, the number of samples, and more. Before it goes out, the agent sends it to Predictika, which checks it against a declarative model of the published assay menus and returns a verdict, every reason and the figures it computed.
    2. 
      
  2. I will start with the first request by the agent.
    3. 
      
  3. The agent says. Please quote an order of the alpha-Synuclein Discovery kit on the Simoa HD-X for 300 serum samples, with 1 kit and 15 microliters of sample available per sample. The order states that each sample needs 18.2 microliters. The rest of the request is on screen.
    4. 
      
  4. Before it goes out, the agent calls the validator.
    5. 
      
  5. Blocked, with two findings, all in one answer. 300 samples are planned, but the Discovery kits on the order process up to 192 samples (up to 192 samples per kit). Each sample needs at least 18.2 microliters for this assay (menu volume at bench dilution), but only 15 microliters are available per sample.
    6. 
      
  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. 
      
  7. What this shows: for sample volume that depends on kit, analyzer and sample type, a rules-based CPQ can do this only with workarounds.
    8. 
      
  8. Now the agent resubmits.
    9. 
      
  9. The corrected request. It changes the kits ordered to 2.
    10. 
      
  10. It calls the validator again.
    11. 
      
  11. Still blocked, with one finding, all in one answer. Each sample needs at least 18.2 microliters for this assay (menu volume at bench dilution), but only 15 microliters are available per sample.
    12. 
      
  12. One finding cleared. Still blocking: not enough sample volume.
    13. 
      
  13. The agent resubmits once more.
    14. 
      
  14. The revised request. It changes the sample available per sample to 25.
    15. 
      
  15. It calls the validator once more.
    16. 
      
  16. This time the validator clears it.
    17. 
      
  17. The earlier finding is cleared, and the validator's figure matches the quote.
    18. 
      
  18. Two 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.
    19.