Mom Test Rules Question Checker

Audit independently annotated MomTest-style question features; past-behavior vs hypothetical/leading prompts, not automatic NLP intent or interview validity. Caller independently verifies policy, evidence, dates and applicability; not legal/compliance advice or causal business-success prediction.

Description

Interview-question quality can be annotated for past specificity, leading language and hypothetical purchase framing.

Interview-question quality can be annotated for past specificity, leading language and hypothetical purchase framing.^[1]

Binary annotations support a review list but do not analyze the actual question text. Use this tool to calculate mom Test Rules Question Checker from the supplied measurements and assumptions.

When to use Mom Test Rules Question Checker

Use this tool to calculate mom Test Rules Question Checker from the supplied measurements and assumptions. Establish the business period, event definitions, jurisdiction or agreement edition, and independently documented evidence or comparison rubric.

How to use Mom Test Rules Question Checker and understand its results

Establish the business period, event definitions, jurisdiction or agreement edition, and independently documented evidence or comparison rubric.
Enter callerAnnotatedQuestionIds, askedAboutSpecificPastBehaviorFlags, containsLeadingComplimentPromptFlags, requestsHypotheticalPurchaseFlags, using the field meanings and rules below, then run the tool.
Read callerInterviewQuestionReviewIds. Interpret the fields using their units, signs and evidence conventions below.
If input validation fails, correct the reported field and run again. Before applying the result, check reference scope, model assumptions and any missing evidence or placeholder values.

Input field	Meaning	Value type	Requirement
callerAnnotatedQuestionIds	Caller annotated question ids	list of string	Required
askedAboutSpecificPastBehaviorFlags	Asked about specific past behavior flags; binary 0/1 under the definitions below	list of number	Required
containsLeadingComplimentPromptFlags	Contains leading compliment prompt flags; binary 0/1 under the definitions below	list of number	Required
requestsHypotheticalPurchaseFlags	Requests hypothetical purchase flags; binary 0/1 under the definitions below	list of number	Required

Enter nonempty unique question IDs and three aligned binary annotation lists: past-specific evidence, leading/compliment framing and hypothetical-purchase framing. Return IDs where past-specific=0 or either other flag=1. Annotations are treated as explicitly known; no raw text, NLP or question generation is used.

review={id_i:not pastSpecific_i or leading_i or hypotheticalPurchase_i}

Use the exact units, boundary rules, ordering and missing-evidence conventions above.

Output field	Meaning	Value type
callerInterviewQuestionReviewIds	Caller Interview Question Review Ids; follow the units, sign, ordering and evidence convention stated above	list of string

json

{
  "input": {
    "callerAnnotatedQuestionIds": [
      "q1",
      "q2"
    ],
    "askedAboutSpecificPastBehaviorFlags": [
      1,
      0
    ],
    "containsLeadingComplimentPromptFlags": [
      0,
      1
    ],
    "requestsHypotheticalPurchaseFlags": [
      0,
      1
    ]
  },
  "output": {
    "callerInterviewQuestionReviewIds": [
      "q2"
    ]
  }
}

Limitations and assumptions

Binary annotations support a review list but do not analyze the actual question text. Interpretation depends on the units, sampling scope and exact model described above.

All listed fields require explicit values. Unexpected fields, incorrect types, nonfinite numbers and sparse evidence arrays fail validation; the specific bounds and alignment requirements are stated above. Extremely large inputs or outputs can also be rejected. An input error is distinct from a successful result reporting false, no matches or missing evidence.

Alternative or Complementary methods

Use Problem Interview Discovery Question Bank for this related task: Problem interviews use questions grouped by the issue being explored.

Use YC Application Short Answer Quality Guide when its separate inputs and assumptions fit the question: Short application answers can be screened for length and independently annotated specificity.

References

Mom Test Rules Question Checker — tool.io

Similar or alternative tools

Problem Interview Discovery Question Bank
Problem interviews use questions grouped by the issue being explored.
YC Application Short Answer Quality Guide
Short application answers can be screened for length and independently annotated specificity.