---
title: "POST /v1/{+parent}/qaQuestions"
method: POST
path: "/v1/{+parent}/qaQuestions"
tags: ["projects"]
---

# POST /v1/{+parent}/qaQuestions

`POST /v1/{+parent}/qaQuestions`

Create a QaQuestion.

## Path parameters

- `parent` string, required

## Query parameters

- `qaQuestionId` string

## Request body

- GoogleCloudContactcenterinsightsV1QaQuestion — A single question to be scored by the Insights QA feature.
  - `predefinedQuestionConfig` GoogleCloudContactcenterinsightsV1QaQuestionPredefinedQuestionConfig — Configuration for a predefined question. This field will only be set if the Question Type is predefined.
    - `type` 'PREDEFINED_QUESTION_TYPE_UNSPECIFIED' | 'CONVERSATION_OUTCOME' | 'CONVERSATION_OUTCOME_ESCALATION_INITIATOR_ROLE' — The type of the predefined question.
  - `tuningMetadata` GoogleCloudContactcenterinsightsV1QaQuestionTuningMetadata — Metadata about the tuning operation for the question. Will only be set if a scorecard containing this question has been tuned.
    - `datasetValidationWarnings` string[] — A list of any applicable data validation warnings about the question's feedback labels.
    - `tuningError` string — Error status of the tuning operation for the question. Will only be set if the tuning operation failed.
    - `totalValidLabelCount` string, int64 — Total number of valid labels provided for the question at the time of tuining.
  - `abbreviation` string — Short, descriptive string, used in the UI where it's not practical to display the full question body. E.g., "Greeting".
  - `qaQuestionDataOptions` GoogleCloudContactcenterinsightsV1QaQuestionQaQuestionDataOptions — Options for configuring the data used to generate the QA question.
    - `conversationDataOptions` GoogleCloudContactcenterinsightsV1ConversationDataOptions — Options for configuring what metadata is included in the conversation data used in QAI and Discovery Engine.
      - `includeDialogflowInteractionData` boolean — Whether to include the per turn Dialogflow interaction data in conversation transcript.
  - `answerChoices` GoogleCloudContactcenterinsightsV1QaQuestionAnswerChoice[] — A list of valid answers to the question, which the LLM must choose from.
    - `key` string — A short string used as an identifier.
    - `strValue` string — String value.
    - `numValue` number, double — Numerical value.
    - `boolValue` boolean — Boolean value.
    - `naValue` boolean — A value of "Not Applicable (N/A)". If provided, this field may only be set to `true`. If a question receives this answer, it will be excluded from any score calculations.
    - `score` number, double — Numerical score of the answer, used for generating the overall score of a QaScorecardResult. If the answer uses na_value, this field is unused.
  - `answerInstructions` string — Instructions describing how to determine the answer.
  - `questionType` 'QA_QUESTION_TYPE_UNSPECIFIED' | 'CUSTOMIZABLE' | 'PREDEFINED' — The type of question.
  - `questionBody` string — Question text. E.g., "Did the agent greet the customer?"
  - `createTime` string, google-datetime — Output only. The time at which this question was created.
  - `updateTime` string, google-datetime — Output only. The most recent time at which the question was updated.
  - `name` string — Identifier. The resource name of the question. Format: projects/{project}/locations/{location}/qaScorecards/{qa_scorecard}/revisions/{revision}/qaQuestions/{qa_question}
  - `tags` string[] — Questions are tagged for categorization and scoring. Tags can either be: - Default Tags: These are predefined categories. They are identified by their string value (e.g., "BUSINESS", "COMPLIANCE", and "CUSTOMER"). - Custom Tags: These are user-defined categories. They are identified by their full resource name (e.g., projects/{project}/locations/{location}/qaQuestionTags/{qa_question_tag}). Both default and custom tags are used to group questions and to influence the scoring of each question.
  - `order` integer — Defines the order of the question within its parent scorecard revision.
  - `metrics` GoogleCloudContactcenterinsightsV1QaQuestionMetrics — A wrapper representing metrics calculated against a test-set on a LLM that was fine tuned for this question.
    - `accuracy` number, double — Output only. Accuracy of the model. Measures the percentage of correct answers the model gave on the test set.

## Response `200`

Successful response

---

[API](https://skmtc.net/google/apis/contactcenterinsights.md) · [All operations](https://skmtc.net/google/apis/contactcenterinsights/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/google/contactcenterinsights/versions/e071ddf4dfc3/schema)