​
Create Bulk Metrics API

Create multiple metrics simultaneously for an agent.

​
API Endpoint

MethodEndpoint
POSThttps://new-prod.vocera.ai/test_framework/v1/metrics-external/bulk_create/

​
Authentication

Include your API key in the request headers:

HeaderDescription
X-VOCERA-API-KEYYour API key obtained from the dashboard

​
Request Body

The request body should be an array of metric objects. Each metric object has the following parameters:

ParameterTypeRequiredDescription
namestringYesName of the metric
descriptionstringYesDescription of what the metric evaluates
agentintegerYesID of the agent to evaluate
eval_typestringYesType of metric (binary_workflow_adherence, binary_qualitative, continuous_qualitative, numeric, enum)
enum_valuesarrayNoList of possible values when eval_type is “enum”
audio_enabledbooleanNoWhether audio analysis is enabled. Defaults to false
prompt_enabledbooleanNoWhether to use a custom prompt. Defaults to false
promptstringNoCustom evaluation prompt template when prompt_enabled is true
evaluation_triggerstringNoTrigger type for evaluation (always, automatic, custom)
evaluation_trigger_promptstringNoCustom trigger prompt when evaluation_trigger is “custom”

​
Example Request Body

[

    {

        "name": "Introduction Clarity",

        "description": "This metric evaluates whether the AI voice agent clearly introduces itself...",

        "agent": 1,

        "eval_type": "binary_workflow_adherence"

    },

    {

        "name": "User Response Handling",

        "description": "This metric assesses whether the AI voice agent waits for user responses...",

        "agent": 1,

        "eval_type": "binary_workflow_adherence"

    }

]

​
Response

The API returns an array of created metric objects.

​
Response Fields

FieldTypeDescription
idintegerUnique identifier for the metric
agentintegerID of the associated agent
namestringName of the metric
descriptionstringDescription of the metric
eval_typestringType of metric
enum_valuesarrayList of possible enum values
audio_enabledbooleanWhether audio analysis is enabled
prompt_enabledbooleanWhether custom prompt is enabled
promptstringCustom evaluation prompt template
display_orderintegerOrder for displaying the metric
overall_scorenumberTotal testsets passed
total_scorenumberReviewed in total testsets

​
Example Response

[

    {

        "id": 49,

        "agent": 1,

        "name": "Introduction Clarity",

        "description": "This metric evaluates whether the AI voice agent clearly introduces itself...",

        "eval_type": "binary_workflow_adherence",

        "enum_values": [],

        "audio_enabled": false,

        "prompt_enabled": false,

        "prompt": "",

        "display_order": 20,

        "overall_score": null,

        "total_score": 35

    },

    {

        "id": 50,

        "agent": 1,

        "name": "User Response Handling",

        "description": "This metric assesses whether the AI voice agent waits for user responses...",

        "eval_type": "binary_workflow_adherence",

        "enum_values": [],

        "audio_enabled": false,

        "prompt_enabled": false,

        "prompt": "",

        "display_order": 21,

        "overall_score": null,

        "total_score": 35

    }

]

​
Code Examples

curl -X POST https://new-prod.vocera.ai/test_framework/v1/metrics-external/bulk_create/ \

  -H "X-VOCERA-API-KEY: <your-api-key-here>" \

  -H "Content-Type: application/json" \

  -d '[

    {

      "name": "Example Metric",

      "description": "Example description",

      "agent": 123,

      "eval_type": "binary_workflow_adherence"

    }

  ]'