POST /test_framework/v1/metrics/generate_clean_description/

URL-friendly unique identifier in snake_case format. Example: "customer_satisfaction_1562"

Name of the metric. Example: "Customer Satisfaction" or "Appointment Booking"

Description of what the metric measures. Example: "Measures how satisfied customers are with the service provided"

Type of metric

• basic - Basic (Deprecated in favor of LLM Judge)
• custom_prompt - Custom Prompt ( Deprecated in favor of LLM Judge)
• custom_code - Custom Code
• llm_judge - LLM Judge

• binary - Binary
• continuous_qualitative - Continuous Qualitative
• numeric - Numeric
• enum - Enum

Whether this metric requires audio analysis. Example: true or false

Evaluation prompt for the metric. Example: "Evaluate customer satisfaction based on conversation"

• always - Always
• automatic - Automatic
• custom - Custom

Type of trigger evaluation: LLM judge or custom code. Only used when evaluation_trigger is CUSTOM. Example: "llm_judge" or "custom_code"

• llm_judge - LLM Judge
• custom_code - Custom Code

Evaluation trigger prompt for the metric. Example: "Evaluate metric only if call ended reason is main-agent-ended-call"

Python custom code to determine metric relevance. Code should set _result (bool) and _explanation (str). Example:

_result = True
_explanation = "Metric is relevant"
if "call_end_reason" in data and data["call_end_reason"] == "customer-hung-up":
    _result = False
    _explanation = "Customer hung up, metric not applicable"

Priority assignment prompt for the metric.

The overall score for this metric across all test sets

The total score for this metric

Knowledge base files associated with this metric

Enable this metric for observability. Example: true or false

Enable this metric for simulations. Example: true or false

Enable sampling for this metric using its sample_rate, or the project sample rate when unset

Sampling rate for this metric (0.0 to 1.0). Overrides the project sample rate when set.

Enable alerts for this metric when it fails (value=false). Only applicable to binary metrics (eval_type=binary). For other metric types, use significant_change_alert_status instead. Example: true or false

• disabled - Alerts Disabled
• normal - Normal Alerts
• significant_change - Significant Change Alerts

Slack workspace to send alerts to

Override channel ID for this metric's alerts

Alert status: enabled or disabled.

• enabled - Enabled
• disabled - Disabled

Alert direction: increase only, decrease only, or both (empty = both). Example: "increase", "decrease", or "both"

• `` - Both (Increase and Decrease)
• increase - Increase Only
• decrease - Decrease Only

Predefined function name Example: "get_latency" or "check_critical_deviations"

Python custom code for the metric. Example:

_resul = True
_explanation = None
if  "call_end_reason" in data and data["call_end_reason"] == "customer_satisfaction":
    _result = True
    _explanation = "Customer expressed satisfaction with service"

Vocera defined metric code for the metric. Example: "7fd534f5"

Window size for rolling statistics calculation. Example: 50

Standard deviation multiplier for threshold calculation. Example: 2.0

Alpha value for exponentially weighted moving average (EWMA) calculation. Example: 0.1

When enabled, this metric is automatically assigned to new agents created in the project.

URL-friendly unique identifier in snake_case format. Example: "customer_satisfaction_1562"

Name of the metric. Example: "Customer Satisfaction" or "Appointment Booking"

Description of what the metric measures. Example: "Measures how satisfied customers are with the service provided"

Type of metric

• basic - Basic (Deprecated in favor of LLM Judge)
• custom_prompt - Custom Prompt ( Deprecated in favor of LLM Judge)
• custom_code - Custom Code
• llm_judge - LLM Judge

• binary - Binary
• continuous_qualitative - Continuous Qualitative
• numeric - Numeric
• enum - Enum

Whether this metric requires audio analysis. Example: true or false

Evaluation prompt for the metric. Example: "Evaluate customer satisfaction based on conversation"

• always - Always
• automatic - Automatic
• custom - Custom

Type of trigger evaluation: LLM judge or custom code. Only used when evaluation_trigger is CUSTOM. Example: "llm_judge" or "custom_code"

• llm_judge - LLM Judge
• custom_code - Custom Code

Evaluation trigger prompt for the metric. Example: "Evaluate metric only if call ended reason is main-agent-ended-call"

Python custom code to determine metric relevance. Code should set _result (bool) and _explanation (str). Example:

_result = True
_explanation = "Metric is relevant"
if "call_end_reason" in data and data["call_end_reason"] == "customer-hung-up":
    _result = False
    _explanation = "Customer hung up, metric not applicable"

Priority assignment prompt for the metric.

The overall score for this metric across all test sets

The total score for this metric

Knowledge base files associated with this metric

Enable this metric for observability. Example: true or false

Enable this metric for simulations. Example: true or false

Enable sampling for this metric using its sample_rate, or the project sample rate when unset

Sampling rate for this metric (0.0 to 1.0). Overrides the project sample rate when set.

Enable alerts for this metric when it fails (value=false). Only applicable to binary metrics (eval_type=binary). For other metric types, use significant_change_alert_status instead. Example: true or false

• disabled - Alerts Disabled
• normal - Normal Alerts
• significant_change - Significant Change Alerts

Slack workspace to send alerts to

Override channel ID for this metric's alerts

Alert status: enabled or disabled.

• enabled - Enabled
• disabled - Disabled

Alert direction: increase only, decrease only, or both (empty = both). Example: "increase", "decrease", or "both"

• `` - Both (Increase and Decrease)
• increase - Increase Only
• decrease - Decrease Only

Predefined function name Example: "get_latency" or "check_critical_deviations"

Python custom code for the metric. Example:

_resul = True
_explanation = None
if  "call_end_reason" in data and data["call_end_reason"] == "customer_satisfaction":
    _result = True
    _explanation = "Customer expressed satisfaction with service"

Vocera defined metric code for the metric. Example: "7fd534f5"

Window size for rolling statistics calculation. Example: 50

Standard deviation multiplier for threshold calculation. Example: 2.0

Alpha value for exponentially weighted moving average (EWMA) calculation. Example: 0.1

When enabled, this metric is automatically assigned to new agents created in the project.