namestring required
Name of the metric.
Example:
- "Customer Satisfaction"
- "Response Time"
descriptionstring required
Description of what the metric measures.
Example: "Measures how satisfied customers are with the service provided"
codestring
Unique code identifier for the metric
slugstring nullable
URL-friendly unique identifier in snake_case format
type'basic' | 'custom_prompt' | 'custom_code' | 'llm_judge'
- 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
eval_type'binary' | 'continuous_qualitative' | 'numeric' | 'enum'
- binary - Binary
- continuous_qualitative - Continuous Qualitative
- numeric - Numeric
- enum - Enum
audio_enabledboolean
Whether this metric requires audio analysis
promptstring
Evaluation prompt for the metric
function_namestring nullable
Python function name for custom metric evaluation
custom_codestring
Custom evaluation code for the metric
simulation_enabledboolean
Enable this metric for simulations.
Example: true or false
observability_enabledboolean
Enable this metric for observability.
Example: true or false
coststring decimal
Cost in credits for evaluating this metric.
Example: 0.005000
evaluation_trigger'always' | 'automatic' | 'custom'
When to trigger this metric evaluation
- always - Always
- automatic - Automatic
- custom - Custom
evaluation_trigger_promptstring
Prompt to determine when to trigger metric evaluation
category'Speech Quality' | 'Conversation Quality' | 'Accuracy' | 'Customer Experience' | 'null' nullable
Category of the metric
- Speech Quality - Speech Quality
- Conversation Quality - Conversation Quality
- Accuracy - Accuracy
- Customer Experience - Customer Experience
sub_categorystring nullable
Sub category of the metric
organizationinteger nullable