from meibel import MeibelClient
client = MeibelClient(api_key="your-api-key")
result = client.confidence_scoring.get_scoring_jobs_summary()
print(result){
"primary_field": "<string>",
"primary_value": "<string>",
"secondary_field": "<string>",
"secondary_value": "<string>",
"status": "<string>",
"aggregate_score": 123,
"module_scores": {},
"n_jobs_per_module": {},
"jobs": [
{
"job_id": "<string>",
"agent_identity_context": {
"customer_id": "<string>",
"project_id": "<string>",
"agent_name": "<string>",
"agent_version": "<string>",
"agent_session_id": "<string>",
"agent_workflow_name": "<string>",
"agent_workflow_version": "<string>",
"agent_workflow_session_id": "<string>",
"tool_id": "<string>",
"tool_instance_id": "<string>",
"tool_execution_id": "<string>"
},
"module": "<string>",
"input_value": "<string>",
"output_value": "<string>",
"status": "<string>",
"scoring_config": "<unknown>",
"score": 123
}
]
}Get an aggregated summary of confidence scores. Requires a primary filter; an optional secondary filter narrows results further. Filters use the format “field:value”, where field is any identity context field name.
from meibel import MeibelClient
client = MeibelClient(api_key="your-api-key")
result = client.confidence_scoring.get_scoring_jobs_summary()
print(result){
"primary_field": "<string>",
"primary_value": "<string>",
"secondary_field": "<string>",
"secondary_value": "<string>",
"status": "<string>",
"aggregate_score": 123,
"module_scores": {},
"n_jobs_per_module": {},
"jobs": [
{
"job_id": "<string>",
"agent_identity_context": {
"customer_id": "<string>",
"project_id": "<string>",
"agent_name": "<string>",
"agent_version": "<string>",
"agent_session_id": "<string>",
"agent_workflow_name": "<string>",
"agent_workflow_version": "<string>",
"agent_workflow_session_id": "<string>",
"tool_id": "<string>",
"tool_instance_id": "<string>",
"tool_execution_id": "<string>"
},
"module": "<string>",
"input_value": "<string>",
"output_value": "<string>",
"status": "<string>",
"scoring_config": "<unknown>",
"score": 123
}
]
}Documentation Index
Fetch the complete documentation index at: https://docs.meibel.ai/llms.txt
Use this file to discover all available pages before exploring further.
Primary filter in "field:value" format, where field is an identity context field name (e.g. "agent_name:my-agent" or "agent_session_id:sess_abc123").
Optional secondary filter in the same "field:value" format to further narrow results (e.g. "agent_version:1.2.0").
Successful Response
Aggregated summary of scoring jobs matching one or two identity context filters.
The identity context field used as the primary filter (e.g. "agent_name").
The value matched by the primary filter.
An optional second identity context field used to further narrow results.
The value matched by the secondary filter.
Overall status across the matched scoring jobs. Null if no jobs matched the filters.
Average score across all completed jobs matching the filters.
Average score per scoring module, keyed by module name.
Show child attributes
Number of completed scoring jobs per module.
Show child attributes
The individual scoring job records matching the filters.
Show child attributes
Was this page helpful?