For AI agents and LLMs: a machine-readable index is available at llms.txt. A plain-Markdown version of any documentation page is available by appending .md to its URL.
Skip to main content
Chat TestingGet evaluation results for a workflow
TestMu AI
StatusCommunityBlog
Chat Testing

Get evaluation results for a workflow

Get the conversational-evaluation results for the workflow's chat scenarios, including per-scenario verdicts and metrics.

GET
/api/evaluation-results/{workflow_id}
Get evaluation results for a workflow
curl --request GET \
--url "https://agent-testing.lambdatest.com/api/evaluation-results/{workflow_id}" \
--header "Authorization: Basic <encoded-value>"
{
"success": true,
"message": "Evaluation results retrieved successfully from the database.",
"data": {
"evaluation_results": {
"results": [
{
"scenario_id": "scn_2b8d4f",
"scenario_title": "Refund policy question",
"overall_score": 0.86,
"status": "pass",
"conversation_history": [
{
"role": "user",
"content": "What is your refund policy?"
},
{
"role": "assistant",
"content": "You can return items within 30 days."
}
]
}
]
},
"overall_score_threshold": 0.5
}
}

Authorizations

Authorizationstringheaderrequired

Basic authentication header of the form Basic <encoded-value>, where <encoded-value> is the base64-encoded string username:password.

Path Parameters

workflow_idstringrequired

Query Parameters

project_idstring
suite_idstring

Response

application/json

`data.evaluation_results` carries the stored results (an object with a `results` list, or an empty list when none exist) plus the project's effective threshold config, `overall_score_threshold`, and a top-level `hyperexecute_url` when a job is linked.

successbooleanrequired

Whether the operation was successful

messagestringrequired

Response message

dataobject

Response data

Get evaluation results for a workflow
curl --request GET \
--url "https://agent-testing.lambdatest.com/api/evaluation-results/{workflow_id}" \
--header "Authorization: Basic <encoded-value>"
{
"success": true,
"message": "Evaluation results retrieved successfully from the database.",
"data": {
"evaluation_results": {
"results": [
{
"scenario_id": "scn_2b8d4f",
"scenario_title": "Refund policy question",
"overall_score": 0.86,
"status": "pass",
"conversation_history": [
{
"role": "user",
"content": "What is your refund policy?"
},
{
"role": "assistant",
"content": "You can return items within 30 days."
}
]
}
]
},
"overall_score_threshold": 0.5
}
}