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 Testing›Run Conversational Evaluation
TestMu AI
StatusCommunityBlog
Selenium Automation API
Automated Screenshots API
App Automation API (Real Devices)
Smart UI
Cypress Automation
User Management
Test Manager
HyperExecute
Accessibility Testing
Analytics
Performance Testing
Audit logs
Agent Testing API
Chat Testing

Run Conversational Evaluation

Run conversational evaluation for the workflow's chat scenarios and persist the results. Poll GET /api/evaluation-results/{workflow_id} for the outcome.

POST
/api/run-conversational-evaluation/{workflow_id}
Run Conversational Evaluation
curl --request POST \
  --url "https://agent-testing.lambdatest.com/api/run-conversational-evaluation/{workflow_id}" \
  --header "Authorization: Basic <encoded-value>" \
  --header "Content-Type: application/json" \
  --data '{
    "workflow_id": "<workflow_id>",
    "project_id": "<project_id>",
    "request": "<request>",
    "responseSchema": "<responseSchema>",
    "api_config": "<api_config>",
    "metrics": [],
    "suite_id": "<suite_id>",
    "endpoint_profile_id": "<endpoint_profile_id>",
    "test_profile_id": "<test_profile_id>",
    "scenario_ids": []
  }'
{
  "success": true,
  "message": "<string>",
  "data": {}
}

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

Body

application/json
workflow_idstringrequired
project_idstringrequired

Project ID associated with the workflow

requeststring

Request data for the evaluation (cURL command as JSON). Required if endpoint_profile_id is not provided.

responseSchemastring

Response schema for the evaluation as a JSON string

api_configobject

API configuration for the evaluation

metricsarray

List of metrics to evaluate. If not provided, all available metrics will be used.

suite_idstring

Optional suite_id for suite-based evaluations

endpoint_profile_idstring

ID of the endpoint profile to use for API configuration. If provided, 'request' field is ignored.

test_profile_idstring

ID of the test profile to use for variable data (e.g., mobile number, OTP).

scenario_idsarray

Optional list of specific scenario IDs to run — for example, to re-run only failed / NO-RESULTS scenarios. When provided, only these scenarios are packaged and run; composes with suite_id (suite filter applies first).

Response

application/json

Successful Response

successbooleanrequired

Whether the operation was successful

messagestringrequired

Response message

dataobject

Response data

Run Conversational Evaluation
curl --request POST \
  --url "https://agent-testing.lambdatest.com/api/run-conversational-evaluation/{workflow_id}" \
  --header "Authorization: Basic <encoded-value>" \
  --header "Content-Type: application/json" \
  --data '{
    "workflow_id": "<workflow_id>",
    "project_id": "<project_id>",
    "request": "<request>",
    "responseSchema": "<responseSchema>",
    "api_config": "<api_config>",
    "metrics": [],
    "suite_id": "<suite_id>",
    "endpoint_profile_id": "<endpoint_profile_id>",
    "test_profile_id": "<test_profile_id>",
    "scenario_ids": []
  }'
{
  "success": true,
  "message": "<string>",
  "data": {}
}