POST
/
v1
/
tests
JavaScript
import Semilattice from 'semilattice';

const client = new Semilattice({
  apiKey: 'My API Key',
});

const apiResponseListTests = await client.tests.create({
  population_id: 'population_id',
  tests: {
    ground_answer_counts: { foo: 0 },
    ground_answer_sample_size: 0,
    question: 'question',
    question_options: { question_type: 'single-choice' },
  },
});

console.log(apiResponseListTests.data);
{
  "data": [
    {
      "id": "b8b3e8cb-4c67-40d7-8350-3eac3c2b127d",
      "batch": "1e6bfe22-40d9-46c4-b241-9e1d7d5c5560",
      "created_at": "2025-06-23T15:40:52Z",
      "test_started_at": "2025-06-23T15:44:10Z",
      "test_finished_at": "2025-06-23T15:45:30Z",
      "ground_answer_counts": {
        "Tech debt": 58,
        "Unclear error messages": 42
      },
      "ground_answer_percentages": {
        "Tech debt": 0.58,
        "Unclear error messages": 0.42
      },
      "population": "af8917b4-a09c-41f9-9c9f-c4c40c1f7415",
      "simulation_engine": "answers-1",
      "status": "Predicted",
      "public": false,
      "answer_options": [
        "Tech debt",
        "Unclear error messages"
      ],
      "population_name": "Developers",
      "question": "Tech debt or unclear error messages, what's worse?",
      "question_options": {
        "question_type": "single-choice"
      },
      "accuracy": 0.8528,
      "squared_error": 0.1607,
      "root_mean_squared_error": 0.1607,
      "simulated_answer_percentages": {
        "Tech debt": 0.5488,
        "Unclear error messages": 0.4512
      },
      "predicted_answer_percentages": {
        "Tech debt": 0.5488,
        "Unclear error messages": 0.4512
      },
      "information_loss": 0.0043,
      "normalised_information_loss": 0.051
    }
  ],
  "errors": [
    {
      "code": "<string>",
      "message": "<string>"
    }
  ]
}

Headers

authorization
string

Body

application/json

Parameters for one or more test predictions you'd like to run. Accepts either a single object or a list.

population_id
string
required

ID of the population model against which to run the simulation

tests
required

One or more test predictions to run.

batch
object | null

Optional batch details to apply to these predictions. If provided, a batch object will be created.

Response

Successful Response

data
TestsResponse · object[] | null

The primary response payload. Contains the result of the request if successful.

errors
ErrorResponse · object[] | null

List of structured error messages, if any occurred during the request.