> For the complete documentation index, see [llms.txt](https://docs.umbraco.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.umbraco.com/ai-in-umbraco/testing-and-evaluation/api.md).

# API

Management API endpoints for AI Testing and Evaluation.

The Test API provides endpoints for creating, managing, and executing AI tests, as well as querying and comparing test runs.

## Test Endpoints

| Method | Endpoint                                                                         | Description               |
| ------ | -------------------------------------------------------------------------------- | ------------------------- |
| GET    | [`/tests`](/ai-in-umbraco/testing-and-evaluation/api/list.md)                    | List all tests            |
| GET    | [`/tests/{idOrAlias}`](/ai-in-umbraco/testing-and-evaluation/api/get.md)         | Get a test by ID or alias |
| POST   | [`/tests`](/ai-in-umbraco/testing-and-evaluation/api/create.md)                  | Create a new test         |
| PUT    | [`/tests/{idOrAlias}`](/ai-in-umbraco/testing-and-evaluation/api/update.md)      | Update an existing test   |
| DELETE | [`/tests/{idOrAlias}`](/ai-in-umbraco/testing-and-evaluation/api/delete.md)      | Delete a test             |
| POST   | [`/tests/{idOrAlias}/run`](/ai-in-umbraco/testing-and-evaluation/api/run.md)     | Execute a single test     |
| POST   | [`/tests/run-batch`](/ai-in-umbraco/testing-and-evaluation/api/run-batch.md)     | Execute multiple tests    |
| POST   | [`/tests/run-by-tags`](/ai-in-umbraco/testing-and-evaluation/api/run-by-tags.md) | Execute tests by tags     |

## Test Run Endpoints

| Method | Endpoint                                                                                | Description                                      |
| ------ | --------------------------------------------------------------------------------------- | ------------------------------------------------ |
| GET    | [`/test-runs`](/ai-in-umbraco/testing-and-evaluation/api/runs.md)                       | List test runs (filtered)                        |
| GET    | `/test-runs/{id}`                                                                       | Get a test run by ID                             |
| GET    | `/test-runs/{id}/transcript`                                                            | Get the transcript for a run                     |
| GET    | `/test-runs/latest/{testId}`                                                            | Get the most recent run for a test               |
| GET    | `/test-runs/executions/{executionId}`                                                   | Get execution summary with per-variation metrics |
| DELETE | `/test-runs/{id}`                                                                       | Delete a test run                                |
| POST   | `/test-runs/baseline/{testId}/{testRunId}`                                              | Set a run as the test baseline                   |
| POST   | [`/test-runs/compare`](/ai-in-umbraco/testing-and-evaluation/api/compare.md)            | Compare two test runs                            |
| POST   | [`/test-runs/compare-variations`](/ai-in-umbraco/testing-and-evaluation/api/compare.md) | Compare two variation groups                     |

## Base URL

```
/umbraco/ai/management/api/v1
```

## Test Object

{% code title="Test" %}

```json
{
    "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
    "alias": "test-summarize-quality",
    "name": "Summarization Quality",
    "description": "Validates summarization output quality and format",
    "testFeatureId": "prompt",
    "testTargetId": "d290f1ee-6c54-4b01-90e6-d701748f0851",
    "profileId": "e401f2ff-7d65-5c12-a1f7-e812859a1962",
    "contextIds": [],
    "testFeatureConfig": {
        "variables": {
            "content": "Sample article text for testing..."
        }
    },
    "graders": [
        {
            "id": "a1b2c3d4-0000-0000-0000-000000000001",
            "graderTypeId": "contains",
            "name": "Has bullet points",
            "config": { "searchPattern": "- ", "ignoreCase": true },
            "negate": false,
            "severity": "Error",
            "weight": 1.0
        }
    ],
    "variations": [],
    "runCount": 3,
    "tags": ["quality", "summarization"],
    "baselineRunId": null,
    "version": 1,
    "dateCreated": "2024-06-15T10:30:00Z",
    "dateModified": "2024-06-15T10:30:00Z"
}
```

{% endcode %}

## Properties

| Property            | Type      | Description                              |
| ------------------- | --------- | ---------------------------------------- |
| `id`                | guid      | Unique identifier                        |
| `alias`             | string    | Unique alias for code references         |
| `name`              | string    | Display name                             |
| `description`       | string    | Optional description                     |
| `testFeatureId`     | string    | Test feature harness (`prompt`, `agent`) |
| `testTargetId`      | guid      | ID of the target entity                  |
| `profileId`         | guid      | Default AI profile (optional)            |
| `contextIds`        | guid\[]   | Default AI contexts                      |
| `testFeatureConfig` | object    | Feature-specific configuration (JSON)    |
| `graders`           | array     | Success criteria                         |
| `variations`        | array     | A/B testing overrides                    |
| `runCount`          | int       | Number of runs per execution             |
| `tags`              | string\[] | Organization tags                        |
| `baselineRunId`     | guid      | Baseline run for regression detection    |
| `dateCreated`       | date      | When the test was created (UTC)          |
| `dateModified`      | date      | When the test was last modified (UTC)    |
| `version`           | int       | Current version number                   |

## Related

* [Test Concepts](/ai-in-umbraco/testing-and-evaluation/concepts.md)
* [Graders](/ai-in-umbraco/testing-and-evaluation/graders.md)
* [Variations](/ai-in-umbraco/testing-and-evaluation/variations.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.umbraco.com/ai-in-umbraco/testing-and-evaluation/api.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.