> ## Documentation Index
> Fetch the complete documentation index at: https://veryfront.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Evaluations API

> Define agent evaluations, run them, and inspect results.

Define agent evaluations, run them, and inspect results.

An evaluation definition specifies the target agent, dataset, metrics, and repetitions. Each evaluation run records its own results. Manage agent definitions through the [Agents API](/docs/cloud/rest/apis/agents-api).

Start evaluation runs and read their reports in this section. Use [Runs](/docs/cloud/rest/apis/execution-api#runs) for shared run operations. Send `{}` when no input or configuration is needed.

## Evaluation Definitions

List and create evaluation definitions stored in project source. Read the source document to inspect its dataset, metrics, and editable fields, then update supported fields.

| Endpoint | Methods | Description |
| - | - | - |
| `/projects/{project_reference}/evals` | [GET](/docs/cloud/rest/api-reference/evaluation-definitions/list-evaluations), [POST](/docs/cloud/rest/api-reference/evaluation-definitions/create-evaluation) | List evaluations; Create evaluation |
| `/projects/{project_reference}/evals/{eval_id}/source` | [GET](/docs/cloud/rest/api-reference/evaluation-definitions/get-evaluation-source), [PATCH](/docs/cloud/rest/api-reference/evaluation-definitions/update-evaluation-source) | Get evaluation source; Update evaluation source |

[Back to REST API reference](/docs/cloud/rest)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.