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

# Remove Check Eval

> Drop one eval from an environment's promotion checks.

### Overview

Removes a single eval from the checks that gate promotion into an environment, leaving the rest of the roster in place. Use [Set Agent Checks](/api-v2/put/agents-id-environments-env-checks) to replace the whole roster instead, or [Delete Agent Checks](/api-v2/delete/agents-id-environments-env-checks) to clear it.

Removing the last eval deletes the environment's check configuration entirely. The response then carries `config` of `null`, and promotion into that environment is no longer gated.

The call is idempotent. Removing an eval that is not on the roster, or one from an environment with no configuration, returns `200` with `removed` set to `false` and changes nothing.

Requires an admin, owner, operator, or prompter role.

### Headers

<ParamField header="authorization" type="string" required>
  Your API key for authentication.
</ParamField>

### Path Parameters

<ParamField path="agent_id" type="string" required>
  The agent's unique identifier.
</ParamField>

<ParamField path="env" type="string" required>
  Which environment's checks to change. Must be `staging` or `production`; `dev` is not gated and returns `400 BAD_REQUEST`.
</ParamField>

<ParamField path="eval_agent_id" type="string" required>
  The eval to remove.
</ParamField>

### Response

<ResponseField name="data.removed" type="boolean">
  `true` when an eval was taken off the roster, `false` when there was nothing to remove.
</ResponseField>

<ResponseField name="data.config" type="object | null">
  The environment's remaining check configuration, in the same shape as [Get Agent Checks](/api-v2/get/agents-id-environments-env-checks). `null` when removing the last eval deleted the configuration.
</ResponseField>

<ResponseField name="errors" type="null | array">
  `null` on success, or a list of error objects if the request failed.
</ResponseField>

<ResponseExample>
  ```json Response theme={null}
  {
    "data": {
      "removed": true,
      "config": {
        "env_type": "production",
        "simulations_count": 5,
        "evals": [
          {
            "eval_agent_id": "3fec6d8e-053b-4d6b-9544-4bf559a13a1a",
            "eval_agent_version_id": "f3a84fb2-81d9-41e7-95e3-3d1f7e44fb31",
            "passing_level": "pass"
          }
        ]
      }
    },
    "errors": null
  }
  ```

  ```json Nothing To Remove theme={null}
  {
    "data": {
      "removed": false,
      "config": null
    },
    "errors": null
  }
  ```

  ```json Invalid Environment theme={null}
  {
    "data": null,
    "errors": [
      {
        "error": "BAD_REQUEST",
        "message": "env must be 'staging' or 'production'"
      }
    ]
  }
  ```

  ```json Not Found theme={null}
  {
    "data": null,
    "errors": [
      {
        "error": "NOT_FOUND",
        "message": "Agent not found"
      }
    ]
  }
  ```
</ResponseExample>

***

Docs for agents: [llms.txt](/llms.txt)