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

# Manage evaluators

The `eval evaluator` command group manages evaluators (the judging models that assign scores): browse built-in templates, list and show existing evaluators, derive a new evaluator from a template, and delete evaluators. An evaluator is typically a prompt with a scoring rubric backed by a large-model endpoint; it takes several input fields (such as `input`, `output`, `reference_output`) and produces a score.

<Note>
  All subcommands share `-p, --project <name>` (project name, default `default`) and `--json` (output raw JSON).
</Note>

## evaluator templates

Browse the platform's built-in evaluator templates as a starting point for creating your own evaluators.

```bash lines theme={null}
agentkit eval evaluator templates
```

## evaluator list

List the evaluators in your current project.

```bash lines theme={null}
agentkit eval evaluator list
```

## evaluator show

Show details of an evaluator: the rubric prompt, model configuration, and input field schema.

| Flag / Argument | Description | Default |
| - | - | - |
| `<id>` | Evaluator id or name (required) | None |

```bash lines theme={null}
agentkit eval evaluator show relevance
```

## evaluator create

Create an evaluator. The simplest way is to clone the rubric and input schema from a built-in template, then point it at your own model endpoint.

| Flag / Argument | Description | Default |
| - | - | - |
| `--name <name>` | Evaluator name (required) | None |
| `--from-template <id\|name>` | Clone the rubric and input schema from a built-in template | None |
| `--model <endpoint>` | Ark model endpoint id (`ep-…`) used as the judge | None |
| `--prompt-file <path>` | Custom rubric text file (overrides the template prompt) | None |
| `--description <text>` | Evaluator description | None |

You must provide at least one of `--from-template` or `--prompt-file`.

```bash lines theme={null}
# Derive from the built-in "relevance" template and swap in your own model endpoint
agentkit eval evaluator create --name relevance --from-template "relevance" --model ep-xxxxxxxx
```

<Tip>
  Reference input fields in the prompt with placeholders like <code>{'{{input}}'}</code>, <code>{'{{output}}'}</code>, and <code>{'{{reference_output}}'}</code>; these field names are the evaluator's input schema and are mapped automatically during [`eval run`](/productions/agentkit-cli/archives/0.50.0/en/commands/eval/run).
</Tip>

## evaluator delete

Delete an evaluator. (Alias: `rm`)

| Flag / Argument | Description | Default |
| - | - | - |
| `<id>` | Evaluator id or name (required) | None |
| `-y, --yes` | Skip the confirmation prompt | `false` |

```bash lines theme={null}
agentkit eval evaluator delete relevance -y
```