---
title: "Evaluate"
method: POST
path: "/ai/evaluator/evaluate"
tags: ["AI - Evaluator"]
---

# Evaluate

`POST /ai/evaluator/evaluate`

Run an AI evaluator

## Request body

- object — Body schema for the evaluator evaluate endpoint. Provide either `messageUuid` or `output` as the thing to grade.
  - `messageUuid` string, uuid — When set, the output to grade is read from this message's text.
  - `output` string — Text to grade directly. Used when `messageUuid` is not provided.
  - `rubric` string, required — Natural-language criteria describing what a good output looks like.
  - `context` string — Optional extra context to ground the evaluation.

## Response `200`

Successful response

- object
  - `evaluation` object, required
    - `score` number, required
    - `passed` boolean, required
    - `criteria` object[], required
      - `name` string, required
      - `passed` boolean, required
      - `reason` string, required
    - `summary` string, required

## Other responses

- `400` — Bad request
- `401` — Unauthorized
- `404` — Not found
- `500` — Internal server error

---

[API](https://skmtc.net/getcargo/apis/cargo-api.md) · [All operations](https://skmtc.net/getcargo/apis/cargo-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/getcargo/cargo-api/revisions/1d5a19e01d83/schema)